back out torch.no_grad()

- Set min size for floating gallery panel
- Correct the default pinned width (it cannot be less than the min width
and this was sometimes happening during window resize)

.github/workflows/test-invoke-pip-skip.yml

@@ -1,10 +1,16 @@
 name: Test invoke.py pip
+
+# This is a dummy stand-in for the actual tests
+# we don't need to run python tests on non-Python changes
+# But PRs require passing tests to be mergeable
+
 on:
   pull_request:
     paths:
       - '**'
       - '!pyproject.toml'
       - '!invokeai/**'
+      - '!tests/**'
       - 'invokeai/frontend/web/**'
   merge_group:
   workflow_dispatch:
@@ -19,48 +25,26 @@ jobs:
     strategy:
       matrix:
         python-version:
-          # - '3.9'
           - '3.10'
         pytorch:
-          # - linux-cuda-11_6
           - linux-cuda-11_7
           - linux-rocm-5_2
           - linux-cpu
           - macos-default
           - windows-cpu
-          # - windows-cuda-11_6
-          # - windows-cuda-11_7
         include:
-          # - pytorch: linux-cuda-11_6
-          #   os: ubuntu-22.04
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
-          #   github-env: $GITHUB_ENV
           - pytorch: linux-cuda-11_7
             os: ubuntu-22.04
-            github-env: $GITHUB_ENV
           - pytorch: linux-rocm-5_2
             os: ubuntu-22.04
-            extra-index-url: 'https://download.pytorch.org/whl/rocm5.2'
-            github-env: $GITHUB_ENV
           - pytorch: linux-cpu
             os: ubuntu-22.04
-            extra-index-url: 'https://download.pytorch.org/whl/cpu'
-            github-env: $GITHUB_ENV
           - pytorch: macos-default
             os: macOS-12
-            github-env: $GITHUB_ENV
           - pytorch: windows-cpu
             os: windows-2022
-            github-env: $env:GITHUB_ENV
-          # - pytorch: windows-cuda-11_6
-          #   os: windows-2022
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
-          #   github-env: $env:GITHUB_ENV
-          # - pytorch: windows-cuda-11_7
-          #   os: windows-2022
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu117'
-          #   github-env: $env:GITHUB_ENV
     name: ${{ matrix.pytorch }} on ${{ matrix.python-version }}
     runs-on: ${{ matrix.os }}
     steps:
-      - run: 'echo "No build required"'
+      - name: skip
+        run: echo "no build required"

.github/workflows/test-invoke-pip.yml

@@ -11,6 +11,7 @@ on:
     paths:
       - 'pyproject.toml'
       - 'invokeai/**'
+      - 'tests/**'
       - '!invokeai/frontend/web/**'
     types:
       - 'ready_for_review'
@@ -32,19 +33,12 @@ jobs:
           # - '3.9'
           - '3.10'
         pytorch:
-          # - linux-cuda-11_6
           - linux-cuda-11_7
           - linux-rocm-5_2
           - linux-cpu
           - macos-default
           - windows-cpu
-          # - windows-cuda-11_6
-          # - windows-cuda-11_7
         include:
-          # - pytorch: linux-cuda-11_6
-          #   os: ubuntu-22.04
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
-          #   github-env: $GITHUB_ENV
           - pytorch: linux-cuda-11_7
             os: ubuntu-22.04
             github-env: $GITHUB_ENV
@@ -62,14 +56,6 @@ jobs:
           - pytorch: windows-cpu
             os: windows-2022
             github-env: $env:GITHUB_ENV
-          # - pytorch: windows-cuda-11_6
-          #   os: windows-2022
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
-          #   github-env: $env:GITHUB_ENV
-          # - pytorch: windows-cuda-11_7
-          #   os: windows-2022
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu117'
-          #   github-env: $env:GITHUB_ENV
     name: ${{ matrix.pytorch }} on ${{ matrix.python-version }}
     runs-on: ${{ matrix.os }}
     env:
@@ -100,40 +86,38 @@ jobs:
         id: run-pytest
         run: pytest
 
-      - name: run invokeai-configure
-        id: run-preload-models
-        env:
-          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGINGFACE_TOKEN }}
-        run: >
-          invokeai-configure
-          --yes
-          --default_only
-          --full-precision
-        # can't use fp16 weights without a GPU
+      # - name: run invokeai-configure
+      #   env:
+      #     HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGINGFACE_TOKEN }}
+      #   run: >
+      #     invokeai-configure
+      #     --yes
+      #     --default_only
+      #     --full-precision
+      #   # can't use fp16 weights without a GPU
 
-      - name: run invokeai
-        id: run-invokeai
-        env:
-          # Set offline mode to make sure configure preloaded successfully.
-          HF_HUB_OFFLINE: 1
-          HF_DATASETS_OFFLINE: 1
-          TRANSFORMERS_OFFLINE: 1
-          INVOKEAI_OUTDIR: ${{ github.workspace }}/results
-        run: >
-          invokeai
-          --no-patchmatch
-          --no-nsfw_checker
-          --precision=float32
-          --always_use_cpu
-          --use_memory_db
-          --outdir ${{ env.INVOKEAI_OUTDIR }}/${{ matrix.python-version }}/${{ matrix.pytorch }}
-          --from_file ${{ env.TEST_PROMPTS }}
+      # - name: run invokeai
+      #   id: run-invokeai
+      #   env:
+      #     # Set offline mode to make sure configure preloaded successfully.
+      #     HF_HUB_OFFLINE: 1
+      #     HF_DATASETS_OFFLINE: 1
+      #     TRANSFORMERS_OFFLINE: 1
+      #     INVOKEAI_OUTDIR: ${{ github.workspace }}/results
+      #   run: >
+      #     invokeai
+      #     --no-patchmatch
+      #     --no-nsfw_checker
+      #     --precision=float32
+      #     --always_use_cpu
+      #     --use_memory_db
+      #     --outdir ${{ env.INVOKEAI_OUTDIR }}/${{ matrix.python-version }}/${{ matrix.pytorch }}
+      #     --from_file ${{ env.TEST_PROMPTS }}
 
-      - name: Archive results
-        id: archive-results
-        env:
-          INVOKEAI_OUTDIR: ${{ github.workspace }}/results
-        uses: actions/upload-artifact@v3
-        with:
-          name: results
-          path: ${{ env.INVOKEAI_OUTDIR }}
+      # - name: Archive results
+      #   env:
+      #     INVOKEAI_OUTDIR: ${{ github.workspace }}/results
+      #   uses: actions/upload-artifact@v3
+      #   with:
+      #     name: results
+      #     path: ${{ env.INVOKEAI_OUTDIR }}

.gitignore

@@ -201,7 +201,9 @@ checkpoints
 # If it's a Mac
 .DS_Store
 
-invokeai/frontend/web/dist/*
+# LS: the frontend dist files need to be in the repository in order to 
+# do a pip network install
+# invokeai/frontend/web/dist/*
 
 # Let the frontend manage its own gitignore
 !invokeai/frontend/web/*

README.md

@@ -1,8 +1,11 @@
 <div align="center">
 
-![project logo](https://github.com/invoke-ai/InvokeAI/raw/main/docs/assets/invoke_ai_banner.png)
+![project hero](https://github.com/invoke-ai/InvokeAI/assets/31807370/1a917d94-e099-4fa1-a70f-7dd8d0691018)
+
+# Invoke AI - Generative AI for Professional Creatives
+## Image Generation for Stable Diffusion, Custom-Trained Models, and more. 
+  Learn more about us and get started instantly at [invoke.ai](https://invoke.ai)
 
-# InvokeAI: A Stable Diffusion Toolkit
 
 [![discord badge]][discord link]
 
@@ -33,32 +36,32 @@
 
 </div>
 
-_**Note: The UI is not fully functional on `main`. If you need a stable UI based on `main`, use the `pre-nodes` tag while we [migrate to a new backend](https://github.com/invoke-ai/InvokeAI/discussions/3246).**_
+_**Note: This is an alpha release. Bugs are expected and not all
+features are fully implemented. Please use the GitHub [Issues
+pages](https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen)
+to report unexpected problems. Also note that InvokeAI root directory
+which contains models, outputs and configuration files, has changed
+between the 2.x and 3.x release. If you wish to use your v2.3 root
+directory with v3.0, please follow the directions in [Migrating a 2.3
+root directory to 3.0](#migrating-to-3).**_
 
-InvokeAI is a leading creative engine built to empower professionals and enthusiasts alike. Generate and create stunning visual media using the latest AI-driven technologies. InvokeAI offers an industry leading Web Interface, interactive Command Line Interface, and also serves as the foundation for multiple commercial products.
+InvokeAI is a leading creative engine built to empower professionals
+and enthusiasts alike. Generate and create stunning visual media using
+the latest AI-driven technologies. InvokeAI offers an industry leading
+Web Interface, interactive Command Line Interface, and also serves as
+the foundation for multiple commercial products.
 
-**Quick links**: [[How to Install](https://invoke-ai.github.io/InvokeAI/#installation)] [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>] [<a href="https://invoke-ai.github.io/InvokeAI/">Documentation and Tutorials</a>] [<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>] [<a href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion, Ideas & Q&A</a>]
-
-_Note: InvokeAI is rapidly evolving. Please use the
-[Issues](https://github.com/invoke-ai/InvokeAI/issues) tab to report bugs and make feature
-requests. Be sure to use the provided templates. They will help us diagnose issues faster._
-
-## FOR DEVELOPERS - MIGRATING TO THE 3.0.0 MODELS FORMAT
-
-The models directory and models.yaml have changed. To migrate to the
-new layout, please follow this recipe:
-
-1. Run `python scripts/migrate_models_to_3.0.py <path_to_root_directory>
-
-2. This will create a new models directory named `models-3.0` and a
-   new config directory named `models.yaml-3.0`, both in the current
-   working directory. If you prefer to name them something else, pass
-   the `--dest-directory` and/or `--dest-yaml` arguments.
-
-3. Check that the new models directory and yaml file look ok.
-
-4. Replace the existing directory and file, keeping backup copies just in
-case.
+**Quick links**: [[How to
+  Install](https://invoke-ai.github.io/InvokeAI/#installation)] [<a
+  href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>] [<a
+  href="https://invoke-ai.github.io/InvokeAI/">Documentation and
+  Tutorials</a>] [<a
+  href="https://github.com/invoke-ai/InvokeAI/">Code and
+  Downloads</a>] [<a
+  href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>]
+  [<a
+  href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion,
+  Ideas & Q&A</a>]
 
 <div align="center">
 
@@ -68,22 +71,30 @@ case.
 
 ## Table of Contents
 
-1. [Quick Start](#getting-started-with-invokeai)
-2. [Installation](#detailed-installation-instructions)
-3. [Hardware Requirements](#hardware-requirements)
-4. [Features](#features)
-5. [Latest Changes](#latest-changes)
-6. [Troubleshooting](#troubleshooting)
-7. [Contributing](#contributing)
-8. [Contributors](#contributors)
-9. [Support](#support)
-10. [Further Reading](#further-reading)
+Table of Contents 📝
 
-## Getting Started with InvokeAI
+**Getting Started**
+1. 🏁 [Quick Start](#quick-start) 
+3. 🖥️ [Hardware Requirements](#hardware-requirements) 
+
+**More About Invoke**
+1. 🌟 [Features](#features) 
+2. 📣 [Latest Changes](#latest-changes) 
+3. 🛠️ [Troubleshooting](#troubleshooting) 
+
+**Supporting the Project**
+1. 🤝 [Contributing](#contributing) 
+2. 👥 [Contributors](#contributors) 
+3. 💕 [Support](#support) 
+
+## Quick Start
 
 For full installation and upgrade instructions, please see:
 [InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/)
 
+If upgrading from version 2.3, please read [Migrating a 2.3 root
+directory to 3.0](#migrating-to-3) first.
+
 ### Automatic Installer (suggested for 1st time users)
 
 1. Go to the bottom of the [Latest Release Page](https://github.com/invoke-ai/InvokeAI/releases/latest)
@@ -92,9 +103,8 @@ For full installation and upgrade instructions, please see:
 
 3. Unzip the file.
 
-4. If you are on Windows, double-click on the `install.bat` script. On
-macOS, open a Terminal window, drag the file `install.sh` from Finder
-into the Terminal, and press return. On Linux, run `install.sh`.
+4. **Windows:** double-click on the `install.bat` script. **macOS:** Open a Terminal window, drag the file `install.sh` from Finder
+into the Terminal, and press return. **Linux:** run `install.sh`.
 
 5. You'll be asked to confirm the location of the folder in which
 to install InvokeAI and its image generation model files. Pick a
@@ -120,7 +130,7 @@ and go to http://localhost:9090.
 
 10. Type `banana sushi` in the box on the top left and click `Invoke`
 
-### Command-Line Installation (for users familiar with Terminals)
+### Command-Line Installation (for developers and users familiar with Terminals)
 
 You must have Python 3.9 or 3.10 installed on your machine. Earlier or later versions are
 not supported.
@@ -196,7 +206,7 @@ not supported.
 Be sure to activate the virtual environment each time before re-launching InvokeAI,
 using `source .venv/bin/activate` or `.venv\Scripts\activate`.
 
-### Detailed Installation Instructions
+## Detailed Installation Instructions
 
 This fork is supported across Linux, Windows and Macintosh. Linux
 users can use either an Nvidia-based card (with CUDA support) or an
@@ -204,6 +214,87 @@ AMD card (using the ROCm driver). For full installation and upgrade
 instructions, please see:
 [InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_SOURCE/)
 
+<a name="migrating-to-3"></a>
+### Migrating a v2.3 InvokeAI root directory
+
+The InvokeAI root directory is where the InvokeAI startup file,
+installed models, and generated images are stored. It is ordinarily
+named `invokeai` and located in your home directory. The contents and
+layout of this directory has changed between versions 2.3 and 3.0 and
+cannot be used directly.
+
+We currently recommend that you use the installer to create a new root
+directory named differently from the 2.3 one, e.g. `invokeai-3` and
+then use a migration script to copy your 2.3 models into the new
+location. However, if you choose, you can upgrade this directory in
+place.  This section gives both recipes.
+
+#### Creating a new root directory and migrating old models
+
+This is the safer recipe because it leaves your old root directory in
+place to fall back on.
+
+1. Follow the instructions above to create and install InvokeAI in a
+directory that has a different name from the 2.3 invokeai directory.
+In this example, we will use "invokeai-3"
+
+2. When you are prompted to select models to install, select a minimal
+set of models, such as stable-diffusion-v1.5 only.
+
+3. After installation is complete launch `invokeai.sh` (Linux/Mac) or
+`invokeai.bat` and select option 8 "Open the developers console". This
+will take you to the command line.
+
+4. Issue the command `invokeai-migrate3 --from /path/to/v2.3-root --to
+/path/to/invokeai-3-root`. Provide the correct `--from` and `--to`
+paths for your v2.3 and v3.0 root directories respectively.
+
+This will copy and convert your old models from 2.3 format to 3.0
+format and create a new `models` directory in the 3.0 directory. The
+old models directory (which contains the models selected at install
+time) will be renamed `models.orig` and can be deleted once you have
+confirmed that the migration was successful.
+
+#### Migrating in place
+
+For the adventurous, you may do an in-place upgrade from 2.3 to 3.0
+without touching the command line. The recipe is as follows>
+
+1. Launch the InvokeAI launcher script in your current v2.3 root directory.
+
+2. Select option [9] "Update InvokeAI" to bring up the updater dialog.
+
+3a. During the alpha release phase, select option [3] and manually
+enter the tag name `v3.0.0+a2`.
+
+3b. Once 3.0 is released, select option [1] to upgrade to the latest release.
+
+4. Once the upgrade is finished you will be returned to the launcher
+menu. Select option [7] "Re-run the configure script to fix a broken
+install or to complete a major upgrade".
+
+This will run the configure script against the v2.3 directory and
+update it to the 3.0 format. The following files will be replaced:
+
+  - The invokeai.init file, replaced by invokeai.yaml
+  - The models directory
+  - The configs/models.yaml model index
+  
+The original versions of these files will be saved with the suffix
+".orig" appended to the end. Once you have confirmed that the upgrade
+worked, you can safely remove these files. Alternatively you can
+restore a working v2.3 directory by removing the new files and
+restoring the ".orig" files' original names.
+
+#### Migration Caveats
+
+The migration script will migrate your invokeai settings and models,
+including textual inversion models, LoRAs and merges that you may have
+installed previously. However it does **not** migrate the generated
+images stored in your 2.3-format outputs directory. The released
+version of 3.0 is expected to have an interface for importing an
+entire directory of image files as a batch.
+
 ## Hardware Requirements
 
 InvokeAI is supported across Linux, Windows and macOS. Linux
@@ -222,13 +313,9 @@ We do not recommend the GTX 1650 or 1660 series video cards. They are
 unable to run in half-precision mode and do not have sufficient VRAM
 to render 512x512 images.
 
-### Memory
+**Memory** - At least 12 GB Main Memory RAM.
 
-- At least 12 GB Main Memory RAM.
-
-### Disk
-
-- At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
+**Disk** - At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
 
 ## Features
 
@@ -244,7 +331,7 @@ The Unified Canvas is a fully integrated canvas implementation with support for
 
 ### *Advanced Prompt Syntax*
 
-InvokeAI's advanced prompt syntax allows for token weighting, cross-attention control, and prompt blending, allowing for fine-tuned tweaking of your invocations and exploration of the latent space.
+Invoke AI's advanced prompt syntax allows for token weighting, cross-attention control, and prompt blending, allowing for fine-tuned tweaking of your invocations and exploration of the latent space. 
 
 ### *Command Line Interface*
 
@@ -254,16 +341,12 @@ For users utilizing a terminal-based environment, or who want to take advantage
 
 - *Support for both ckpt and diffusers models*
 - *SD 2.0, 2.1 support*
-- *Noise Control & Tresholding*
-- *Popular Sampler Support*
 - *Upscaling & Face Restoration Tools*
 - *Embedding Manager & Support*
 - *Model Manager & Support*
-
-### Coming Soon
-
-- *Node-Based Architecture & UI*
-- And more...
+- *Node-Based Architecture*
+- *Node-Based Plug-&-Play UI (Beta)*
+- *Boards & Gallery Management
 
 ### Latest Changes
 
@@ -271,12 +354,12 @@ For our latest changes, view our [Release
 Notes](https://github.com/invoke-ai/InvokeAI/releases) and the
 [CHANGELOG](docs/CHANGELOG.md).
 
-## Troubleshooting
+### Troubleshooting
 
 Please check out our **[Q&A](https://invoke-ai.github.io/InvokeAI/help/TROUBLESHOOT/#faq)** to get solutions for common installation
 problems and other issues.
 
-## Contributing
+## 🤝 Contributing
 
 Anyone who wishes to contribute to this project, whether documentation, features, bug fixes, code
 cleanup, testing, or code reviews, is very much encouraged to do so.
@@ -295,14 +378,12 @@ to become part of our community.
 
 Welcome to InvokeAI!
 
-### Contributors
+### 👥 Contributors
 
 This fork is a combined effort of various people from across the world.
 [Check out the list of all these amazing people](https://invoke-ai.github.io/InvokeAI/other/CONTRIBUTORS/). We thank them for
 their time, hard work and effort.
 
-Thanks to [Weblate](https://weblate.org/) for generously providing translation services to this project.
-
 ### Support
 
 For support, please use this repository's GitHub Issues tracking service, or join the Discord.

docs/CHANGELOG.md

@@ -4,6 +4,236 @@ title: Changelog
 
 # :octicons-log-16: **Changelog**
 
+## v2.3.5 <small>(22 May 2023)</small>
+
+This release (along with the post1 and post2 follow-on releases) expands support for additional LoRA and LyCORIS models, upgrades diffusers versions, and fixes a few bugs.
+
+### LoRA and LyCORIS Support Improvement
+
+    A number of LoRA/LyCORIS fine-tune files (those which alter the text encoder as well as the unet model) were not having the desired effect in InvokeAI. This bug has now been fixed. Full documentation of LoRA support is available at InvokeAI LoRA Support.
+    Previously, InvokeAI did not distinguish between LoRA/LyCORIS models based on Stable Diffusion v1.5 vs those based on v2.0 and 2.1, leading to a crash when an incompatible model was loaded. This has now been fixed. In addition, the web pulldown menus for LoRA and Textual Inversion selection have been enhanced to show only those files that are compatible with the currently-selected Stable Diffusion model.
+    Support for the newer LoKR LyCORIS files has been added.
+
+### Library Updates and Speed/Reproducibility Advancements
+The major enhancement in this version is that NVIDIA users no longer need to decide between speed and reproducibility. Previously, if you activated the Xformers library, you would see improvements in speed and memory usage, but multiple images generated with the same seed and other parameters would be slightly different from each other. This is no longer the case. Relative to 2.3.5 you will see improved performance when running without Xformers, and even better performance when Xformers is activated. In both cases, images generated with the same settings will be identical.
+
+Here are the new library versions:
+Library 	Version
+Torch 	2.0.0
+Diffusers 	0.16.1
+Xformers 	0.0.19
+Compel 	1.1.5
+Other Improvements
+
+### Performance Improvements
+
+    When a model is loaded for the first time, InvokeAI calculates its checksum for incorporation into the PNG metadata. This process could take up to a minute on network-mounted disks and WSL mounts. This release noticeably speeds up the process.
+
+### Bug Fixes
+
+    The "import models from directory" and "import from URL" functionality in the console-based model installer has now been fixed.
+    When running the WebUI, we have reduced the number of times that InvokeAI reaches out to HuggingFace to fetch the list of embeddable Textual Inversion models. We have also caught and fixed a problem with the updater not correctly detecting when another instance of the updater is running 
+
+
+## v2.3.4 <small>(7 April 2023)</small>
+
+What's New in 2.3.4
+
+This features release adds support for LoRA (Low-Rank Adaptation) and LyCORIS (Lora beYond Conventional) models, as well as some minor bug fixes.
+### LoRA and LyCORIS Support
+
+LoRA files contain fine-tuning weights that enable particular styles, subjects or concepts to be applied to generated images. LyCORIS files are an extended variant of LoRA. InvokeAI supports the most common LoRA/LyCORIS format, which ends in the suffix .safetensors. You will find numerous LoRA and LyCORIS models for download at Civitai, and a small but growing number at Hugging Face. Full documentation of LoRA support is available at InvokeAI LoRA Support.( Pre-release note: this page will only be available after release)
+
+To use LoRA/LyCORIS models in InvokeAI:
+
+    Download the .safetensors files of your choice and place in /path/to/invokeai/loras. This directory was not present in earlier version of InvokeAI but will be created for you the first time you run the command-line or web client. You can also create the directory manually.
+
+    Add withLora(lora-file,weight) to your prompts. The weight is optional and will default to 1.0. A few examples, assuming that a LoRA file named loras/sushi.safetensors is present:
+
+family sitting at dinner table eating sushi withLora(sushi,0.9)
+family sitting at dinner table eating sushi withLora(sushi, 0.75)
+family sitting at dinner table eating sushi withLora(sushi)
+
+Multiple withLora() prompt fragments are allowed. The weight can be arbitrarily large, but the useful range is roughly 0.5 to 1.0. Higher weights make the LoRA's influence stronger. Negative weights are also allowed, which can lead to some interesting effects.
+
+    Generate as you usually would! If you find that the image is too "crisp" try reducing the overall CFG value or reducing individual LoRA weights. As is the case with all fine-tunes, you'll get the best results when running the LoRA on top of the model similar to, or identical with, the one that was used during the LoRA's training. Don't try to load a SD 1.x-trained LoRA into a SD 2.x model, and vice versa. This will trigger a non-fatal error message and generation will not proceed.
+
+    You can change the location of the loras directory by passing the --lora_directory option to `invokeai.
+
+### New WebUI LoRA and Textual Inversion Buttons
+
+This version adds two new web interface buttons for inserting LoRA and Textual Inversion triggers into the prompt as shown in the screenshot below.
+
+Clicking on one or the other of the buttons will bring up a menu of available LoRA/LyCORIS or Textual Inversion trigger terms. Select a menu item to insert the properly-formatted withLora() or <textual-inversion> prompt fragment into the positive prompt. The number in parentheses indicates the number of trigger terms currently in the prompt. You may click the button again and deselect the LoRA or trigger to remove it from the prompt, or simply edit the prompt directly.
+
+Currently terms are inserted into the positive prompt textbox only. However, some textual inversion embeddings are designed to be used with negative prompts. To move a textual inversion trigger into the negative prompt, simply cut and paste it.
+
+By default the Textual Inversion menu only shows locally installed models found at startup time in /path/to/invokeai/embeddings. However, InvokeAI has the ability to dynamically download and install additional Textual Inversion embeddings from the HuggingFace Concepts Library. You may choose to display the most popular of these (with five or more likes) in the Textual Inversion menu by going to Settings and turning on "Show Textual Inversions from HF Concepts Library." When this option is activated, the locally-installed TI embeddings will be shown first, followed by uninstalled terms from Hugging Face. See The Hugging Face Concepts Library and Importing Textual Inversion files for more information.
+### Minor features and fixes
+
+This release changes model switching behavior so that the command-line and Web UIs save the last model used and restore it the next time they are launched. It also improves the behavior of the installer so that the pip utility is kept up to date.
+  
+### Known Bugs in 2.3.4
+
+These are known bugs in the release.
+
+    The Ancestral DPMSolverMultistepScheduler (k_dpmpp_2a) sampler is not yet implemented for diffusers models and will disappear from the WebUI Sampler menu when a diffusers model is selected.
+    Windows Defender will sometimes raise Trojan or backdoor alerts for the codeformer.pth face restoration model, as well as the CIDAS/clipseg and runwayml/stable-diffusion-v1.5 models. These are false positives and can be safely ignored. InvokeAI performs a malware scan on all models as they are loaded. For additional security, you should use safetensors models whenever they are available.
+
+
+## v2.3.3 <small>(28 March 2023)</small>
+
+This is a bugfix and minor feature release.
+### Bugfixes
+
+Since version 2.3.2 the following bugs have been fixed:
+Bugs
+
+    When using legacy checkpoints with an external VAE, the VAE file is now scanned for malware prior to loading. Previously only the main model weights file was scanned.
+    Textual inversion will select an appropriate batchsize based on whether xformers is active, and will default to xformers enabled if the library is detected.
+    The batch script log file names have been fixed to be compatible with Windows.
+    Occasional corruption of the .next_prefix file (which stores the next output file name in sequence) on Windows systems is now detected and corrected.
+    Support loading of legacy config files that have no personalization (textual inversion) section.
+    An infinite loop when opening the developer's console from within the invoke.sh script has been corrected.
+    Documentation fixes, including a recipe for detecting and fixing problems with the AMD GPU ROCm driver.
+
+Enhancements
+
+    It is now possible to load and run several community-contributed SD-2.0 based models, including the often-requested "Illuminati" model.
+    The "NegativePrompts" embedding file, and others like it, can now be loaded by placing it in the InvokeAI embeddings directory.
+    If no --model is specified at launch time, InvokeAI will remember the last model used and restore it the next time it is launched.
+    On Linux systems, the invoke.sh launcher now uses a prettier console-based interface. To take advantage of it, install the dialog package using your package manager (e.g. sudo apt install dialog).
+    When loading legacy models (safetensors/ckpt) you can specify a custom config file and/or a VAE by placing like-named files in the same directory as the model following this example:
+
+my-favorite-model.ckpt
+my-favorite-model.yaml
+my-favorite-model.vae.pt      # or my-favorite-model.vae.safetensors
+
+### Known Bugs in 2.3.3
+
+These are known bugs in the release.
+
+    The Ancestral DPMSolverMultistepScheduler (k_dpmpp_2a) sampler is not yet implemented for diffusers models and will disappear from the WebUI Sampler menu when a diffusers model is selected.
+    Windows Defender will sometimes raise Trojan or backdoor alerts for the codeformer.pth face restoration model, as well as the CIDAS/clipseg and runwayml/stable-diffusion-v1.5 models. These are false positives and can be safely ignored. InvokeAI performs a malware scan on all models as they are loaded. For additional security, you should use safetensors models whenever they are available.
+
+
+## v2.3.2 <small>(11 March 2023)</small>
+This is a bugfix and minor feature release.
+
+### Bugfixes
+
+Since version 2.3.1 the following bugs have been fixed:
+
+    Black images appearing for potential NSFW images when generating with legacy checkpoint models and both --no-nsfw_checker and --ckpt_convert turned on.
+    Black images appearing when generating from models fine-tuned on Stable-Diffusion-2-1-base. When importing V2-derived models, you may be asked to select whether the model was derived from a "base" model (512 pixels) or the 768-pixel SD-2.1 model.
+    The "Use All" button was not restoring the Hi-Res Fix setting on the WebUI
+    When using the model installer console app, models failed to import correctly when importing from directories with spaces in their names. A similar issue with the output directory was also fixed.
+    Crashes that occurred during model merging.
+    Restore previous naming of Stable Diffusion base and 768 models.
+    Upgraded to latest versions of diffusers, transformers, safetensors and accelerate libraries upstream. We hope that this will fix the assertion NDArray > 2**32 issue that MacOS users have had when generating images larger than 768x768 pixels. Please report back.
+
+As part of the upgrade to diffusers, the location of the diffusers-based models has changed from models/diffusers to models/hub. When you launch InvokeAI for the first time, it will prompt you to OK a one-time move. This should be quick and harmless, but if you have modified your models/diffusers directory in some way, for example using symlinks, you may wish to cancel the migration and make appropriate adjustments.
+New "Invokeai-batch" script
+
+### Invoke AI Batch
+2.3.2 introduces a new command-line only script called invokeai-batch that can be used to generate hundreds of images from prompts and settings that vary systematically. This can be used to try the same prompt across multiple combinations of models, steps, CFG settings and so forth. It also allows you to template prompts and generate a combinatorial list like:
+
+a shack in the mountains, photograph
+a shack in the mountains, watercolor
+a shack in the mountains, oil painting
+a chalet in the mountains, photograph
+a chalet in the mountains, watercolor
+a chalet in the mountains, oil painting
+a shack in the desert, photograph
+...
+
+If you have a system with multiple GPUs, or a single GPU with lots of VRAM, you can parallelize generation across the combinatorial set, reducing wait times and using your system's resources efficiently (make sure you have good GPU cooling).
+
+To try invokeai-batch out. Launch the "developer's console" using the invoke launcher script, or activate the invokeai virtual environment manually. From the console, give the command invokeai-batch --help in order to learn how the script works and create your first template file for dynamic prompt generation.
+
+
+### Known Bugs in 2.3.2
+
+These are known bugs in the release.
+
+    The Ancestral DPMSolverMultistepScheduler (k_dpmpp_2a) sampler is not yet implemented for diffusers models and will disappear from the WebUI Sampler menu when a diffusers model is selected.
+    Windows Defender will sometimes raise a Trojan alert for the codeformer.pth face restoration model. As far as we have been able to determine, this is a false positive and can be safely whitelisted.
+
+
+## v2.3.1 <small>(22 February 2023)</small>
+This is primarily a bugfix release, but it does provide several new features that will improve the user experience.
+
+### Enhanced support for model management
+
+InvokeAI now makes it convenient to add, remove and modify models. You can individually import models that are stored on your local system, scan an entire folder and its subfolders for models and import them automatically, and even directly import models from the internet by providing their download URLs. You also have the option of designating a local folder to scan for new models each time InvokeAI is restarted.
+
+There are three ways of accessing the model management features:
+
+    From the WebUI, click on the cube to the right of the model selection menu. This will bring up a form that allows you to import models individually from your local disk or scan a directory for models to import.
+
+    Using the Model Installer App
+
+Choose option (5) download and install models from the invoke launcher script to start a new console-based application for model management. You can use this to select from a curated set of starter models, or import checkpoint, safetensors, and diffusers models from a local disk or the internet. The example below shows importing two checkpoint URLs from popular SD sites and a HuggingFace diffusers model using its Repository ID. It also shows how to designate a folder to be scanned at startup time for new models to import.
+
+Command-line users can start this app using the command invokeai-model-install.
+
+    Using the Command Line Client (CLI)
+
+The !install_model and !convert_model commands have been enhanced to allow entering of URLs and local directories to scan and import. The first command installs .ckpt and .safetensors files as-is. The second one converts them into the faster diffusers format before installation.
+
+Internally InvokeAI is able to probe the contents of a .ckpt or .safetensors file to distinguish among v1.x, v2.x and inpainting models. This means that you do not need to include "inpaint" in your model names to use an inpainting model. Note that Stable Diffusion v2.x models will be autoconverted into a diffusers model the first time you use it.
+
+Please see INSTALLING MODELS for more information on model management.
+
+### An Improved Installer Experience
+
+The installer now launches a console-based UI for setting and changing commonly-used startup options:
+
+After selecting the desired options, the installer installs several support models needed by InvokeAI's face reconstruction and upscaling features and then launches the interface for selecting and installing models shown earlier. At any time, you can edit the startup options by launching invoke.sh/invoke.bat and entering option (6) change InvokeAI startup options
+
+Command-line users can launch the new configure app using invokeai-configure.
+
+This release also comes with a renewed updater. To do an update without going through a whole reinstallation, launch invoke.sh or invoke.bat and choose option (9) update InvokeAI . This will bring you to a screen that prompts you to update to the latest released version, to the most current development version, or any released or unreleased version you choose by selecting the tag or branch of the desired version.
+
+Command-line users can run this interface by typing invokeai-configure
+
+### Image Symmetry Options
+
+There are now features to generate horizontal and vertical symmetry during generation. The way these work is to wait until a selected step in the generation process and then to turn on a mirror image effect. In addition to generating some cool images, you can also use this to make side-by-side comparisons of how an image will look with more or fewer steps. Access this option from the WebUI by selecting Symmetry from the image generation settings, or within the CLI by using the options --h_symmetry_time_pct and --v_symmetry_time_pct (these can be abbreviated to --h_sym and --v_sym like all other options).
+
+### A New Unified Canvas Look
+
+This release introduces a beta version of the WebUI Unified Canvas. To try it out, open up the settings dialogue in the WebUI (gear icon) and select Use Canvas Beta Layout:
+
+Refresh the screen and go to to Unified Canvas (left side of screen, third icon from the top). The new layout is designed to provide more space to work in and to keep the image controls close to the image itself:
+
+Model conversion and merging within the WebUI
+
+The WebUI now has an intuitive interface for model merging, as well as for permanent conversion of models from legacy .ckpt/.safetensors formats into diffusers format. These options are also available directly from the invoke.sh/invoke.bat scripts.
+An easier way to contribute translations to the WebUI
+
+We have migrated our translation efforts to Weblate, a FOSS translation product. Maintaining the growing project's translations is now far simpler for the maintainers and community. Please review our brief translation guide for more information on how to contribute.
+Numerous internal bugfixes and performance issues
+
+### Bug Fixes
+This releases quashes multiple bugs that were reported in 2.3.0. Major internal changes include upgrading to diffusers 0.13.0, and using the compel library for prompt parsing. See Detailed Change Log for a detailed list of bugs caught and squished.
+Summary of InvokeAI command line scripts (all accessible via the launcher menu)
+Command 	Description
+invokeai 	Command line interface
+invokeai --web 	Web interface
+invokeai-model-install 	Model installer with console forms-based front end
+invokeai-ti --gui 	Textual inversion, with a console forms-based front end
+invokeai-merge --gui 	Model merging, with a console forms-based front end
+invokeai-configure 	Startup configuration; can also be used to reinstall support models
+invokeai-update 	InvokeAI software updater
+
+### Known Bugs in 2.3.1
+
+These are known bugs in the release.
+    MacOS users generating 768x768 pixel images or greater using diffusers models may experience a hard crash with assertion NDArray > 2**32 This appears to be an issu...
+
+
+
 ## v2.3.0 <small>(15 January 2023)</small>
 
 **Transition to diffusers
@@ -264,7 +494,7 @@ sections describe what's new for InvokeAI.
   [Manual Installation](installation/020_INSTALL_MANUAL.md).
 - The ability to save frequently-used startup options (model to load, steps,
   sampler, etc) in a `.invokeai` file. See
-  [Client](features/CLI.md)
+  [Client](deprecated/CLI.md)
 - Support for AMD GPU cards (non-CUDA) on Linux machines.
 - Multiple bugs and edge cases squashed.
 
@@ -387,7 +617,7 @@ sections describe what's new for InvokeAI.
 - `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains for
   backward compatibility.
 - Completely new WebGUI - launch with `python3 scripts/invoke.py --web`
-- Support for [inpainting](features/INPAINTING.md) and
+- Support for [inpainting](deprecated/INPAINTING.md) and
   [outpainting](features/OUTPAINTING.md)
 - img2img runs on all k\* samplers
 - Support for
@@ -399,7 +629,7 @@ sections describe what's new for InvokeAI.
   using facial reconstruction, ESRGAN upscaling, outcropping (similar to DALL-E
   infinite canvas), and "embiggen" upscaling. See the `!fix` command.
 - New `--hires` option on `invoke>` line allows
-  [larger images to be created without duplicating elements](features/CLI.md#this-is-an-example-of-txt2img),
+  [larger images to be created without duplicating elements](deprecated/CLI.md#this-is-an-example-of-txt2img),
   at the cost of some performance.
 - New `--perlin` and `--threshold` options allow you to add and control
   variation during image generation (see
@@ -408,7 +638,7 @@ sections describe what's new for InvokeAI.
   of images and tweaking of previous settings.
 - Command-line completion in `invoke.py` now works on Windows, Linux and Mac
   platforms.
-- Improved [command-line completion behavior](features/CLI.md) New commands
+- Improved [command-line completion behavior](deprecated/CLI.md) New commands
   added:
   - List command-line history with `!history`
   - Search command-line history with `!search`

docs/contributing/CONTRIBUTING.md

@@ -0,0 +1,54 @@
+## Welcome to Invoke AI
+
+We're thrilled to have you here and we're excited for you to contribute. 
+
+Invoke AI originated as a project built by the community, and that vision carries forward today as we aim to build the best pro-grade tools available. We work together to incorporate the latest in AI/ML research, making these tools available in over 20 languages to artists and creatives around the world as part of our fully permissive OSS project designed for individual users to self-host and use.
+
+Here are some guidelines to help you get started:
+
+### Technical Prerequisites
+
+Front-end: You'll need a working knowledge of React and TypeScript.
+
+Back-end: Depending on the scope of your contribution, you may need to know SQLite, FastAPI, Python, and Socketio. Also, a good majority of the backend logic involved in processing images is built in a modular way using a concept called "Nodes", which are isolated functions that carry out individual, discrete operations. This design allows for easy contributions of novel pipelines and capabilities.
+
+### How to Submit Contributions
+
+To start contributing, please follow these steps:
+
+1. Familiarize yourself with our roadmap and open projects to see where your skills and interests align. These documents can serve as a source of inspiration.
+2. Open a Pull Request (PR) with a clear description of the feature you're adding or the problem you're solving. Make sure your contribution aligns with the project's vision.
+3. Adhere to general best practices. This includes assuming interoperability with other nodes, keeping the scope of your functions as small as possible, and organizing your code according to our architecture documents.
+
+### Types of Contributions We're Looking For
+
+We welcome all contributions that improve the project. Right now, we're especially looking for:
+
+1. Quality of life (QOL) enhancements on the front-end.
+2. New backend capabilities added through nodes.
+3. Incorporating additional optimizations from the broader open-source software community.
+
+### Communication and Decision-making Process
+
+Project maintainers and code owners review PRs to ensure they align with the project's goals. They may provide design or architectural guidance, suggestions on user experience, or provide more significant feedback on the contribution itself. Expect to receive feedback on your submissions, and don't hesitate to ask questions or propose changes.
+
+For more robust discussions, or if you're planning to add capabilities not currently listed on our roadmap, please reach out to us on our Discord server. That way, we can ensure your proposed contribution aligns with the project's direction before you start writing code.
+
+### Code of Conduct and Contribution Expectations
+
+We want everyone in our community to have a positive experience. To facilitate this, we've established a code of conduct and a statement of values that we expect all contributors to adhere to. Please take a moment to review these documents—they're essential to maintaining a respectful and inclusive environment.
+
+By making a contribution to this project, you certify that:
+
+1. The contribution was created in whole or in part by you and you have the right to submit it under the open-source license indicated in this project’s GitHub repository; or
+2. The contribution is based upon previous work that, to the best of your knowledge, is covered under an appropriate open-source license and you have the right under that license to submit that work with modifications, whether created in whole or in part by you, under the same open-source license (unless you are permitted to submit under a different license); or
+3. The contribution was provided directly to you by some other person who certified (1) or (2) and you have not modified it; or
+4. You understand and agree that this project and the contribution are public and that a record of the contribution (including all personal information you submit with it, including your sign-off) is maintained indefinitely and may be redistributed consistent with this project or the open-source license(s) involved.
+
+This disclaimer is not a license and does not grant any rights or permissions. You must obtain necessary permissions and licenses, including from third parties, before contributing to this project.
+
+This disclaimer is provided "as is" without warranty of any kind, whether expressed or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose, or non-infringement. In no event shall the authors or copyright holders be liable for any claim, damages, or other liability, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the contribution or the use or other dealings in the contribution.
+
+---
+
+Remember, your contributions help make this project great. We're excited to see what you'll bring to our community!

docs/deprecated/CLI.md

@@ -205,14 +205,14 @@ Here are the invoke> command that apply to txt2img:
 | `--seamless`                              |                                           | `False`                                  | Activate seamless tiling for interesting effects                                                                                                                                                                                                 |
 | `--seamless_axes`                         |                                           | `x,y`                                    | Specify which axes to use circular convolution on.                                                                                                                                                                                               |
 | `--log_tokenization`                      | `-t`                                      | `False`                                  | Display a color-coded list of the parsed tokens derived from the prompt                                                                                                                                                                          |
-| `--skip_normalization`                    | `-x`                                      | `False`                                  | Weighted subprompts will not be normalized. See [Weighted Prompts](./OTHER.md#weighted-prompts)                                                                                                                                                  |
+| `--skip_normalization`                    | `-x`                                      | `False`                                  | Weighted subprompts will not be normalized. See [Weighted Prompts](../features/OTHER.md#weighted-prompts)                                                                                                                                                  |
 | `--upscale <int> <float>`                 | `-U <int> <float>`                        | `-U 1 0.75`                              | Upscale image by magnification factor (2, 4), and set strength of upscaling (0.0-1.0). If strength not set, will default to 0.75.                                                                                                                |
 | `--facetool_strength <float>`             | `-G <float> `                             | `-G0`                                    | Fix faces (defaults to using the GFPGAN algorithm); argument indicates how hard the algorithm should try (0.0-1.0)                                                                                                                               |
 | `--facetool <name>`                       | `-ft <name>`                              | `-ft gfpgan`                             | Select face restoration algorithm to use: gfpgan, codeformer                                                                                                                                                                                     |
 | `--codeformer_fidelity`                   | `-cf <float>`                             | `0.75`                                   | Used along with CodeFormer. Takes values between 0 and 1. 0 produces high quality but low accuracy. 1 produces high accuracy but low quality                                                                                                     |
 | `--save_original`                         | `-save_orig`                              | `False`                                  | When upscaling or fixing faces, this will cause the original image to be saved rather than replaced.                                                                                                                                             |
-| `--variation <float>`                     | `-v<float>`                               | `0.0`                                    | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](./VARIATIONS.md). |
-| `--with_variations <pattern>`             |                                           | `None`                                   | Combine two or more variations. See [Variations](./VARIATIONS.md) for now to use this.                                                                                                                                                           |
+| `--variation <float>`                     | `-v<float>`                               | `0.0`                                    | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](../features/VARIATIONS.md). |
+| `--with_variations <pattern>`             |                                           | `None`                                   | Combine two or more variations. See [Variations](../features/VARIATIONS.md) for now to use this.                                                                                                                                                           |
 | `--save_intermediates <n>`                |                                           | `None`                                   | Save the image from every nth step into an "intermediates" folder inside the output directory                                                                                                                                                    |
 | `--h_symmetry_time_pct <float>`           |                                           | `None`                                   | Create symmetry along the X axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.)                                   |
 | `--v_symmetry_time_pct <float>`           |                                           | `None`                                   | Create symmetry along the Y axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.)                                   |
@@ -257,7 +257,7 @@ additional options:
     by `-M`. You may also supply just a single initial image with the areas
     to overpaint made transparent, but you must be careful not to destroy
     the pixels underneath when you create the transparent areas. See
-    [Inpainting](./INPAINTING.md) for details.
+    [Inpainting](INPAINTING.md) for details.
 
 inpainting accepts all the arguments used for txt2img and img2img, as well as
 the --mask (-M) and --text_mask (-tm) arguments:
@@ -297,7 +297,7 @@ invoke> a piece of cake -I /path/to/breakfast.png -tm bagel 0.6
 
 You can load and use hundreds of community-contributed Textual
 Inversion models just by typing the appropriate trigger phrase. Please
-see [Concepts Library](CONCEPTS.md) for more details.
+see [Concepts Library](../features/CONCEPTS.md) for more details.
 
 ## Other Commands
 

docs/features/CONCEPTS.md

@@ -65,39 +65,21 @@ find out what each concept is for, you can browse the
 [Hugging Face concepts library](https://huggingface.co/sd-concepts-library) and
 look at examples of what each concept produces.
 
-When you have an idea of a concept you wish to try, go to the command-line
-client (CLI) and type a `<` character and the beginning of the Hugging Face
-concept name you wish to load. Press ++tab++, and the CLI will show you all
-matching concepts. You can also type `<` and hit ++tab++ to get a listing of all
-~800 concepts, but be prepared to scroll up to see them all! If there is more
-than one match you can continue to type and ++tab++ until the concept is
-completed.
+To load concepts, you will need to open the Web UI's configuration
+dialogue and activate "Show Textual Inversions from HF Concepts
+Library". This will then add a list of HF Concepts to the dropdown
+"Add Textual Inversion" menu. Select the concept(s) of your choice and
+they will be incorporated into the positive prompt. A few concepts are
+designed for the negative prompt, in which case you can add them to
+the negative prompt box by select the down arrow icon next to the
+textual inversion menu.
 
-!!! example
-
-    if you type in `<x` and hit ++tab++, you'll be prompted with the completions:
-
-    ```py
-    <xatu2>        <xatu>         <xbh>          <xi>           <xidiversity>  <xioboma>      <xuna>         <xyz>
-    ```
-
-    Now type `id` and press ++tab++. It will be autocompleted to `<xidiversity>`
-    because this is a unique match.
-
-    Finish your prompt and generate as usual. You may include multiple concept terms
-    in the prompt.
-
-If you have never used this concept before, you will see a message that the TI
-model is being downloaded and installed. After this, the concept will be saved
-locally (in the `models/sd-concepts-library` directory) for future use.
-
-Several steps happen during downloading and installation, including a scan of
-the file for malicious code. Should any errors occur, you will be warned and the
-concept will fail to load. Generation will then continue treating the trigger
-term as a normal string of characters (e.g. as literal `<ghibli-face>`).
-
-You can also use `<concept-names>` in the WebGUI's prompt textbox. There is no
-autocompletion at this time.
+There are nearly 1000 HF concepts, more than will fit into a menu. For
+this reason we only show the most popular concepts (those which have
+received 5 or more likes). If you wish to use a concept that is not on
+the list, you may simply type its name surrounded by brackets. For
+example, to load the concept named "xidiversity", add `<xidiversity>`
+to the positive or negative prompt text.
 
 ## Installing your Own TI Files
 
@@ -112,18 +94,11 @@ At startup time, InvokeAI will scan the `embeddings` directory and load any TI
 files it finds there. At startup you will see a message similar to this one:
 
 ```bash
->> Current embedding manager terms: *, <HOI4-Leader>, <princess-knight>
+>> Current embedding manager terms: <HOI4-Leader>, <princess-knight>
 ```
 
-Note the `*` trigger term. This is a placeholder term that many early TI
-tutorials taught people to use rather than a more descriptive term.
-Unfortunately, if you have multiple TI files that all use this term, only the
-first one loaded will be triggered by use of the term.
-
-To avoid this problem, you can use the `merge_embeddings.py` script to merge two
-or more TI files together. If it encounters a collision of terms, the script
-will prompt you to select new terms that do not collide. See
-[Textual Inversion](TEXTUAL_INVERSION.md) for details.
+The terms you can use will appear in the "Add Textual Inversion"
+dropdown menu above the HF Concepts.
 
 ## Further Reading
 

docs/features/CONTROLNET.md

@@ -0,0 +1,92 @@
+---
+title: ControlNet
+---
+
+# :material-loupe: ControlNet
+
+## ControlNet
+
+ControlNet
+
+ControlNet is a powerful set of features developed by the open-source community (notably, Stanford researcher [**@ilyasviel**](https://github.com/lllyasviel)) that allows you to apply a secondary neural network model to your image generation process in Invoke.
+
+With ControlNet, you can get more control over the output of your image generation, providing you with a way to direct the network towards generating images that better fit your desired style or outcome.
+
+
+### How it works
+
+ControlNet works by analyzing an input image, pre-processing that image to identify relevant information that can be interpreted by each specific ControlNet model, and then inserting that control information into the generation process. This can be used to adjust the style, composition, or other aspects of the image to better achieve a specific result.
+
+
+### Models
+
+As part of the model installation, ControlNet models can be selected including a variety of pre-trained models that have been added to achieve different effects or styles in your generated images. Further ControlNet models may require additional code functionality to also be incorporated into Invoke's Invocations folder. You should expect to follow any installation instructions for ControlNet models loaded  outside the default models provided by Invoke. The default models include:
+
+
+**Canny**:
+
+When the Canny model is used in ControlNet, Invoke will attempt to generate images that match the edges detected. 
+
+Canny edge detection works by detecting the edges in an image by looking for abrupt changes in intensity. It is known for its ability to detect edges accurately while reducing noise and false edges, and the preprocessor can identify more information by decreasing the thresholds.
+
+**M-LSD**: 
+
+M-LSD is another edge detection algorithm used in ControlNet. It stands for Multi-Scale Line Segment Detector. 
+
+It detects straight line segments in an image by analyzing the local structure of the image at multiple scales.  It can be useful for architectural imagery, or anything where straight-line structural information is needed for the resulting output. 
+
+**Lineart**: 
+
+The Lineart model in ControlNet generates line drawings from an input image. The resulting pre-processed image is a simplified version of the original, with only the outlines of objects visible.The Lineart model in ControlNet is known for its ability to accurately capture the contours of the objects in an input sketch. 
+
+**Lineart Anime**: 
+
+A variant of the Lineart model that generates line drawings with a distinct style inspired by anime and manga art styles.
+
+**Depth**: 
+A model that generates depth maps of images, allowing you to create more realistic 3D models or to simulate depth effects in post-processing.
+
+**Normal Map (BAE):** 
+A model that generates normal maps from input images, allowing for more realistic lighting effects in 3D rendering.
+		
+**Image Segmentation**: 
+A model that divides input images into segments or regions, each of which corresponds to a different object or part of the image. (More details coming soon)
+
+
+**Openpose**: 
+The OpenPose control model allows for the identification of the general pose of a character by pre-processing an existing image with a clear human structure. With advanced options, Openpose can also detect the face or hands in the image. 
+
+**Mediapipe Face**:
+
+The MediaPipe Face identification processor is able to clearly identify facial features in order to capture vivid expressions of human faces.
+
+**Tile (experimental)**:
+
+The Tile model fills out details in the image to match the image, rather than the prompt. The Tile Model is a versatile tool that offers a range of functionalities. Its primary capabilities can be boiled down to two main behaviors:
+
+- It can reinterpret specific details within an image and create fresh, new elements.
+- It has the ability to disregard global instructions if there's a discrepancy between them and the local context or specific parts of the image. In such cases, it uses the local context to guide the process.
+
+The Tile Model can be a powerful tool in your arsenal for enhancing image quality and details. If there are undesirable elements in your images, such as blurriness caused by resizing, this model can effectively eliminate these issues, resulting in cleaner, crisper images. Moreover, it can generate and add refined details to your images, improving their overall quality and appeal. 
+
+**Pix2Pix (experimental)**
+
+With Pix2Pix, you can input an image into the controlnet, and then "instruct" the model to change it using your prompt. For example, you can say "Make it winter" to add more wintry elements to a scene.
+
+**Inpaint**: Coming Soon - Currently this model is available but not functional on the Canvas. An upcoming release will provide additional capabilities for using this model when inpainting.
+
+Each of these models can be adjusted and combined with other ControlNet models to achieve different results, giving you even more control over your image generation process.
+
+
+## Using ControlNet
+
+To use ControlNet, you can simply select the desired model and adjust both the ControlNet and Pre-processor settings to achieve the desired result. You can also use multiple ControlNet models at the same time, allowing you to achieve even more complex effects or styles in your generated images.
+
+
+Each ControlNet has two settings that are applied to the ControlNet.
+
+Weight - Strength of the Controlnet model applied to the generation for the section, defined by start/end.
+
+Start/End  - 0 represents the start of the generation, 1 represents the end. The Start/end setting controls what steps during the generation process have the ControlNet applied.
+
+Additionally, each ControlNet section can be expanded in order to manipulate settings for the image pre-processor that adjusts your uploaded image before using it in when you Invoke.

docs/features/IMG2IMG.md

@@ -4,86 +4,13 @@ title: Image-to-Image
 
 # :material-image-multiple: Image-to-Image
 
-Both the Web and command-line interfaces provide an "img2img" feature
-that lets you seed your creations with an initial drawing or
-photo. This is a really cool feature that tells stable diffusion to
-build the prompt on top of the image you provide, preserving the
-original's basic shape and layout.
+InvokeAI provides an "img2img" feature that lets you seed your
+creations with an initial drawing or photo. This is a really cool
+feature that tells stable diffusion to build the prompt on top of the
+image you provide, preserving the original's basic shape and layout.
 
-See the [WebUI Guide](WEB.md) for a walkthrough of the img2img feature
-in the InvokeAI web server. This document describes how to use img2img
-in the command-line tool.
-
-## Basic Usage
-
-Launch the command-line client by launching `invoke.sh`/`invoke.bat`
-and choosing option (1). Alternative, activate the InvokeAI
-environment and issue the command `invokeai`.
-
-Once the `invoke> ` prompt appears, you can start an img2img render by
-pointing to a seed file with the `-I` option as shown here:
-
-!!! example ""
-
-    ```commandline
-    tree on a hill with a river, nature photograph, national geographic -I./test-pictures/tree-and-river-sketch.png -f 0.85
-    ```
-
-    <figure markdown>
-
-    | original image | generated image |
-    | :------------: | :-------------: |
-    | ![original-image](https://user-images.githubusercontent.com/50542132/193946000-c42a96d8-5a74-4f8a-b4c3-5213e6cadcce.png){ width=320 } | ![generated-image](https://user-images.githubusercontent.com/111189/194135515-53d4c060-e994-4016-8121-7c685e281ac9.png){ width=320 } |
-
-    </figure>
-
-The `--init_img` (`-I`) option gives the path to the seed picture. `--strength`
-(`-f`) controls how much the original will be modified, ranging from `0.0` (keep
-the original intact), to `1.0` (ignore the original completely). The default is
-`0.75`, and ranges from `0.25-0.90` give interesting results. Other relevant
-options include `-C` (classification free guidance scale), and `-s` (steps).
-Unlike `txt2img`, adding steps will continuously change the resulting image and
-it will not converge.
-
-You may also pass a `-v<variation_amount>` option to generate `-n<iterations>`
-count variants on the original image. This is done by passing the first
-generated image back into img2img the requested number of times. It generates
-interesting variants.
-
-Note that the prompt makes a big difference. For example, this slight variation
-on the prompt produces a very different image:
-
-<figure markdown>
-![](https://user-images.githubusercontent.com/111189/194135220-16b62181-b60c-4248-8989-4834a8fd7fbd.png){ width=320 }
-<caption markdown>photograph of a tree on a hill with a river</caption>
-</figure>
-
-!!! tip
-
-    When designing prompts, think about how the images scraped from the internet were
-    captioned. Very few photographs will be labeled "photograph" or "photorealistic."
-    They will, however, be captioned with the publication, photographer, camera model,
-    or film settings.
-
-If the initial image contains transparent regions, then Stable Diffusion will
-only draw within the transparent regions, a process called
-[`inpainting`](./INPAINTING.md#creating-transparent-regions-for-inpainting).
-However, for this to work correctly, the color information underneath the
-transparent needs to be preserved, not erased.
-
-!!! warning "**IMPORTANT ISSUE** "
-
-    `img2img` does not work properly on initial images smaller
-    than 512x512. Please scale your image to at least 512x512 before using it.
-    Larger images are not a problem, but may run out of VRAM on your GPU card. To
-    fix this, use the --fit option, which downscales the initial image to fit within
-    the box specified by width x height:
-
-    ```
-    tree on a hill with a river, national geographic -I./test-pictures/big-sketch.png -H512 -W512 --fit
-    ```
-
-## How does it actually work, though?
+For a walkthrough of using Image-to-Image in the Web UI, see [InvokeAI
+Web Server](./WEB.md#image-to-image).
 
 The main difference between `img2img` and `prompt2img` is the starting point.
 While `prompt2img` always starts with pure gaussian noise and progressively
@@ -99,10 +26,6 @@ seed `1592514025` develops something like this:
 
 !!! example ""
 
-    ```bash
-    invoke> "fire" -s10 -W384 -H384 -S1592514025
-    ```
-
     <figure markdown>
     ![latent steps](../assets/img2img/000019.steps.png){ width=720 }
     </figure>
@@ -157,17 +80,8 @@ Diffusion has less chance to refine itself, so the result ends up inheriting all
 the problems of my bad drawing.
 
 If you want to try this out yourself, all of these are using a seed of
-`1592514025` with a width/height of `384`, step count `10`, the default sampler
-(`k_lms`), and the single-word prompt `"fire"`:
-
-```bash
-invoke> "fire" -s10 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png --strength 0.7
-```
-
-The code for rendering intermediates is on my (damian0815's) branch
-[document-img2img](https://github.com/damian0815/InvokeAI/tree/document-img2img) -
-run `invoke.py` and check your `outputs/img-samples/intermediates` folder while
-generating an image.
+`1592514025` with a width/height of `384`, step count `10`, the
+`k_lms` sampler, and the single-word prompt `"fire"`.
 
 ### Compensating for the reduced step count
 
@@ -180,10 +94,6 @@ give each generation 20 steps.
 Here's strength `0.4` (note step count `50`, which is `20 ÷ 0.4` to make sure SD
 does `20` steps from my image):
 
-```bash
-invoke> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
-```
-
 <figure markdown>
 ![000035.1592514025](../assets/img2img/000035.1592514025.png)
 </figure>
@@ -191,10 +101,6 @@ invoke> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
 and here is strength `0.7` (note step count `30`, which is roughly `20 ÷ 0.7` to
 make sure SD does `20` steps from my image):
 
-```commandline
-invoke> "fire" -s30 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.7
-```
-
 <figure markdown>
 ![000046.1592514025](../assets/img2img/000046.1592514025.png)
 </figure>

docs/features/MODEL_MERGING.md

@@ -71,6 +71,3 @@ under the selected name and register it with InvokeAI.
   use InvokeAI conventions - only alphanumeric letters and the
   characters ".+-".
 
-## Caveats
-
-This is a new script and may contain bugs.

docs/features/NSFW.md

@@ -31,10 +31,22 @@ turned on and off on the command line using `--nsfw_checker` and
 
 At installation time, InvokeAI will ask whether the checker should be
 activated by default (neither argument given on the command line). The
-response is stored in the InvokeAI initialization file (usually
-`invokeai.init` in your home directory). You can change the default at any
-time by opening this file in a text editor and commenting or
-uncommenting the line `--nsfw_checker`.
+response is stored in the InvokeAI initialization file
+(`invokeai.yaml` in the InvokeAI root directory).  You can change the
+default at any time by opening this file in a text editor and
+changing the line `nsfw_checker:` from true to false or vice-versa:
+
+
+```
+...
+  Features:
+    esrgan: true
+    internet_available: true
+    log_tokenization: false
+    nsfw_checker: true
+    patchmatch: true
+    restore: true
+```
 
 ## Caveats
 
@@ -79,11 +91,3 @@ generates. However, it does write metadata into the PNG data area,
 including the prompt used to generate the image and relevant parameter
 settings. These fields can be examined using the `sd-metadata.py`
 script that comes with the InvokeAI package.
-
-Note that several other Stable Diffusion distributions offer
-wavelet-based "invisible" watermarking. We have experimented with the
-library used to generate these watermarks and have reached the
-conclusion that while the watermarking library may be adding
-watermarks to PNG images, the currently available version is unable to
-retrieve them successfully. If and when a functioning version of the
-library becomes available, we will offer this feature as well.

docs/features/OTHER.md

@@ -18,43 +18,16 @@ Output Example:
 
 ## **Seamless Tiling**
 
-The seamless tiling mode causes generated images to seamlessly tile with itself. To use it, add the
-`--seamless` option when starting the script which will result in all generated images to tile, or
-for each `invoke>` prompt as shown here:
+The seamless tiling mode causes generated images to seamlessly tile
+with itself creating repetitive wallpaper-like patterns. To use it,
+activate the Seamless Tiling option in the Web GUI and then select
+whether to tile on the X (horizontal) and/or Y (vertical) axes. Tiling
+will then be active for the next set of generations.
+
+A nice prompt to test seamless tiling with is:
 
-```python
-invoke> "pond garden with lotus by claude monet" --seamless -s100 -n4
 ```
-
-By default this will tile on both the X and Y axes. However, you can also specify specific axes to tile on with `--seamless_axes`.
-Possible values are `x`, `y`, and `x,y`:
-```python
-invoke> "pond garden with lotus by claude monet" --seamless --seamless_axes=x -s100 -n4
-```
-
----
-
-## **Shortcuts: Reusing Seeds**
-
-Since it is so common to reuse seeds while refining a prompt, there is now a shortcut as of version
-1.11. Provide a `-S` (or `--seed`) switch of `-1` to use the seed of the most recent image
-generated. If you produced multiple images with the `-n` switch, then you can go back further
-using `-2`, `-3`, etc. up to the first image generated by the previous command. Sorry, but you can't go
-back further than one command.
-
-Here's an example of using this to do a quick refinement. It also illustrates using the new `-G`
-switch to turn on upscaling and face enhancement (see previous section):
-
-```bash
-invoke> a cute child playing hopscotch -G0.5
-[...]
-outputs/img-samples/000039.3498014304.png: "a cute child playing hopscotch" -s50 -W512 -H512 -C7.5 -mk_lms -S3498014304
-
-# I wonder what it will look like if I bump up the steps and set facial enhancement to full strength?
-invoke> a cute child playing hopscotch -G1.0 -s100 -S -1
-reusing previous seed 3498014304
-[...]
-outputs/img-samples/000040.3498014304.png: "a cute child playing hopscotch" -G1.0 -s100 -W512 -H512 -C7.5 -mk_lms -S3498014304
+pond garden with lotus by claude monet"
 ```
 
 ---
@@ -73,66 +46,27 @@ This will tell the sampler to invest 25% of its effort on the tabby cat aspect o
 on the white duck aspect (surprisingly, this example actually works). The prompt weights can use any
 combination of integers and floating point numbers, and they do not need to add up to 1.
 
----
-
-## **Filename Format**
-
-The argument `--fnformat` allows to specify the filename of the
- image. Supported wildcards are all arguments what can be set such as
- `perlin`, `seed`, `threshold`, `height`, `width`, `gfpgan_strength`,
- `sampler_name`, `steps`, `model`, `upscale`, `prompt`, `cfg_scale`,
- `prefix`.
-
-The following prompt
-```bash
-dream> a red car --steps 25 -C 9.8 --perlin 0.1 --fnformat {prompt}_steps.{steps}_cfg.{cfg_scale}_perlin.{perlin}.png
-```
-
-generates a file with the name: `outputs/img-samples/a red car_steps.25_cfg.9.8_perlin.0.1.png`
-
----
-
 ## **Thresholding and Perlin Noise Initialization Options**
 
-Two new options are the thresholding (`--threshold`) and the perlin noise initialization (`--perlin`) options. Thresholding limits the range of the latent values during optimization, which helps combat oversaturation with higher CFG scale values. Perlin noise initialization starts with a percentage (a value ranging from 0 to 1) of perlin noise mixed into the initial noise. Both features allow for more variations and options in the course of generating images.
+Under the Noise section of the Web UI, you will find two options named
+Perlin Noise and Noise Threshold. [Perlin
+noise](https://en.wikipedia.org/wiki/Perlin_noise) is a type of
+structured noise used to simulate terrain and other natural
+textures. The slider controls the percentage of perlin noise that will
+be mixed into the image at the beginning of generation. Adding a little
+perlin noise to a generation will alter the image substantially.
+
+The noise threshold limits the range of the latent values during
+sampling and helps combat the oversharpening seem with higher CFG
+scale values.
 
 For better intuition into what these options do in practice:
 
 ![here is a graphic demonstrating them both](../assets/truncation_comparison.jpg)
 
-In generating this graphic, perlin noise at initialization was programmatically varied going across on the diagram by values 0.0, 0.1, 0.2, 0.4, 0.5, 0.6, 0.8, 0.9, 1.0; and the threshold was varied going down from
-0, 1, 2, 3, 4, 5, 10, 20, 100. The other options are fixed, so the initial prompt is as follows (no thresholding or perlin noise):
-
-```bash
-invoke> "a portrait of a beautiful young lady" -S 1950357039 -s 100 -C 20 -A k_euler_a --threshold 0 --perlin 0
-```
-
-Here's an example of another prompt used when setting the threshold to 5 and perlin noise to 0.2:
-
-```bash
-invoke> "a portrait of a beautiful young lady" -S 1950357039 -s 100 -C 20 -A k_euler_a --threshold 5 --perlin 0.2
-```
-
-!!! note
-
-    currently the thresholding feature is only implemented for the k-diffusion style samplers, and empirically appears to work best with `k_euler_a` and `k_dpm_2_a`. Using 0 disables thresholding. Using 0 for perlin noise disables using perlin noise for initialization. Finally, using 1 for perlin noise uses only perlin noise for initialization.
-
----
-
-## **Simplified API**
-
-For programmers who wish to incorporate stable-diffusion into other products, this repository
-includes a simplified API for text to image generation, which lets you create images from a prompt
-in just three lines of code:
-
-```bash
-from ldm.generate import Generate
-g       = Generate()
-outputs = g.txt2img("a unicorn in manhattan")
-```
-
-Outputs is a list of lists in the format [filename1,seed1],[filename2,seed2]...].
-
-Please see the documentation in ldm/generate.py for more information.
-
----
+In generating this graphic, perlin noise at initialization was
+programmatically varied going across on the diagram by values 0.0,
+0.1, 0.2, 0.4, 0.5, 0.6, 0.8, 0.9, 1.0; and the threshold was varied
+going down from 0, 1, 2, 3, 4, 5, 10, 20, 100. The other options are
+fixed using the prompt "a portrait of a beautiful young lady" a CFG of
+20, 100 steps, and a seed of 1950357039.

docs/features/POSTPROCESS.md

@@ -8,12 +8,6 @@ title: Postprocessing
 
 This extension provides the ability to restore faces and upscale images.
 
-Face restoration and upscaling can be applied at the time you generate the
-images, or at any later time against a previously-generated PNG file, using the
-[!fix](#fixing-previously-generated-images) command.
-[Outpainting and outcropping](OUTPAINTING.md) can only be applied after the
-fact.
-
 ## Face Fixing
 
 The default face restoration module is GFPGAN. The default upscale is
@@ -23,8 +17,7 @@ Real-ESRGAN. For an alternative face restoration module, see
 As of version 1.14, environment.yaml will install the Real-ESRGAN package into
 the standard install location for python packages, and will put GFPGAN into a
 subdirectory of "src" in the InvokeAI directory. Upscaling with Real-ESRGAN
-should "just work" without further intervention. Simply pass the `--upscale`
-(`-U`) option on the `invoke>` command line, or indicate the desired scale on
+should "just work" without further intervention. Simply indicate the desired scale on
 the popup in the Web GUI.
 
 **GFPGAN** requires a series of downloadable model files to work. These are
@@ -41,48 +34,75 @@ reconstruction.
 
 ### Upscaling
 
-`-U : <upscaling_factor> <upscaling_strength>`
+Open the upscaling dialog by clicking on the "expand" icon located
+above the image display area in the Web UI:
 
-The upscaling prompt argument takes two values. The first value is a scaling
-factor and should be set to either `2` or `4` only. This will either scale the
-image 2x or 4x respectively using different models.
+<figure markdown>
+![upscale1](../assets/features/upscale-dialog.png)
+</figure>
 
-You can set the scaling stength between `0` and `1.0` to control intensity of
-the of the scaling. This is handy because AI upscalers generally tend to smooth
-out texture details. If you wish to retain some of those for natural looking
-results, we recommend using values between `0.5 to 0.8`.
+There are three different upscaling parameters that you can
+adjust. The first is the scale itself, either 2x or 4x.
 
-If you do not explicitly specify an upscaling_strength, it will default to 0.75.
+The second is the "Denoising Strength." Higher values will smooth out
+the image and remove digital chatter, but may lose fine detail at
+higher values.
+
+Third, "Upscale Strength" allows you to adjust how the You can set the
+scaling stength between `0` and `1.0` to control the intensity of the
+scaling. AI upscalers generally tend to smooth out texture details. If
+you wish to retain some of those for natural looking results, we
+recommend using values between `0.5 to 0.8`.
+
+[This figure](../assets/features/upscaling-montage.png) illustrates
+the effects of denoising and strength. The original image was 512x512,
+4x scaled to 2048x2048. The "original" version on the upper left was
+scaled using simple pixel averaging. The remainder use the ESRGAN
+upscaling algorithm at different levels of denoising and strength.
+
+<figure markdown>
+![upscaling](../assets/features/upscaling-montage.png){ width=720 }
+</figure>
+
+Both denoising and strength default to 0.75.
 
 ### Face Restoration
 
-`-G : <facetool_strength>`
+InvokeAI offers alternative two face restoration algorithms,
+[GFPGAN](https://github.com/TencentARC/GFPGAN) and
+[CodeFormer](https://huggingface.co/spaces/sczhou/CodeFormer). These
+algorithms improve the appearance of faces, particularly eyes and
+mouths. Issues with faces are less common with the latest set of
+Stable Diffusion models than with the original 1.4 release, but the
+restoration algorithms can still make a noticeable improvement in
+certain cases. You can also apply restoration to old photographs you
+upload.
 
-This prompt argument controls the strength of the face restoration that is being
-applied. Similar to upscaling, values between `0.5 to 0.8` are recommended.
+To access face restoration, click the "smiley face" icon in the
+toolbar above the InvokeAI image panel. You will be presented with a
+dialog that offers a choice between the two algorithm and sliders that
+allow you to adjust their parameters. Alternatively, you may open the
+left-hand accordion panel labeled "Face Restoration" and have the
+restoration algorithm of your choice applied to generated images
+automatically.
 
-You can use either one or both without any conflicts. In cases where you use
-both, the image will be first upscaled and then the face restoration process
-will be executed to ensure you get the highest quality facial features.
 
-`--save_orig`
+Like upscaling, there are a number of parameters that adjust the face
+restoration output. GFPGAN has a single parameter, `strength`, which
+controls how much the algorithm is allowed to adjust the
+image. CodeFormer has two parameters, `strength`, and `fidelity`,
+which together control the quality of the output image as described in
+the [CodeFormer project
+page](https://shangchenzhou.com/projects/CodeFormer/). Default values
+are 0.75 for both parameters, which achieves a reasonable balance
+between changing the image too much and not enough.
 
-When you use either `-U` or `-G`, the final result you get is upscaled or face
-modified. If you want to save the original Stable Diffusion generation, you can
-use the `-save_orig` prompt argument to save the original unaffected version
-too.
+[This figure](../assets/features/restoration-montage.png) illustrates
+the effects of adjusting GFPGAN and CodeFormer parameters.
 
-### Example Usage
-
-```bash
-invoke> "superman dancing with a panda bear" -U 2 0.6 -G 0.4
-```
-
-This also works with img2img:
-
-```bash
-invoke> "a man wearing a pineapple hat" -I path/to/your/file.png -U 2 0.5 -G 0.6
-```
+<figure markdown>
+![upscaling](../assets/features/restoration-montage.png){ width=720 }
+</figure>
 
 !!! note
 
@@ -95,69 +115,8 @@ invoke> "a man wearing a pineapple hat" -I path/to/your/file.png -U 2 0.5 -G 0.6
     process is complete. While the image generation is taking place, you will still be able to preview
     the base images.
 
-If you wish to stop during the image generation but want to upscale or face
-restore a particular generated image, pass it again with the same prompt and
-generated seed along with the `-U` and `-G` prompt arguments to perform those
-actions.
-
-## CodeFormer Support
-
-This repo also allows you to perform face restoration using
-[CodeFormer](https://github.com/sczhou/CodeFormer).
-
-In order to setup CodeFormer to work, you need to download the models like with
-GFPGAN. You can do this either by running `invokeai-configure` or by manually
-downloading the
-[model file](https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth)
-and saving it to `ldm/invoke/restoration/codeformer/weights` folder.
-
-You can use `-ft` prompt argument to swap between CodeFormer and the default
-GFPGAN. The above mentioned `-G` prompt argument will allow you to control the
-strength of the restoration effect.
-
-### CodeFormer Usage
-
-The following command will perform face restoration with CodeFormer instead of
-the default gfpgan.
-
-`<prompt> -G 0.8 -ft codeformer`
-
-### Other Options
-
-- `-cf` - cf or CodeFormer Fidelity takes values between `0` and `1`. 0 produces
-  high quality results but low accuracy and 1 produces lower quality results but
-  higher accuacy to your original face.
-
-The following command will perform face restoration with CodeFormer. CodeFormer
-will output a result that is closely matching to the input face.
-
-`<prompt> -G 1.0 -ft codeformer -cf 0.9`
-
-The following command will perform face restoration with CodeFormer. CodeFormer
-will output a result that is the best restoration possible. This may deviate
-slightly from the original face. This is an excellent option to use in
-situations when there is very little facial data to work with.
-
-`<prompt> -G 1.0 -ft codeformer -cf 0.1`
-
-## Fixing Previously-Generated Images
-
-It is easy to apply face restoration and/or upscaling to any
-previously-generated file. Just use the syntax
-`!fix path/to/file.png <options>`. For example, to apply GFPGAN at strength 0.8
-and upscale 2X for a file named `./outputs/img-samples/000044.2945021133.png`,
-just run:
-
-```bash
-invoke> !fix ./outputs/img-samples/000044.2945021133.png -G 0.8 -U 2
-```
-
-A new file named `000044.2945021133.fixed.png` will be created in the output
-directory. Note that the `!fix` command does not replace the original file,
-unlike the behavior at generate time.
-
 ## How to disable
 
 If, for some reason, you do not wish to load the GFPGAN and/or ESRGAN libraries,
 you can disable them on the invoke.py command line with the `--no_restore` and
-`--no_upscale` options, respectively.
+`--no_esrgan` options, respectively.

docs/features/PROMPTS.md

@@ -4,77 +4,12 @@ title: Prompting-Features
 
 # :octicons-command-palette-24: Prompting-Features
 
-## **Reading Prompts from a File**
-
-You can automate `invoke.py` by providing a text file with the prompts you want
-to run, one line per prompt. The text file must be composed with a text editor
-(e.g. Notepad) and not a word processor. Each line should look like what you
-would type at the invoke> prompt:
-
-```bash
-"a beautiful sunny day in the park, children playing" -n4 -C10
-"stormy weather on a mountain top, goats grazing" -s100
-"innovative packaging for a squid's dinner" -S137038382
-```
-
-Then pass this file's name to `invoke.py` when you invoke it:
-
-```bash
-python scripts/invoke.py --from_file "/path/to/prompts.txt"
-```
-
-You may also read a series of prompts from standard input by providing
-a filename of `-`. For example, here is a python script that creates a
-matrix of prompts, each one varying slightly:
-
-```bash
-#!/usr/bin/env python
-
-adjectives = ['sunny','rainy','overcast']
-samplers = ['k_lms','k_euler_a','k_heun']
-cfg = [7.5, 9, 11]
-
-for adj in adjectives:
-    for samp in samplers:
-        for cg in cfg:
-            print(f'a {adj} day -A{samp} -C{cg}')
-```
-
-Its output looks like this (abbreviated):
-
-```bash
-a sunny day -Aklms -C7.5
-a sunny day -Aklms -C9
-a sunny day -Aklms -C11
-a sunny day -Ak_euler_a -C7.5
-a sunny day -Ak_euler_a -C9
-...
-a overcast day -Ak_heun -C9
-a overcast day -Ak_heun -C11
-```
-
-To feed it to invoke.py, pass the filename of "-"
-
-```bash
-python matrix.py | python scripts/invoke.py --from_file -
-```
-
-When the script is finished, each of the 27 combinations
-of adjective, sampler and CFG will be executed.
-
-The command-line interface provides `!fetch` and `!replay` commands
-which allow you to read the prompts from a single previously-generated
-image or a whole directory of them, write the prompts to a file, and
-then replay them. Or you can create your own file of prompts and feed
-them to the command-line client from within an interactive session.
-See [Command-Line Interface](CLI.md) for details.
-
----
-
 ## **Negative and Unconditioned Prompts**
 
-Any words between a pair of square brackets will instruct Stable Diffusion to
-attempt to ban the concept from the generated image.
+Any words between a pair of square brackets will instruct Stable
+Diffusion to attempt to ban the concept from the generated image. The
+same effect is achieved by placing words in the "Negative Prompts"
+textbox in the Web UI.
 
 ```text
 this is a test prompt [not really] to make you understand [cool] how this works.
@@ -87,7 +22,9 @@ Here's a prompt that depicts what it does.
 
 original prompt:
 
-`#!bash "A fantastical translucent pony made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
+`#!bash "A fantastical translucent pony made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve"`
+
+`#!bash parameters: steps=20, dimensions=512x768, CFG=7.5, Scheduler=k_euler_a, seed=1654590180`
 
 <figure markdown>
 
@@ -99,7 +36,8 @@ That image has a woman, so if we want the horse without a rider, we can
 influence the image not to have a woman by putting [woman] in the prompt, like
 this:
 
-`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman]"`
+(same parameters as above)
 
 <figure markdown>
 
@@ -110,7 +48,8 @@ this:
 That's nice - but say we also don't want the image to be quite so blue. We can
 add "blue" to the list of negative prompts, so it's now [woman blue]:
 
-`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue]"`
+(same parameters as above)
 
 <figure markdown>
 
@@ -121,7 +60,8 @@ add "blue" to the list of negative prompts, so it's now [woman blue]:
 Getting close - but there's no sense in having a saddle when our horse doesn't
 have a rider, so we'll add one more negative prompt: [woman blue saddle].
 
-`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue saddle]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue saddle]"`
+(same parameters as above)
 
 <figure markdown>
 
@@ -261,19 +201,6 @@ Prompt2prompt `.swap()` is not compatible with xformers, which will be temporari
 The `prompt2prompt` code is based off
 [bloc97's colab](https://github.com/bloc97/CrossAttentionControl).
 
-Note that `prompt2prompt` is not currently working with the runwayML inpainting
-model, and may never work due to the way this model is set up. If you attempt to
-use `prompt2prompt` you will get the original image back. However, since this
-model is so good at inpainting, a good substitute is to use the `clipseg` text
-masking option:
-
-```bash
-invoke> a fluffy cat eating a hotdog
-Outputs:
-[1010] outputs/000025.2182095108.png: a fluffy cat eating a hotdog
-invoke> a smiling dog eating a hotdog -I 000025.2182095108.png -tm cat
-```
-
 ### Escaping parantheses () and speech marks ""
 
 If the model you are using has parentheses () or speech marks "" as part of its
@@ -374,6 +301,5 @@ summoning up the concept of some sort of scifi creature? Let's find out.
 Indeed, removing the word "hybrid" produces an image that is more like what we'd
 expect.
 
-In conclusion, prompt blending is great for exploring creative space, but can be
-difficult to direct. A forthcoming release of InvokeAI will feature more
-deterministic prompt weighting.
+In conclusion, prompt blending is great for exploring creative space,
+but takes some trial and error to achieve the desired effect.

docs/features/TEXTUAL_INVERSION.md

@@ -46,11 +46,19 @@ start the front end by selecting choice (3):
 
 ```sh
 Do you want to generate images using the
-1. command-line
-2. browser-based UI
-3. textual inversion training
-4. open the developer console
-Please enter 1, 2, 3, or 4: [1] 3
+1: Browser-based UI
+2: Command-line interface
+3: Run textual inversion training
+4: Merge models (diffusers type only)
+5: Download and install models
+6: Change InvokeAI startup options
+7: Re-run the configure script to fix a broken install
+8: Open the developer console
+9: Update InvokeAI
+10: Command-line help
+Q: Quit
+
+Please enter 1-10, Q: [1] 
 ```
 
 From the command line, with the InvokeAI virtual environment active,

docs/features/VARIATIONS.md

@@ -6,9 +6,7 @@ title: Variations
 
 ## Intro
 
-Release 1.13 of SD-Dream adds support for image variations.
-
-You are able to do the following:
+InvokeAI's support for variations enables you to do the following:
 
 1. Generate a series of systematic variations of an image, given a prompt. The
    amount of variation from one image to the next can be controlled.
@@ -30,19 +28,7 @@ The prompt we will use throughout is:
 This will be indicated as `#!bash "prompt"` in the examples below.
 
 First we let SD create a series of images in the usual way, in this case
-requesting six iterations:
-
-```bash
-invoke> lucy lawless as xena, warrior princess, character portrait, high resolution -n6
-...
-Outputs:
-./outputs/Xena/000001.1579445059.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S1579445059
-./outputs/Xena/000001.1880768722.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S1880768722
-./outputs/Xena/000001.332057179.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S332057179
-./outputs/Xena/000001.2224800325.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S2224800325
-./outputs/Xena/000001.465250761.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S465250761
-./outputs/Xena/000001.3357757885.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S3357757885
-```
+requesting six iterations.
 
 <figure markdown>
 ![var1](../assets/variation_walkthru/000001.3357757885.png)
@@ -53,22 +39,16 @@ Outputs:
 
 ## Step 2 - Generating Variations
 
-Let's try to generate some variations. Using the same seed, we pass the argument
-`-v0.1` (or --variant_amount), which generates a series of variations each
-differing by a variation amount of 0.2. This number ranges from `0` to `1.0`,
-with higher numbers being larger amounts of variation.
+Let's try to generate some variations on this image. We select the "*"
+symbol in the line of icons above the image in order to fix the prompt
+and seed. Then we open up the "Variations" section of the generation
+panel and use the slider to set the variation amount to 0.2. The
+higher this value, the more each generated image will differ from the
+previous one.
 
-```bash
-invoke> "prompt" -n6 -S3357757885 -v0.2
-...
-Outputs:
-./outputs/Xena/000002.784039624.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 784039624:0.2 -S3357757885
-./outputs/Xena/000002.3647897225.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.2 -S3357757885
-./outputs/Xena/000002.917731034.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 917731034:0.2 -S3357757885
-./outputs/Xena/000002.4116285959.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 4116285959:0.2 -S3357757885
-./outputs/Xena/000002.1614299449.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 1614299449:0.2 -S3357757885
-./outputs/Xena/000002.1335553075.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 1335553075:0.2 -S3357757885
-```
+Now we run the prompt a second time, requesting six iterations. You
+will see six images that are thematically related to each other. Try
+increasing and decreasing the variation amount and see what happens.
 
 ### **Variation Sub Seeding**
 

docs/features/WEB.md

@@ -299,14 +299,6 @@ initial image" icons are located.
 
 See the [Unified Canvas Guide](UNIFIED_CANVAS.md)
 
-## Parting remarks
-
-This concludes the walkthrough, but there are several more features that you can
-explore. Please check out the [Command Line Interface](CLI.md) documentation for
-further explanation of the advanced features that were not covered here.
-
-The WebUI is only rapid development. Check back regularly for updates!
-
 ## Reference
 
 ### Additional Options
@@ -349,11 +341,9 @@ the settings configured in the toolbar.
 
 See below for additional documentation related to each feature:
 
-- [Core Prompt Settings](./CLI.md)
 - [Variations](./VARIATIONS.md)
 - [Upscaling](./POSTPROCESS.md#upscaling)
 - [Image to Image](./IMG2IMG.md)
-- [Inpainting](./INPAINTING.md)
 - [Other](./OTHER.md)
 
 #### Invocation Gallery

docs/features/index.md

@@ -13,28 +13,16 @@ Build complex scenes by combine and modifying multiple images in a stepwise
 fashion. This feature combines img2img, inpainting and outpainting in
 a single convenient digital artist-optimized user interface.
 
-### * The [Command Line Interface (CLI)](CLI.md)
-Scriptable access to InvokeAI's features.
-
 ## Image Generation
 ### * [Prompt Engineering](PROMPTS.md)
 Get the images you want with the InvokeAI  prompt engineering language.
 
-## * [Post-Processing](POSTPROCESS.md)
-Restore mangled faces and make images larger with upscaling. Also see the [Embiggen Upscaling Guide](EMBIGGEN.md).
-
 ## * The [Concepts Library](CONCEPTS.md)
 Add custom subjects and styles using HuggingFace's repository of embeddings.
 
-### * [Image-to-Image Guide for the CLI](IMG2IMG.md)
+### * [Image-to-Image Guide](IMG2IMG.md)
 Use a seed image to build new creations in the CLI.
 
-### * [Inpainting Guide for the CLI](INPAINTING.md)
-Selectively erase and replace portions of an existing image in the CLI.
-
-### * [Outpainting Guide for the CLI](OUTPAINTING.md)
-Extend the borders of the image with an "outcrop" function within the CLI.
-
 ### * [Generating Variations](VARIATIONS.md)
 Have an image you like and want to generate many more like it? Variations
 are the ticket.

docs/index.md

@@ -13,6 +13,7 @@ title: Home
 
 <div align="center" markdown>
 
+
 [![project logo](assets/invoke_ai_banner.png)](https://github.com/invoke-ai/InvokeAI)
 
 [![discord badge]][discord link]
@@ -131,17 +132,13 @@ This method is recommended for those familiar with running Docker containers
 - [WebUI overview](features/WEB.md)
 - [WebUI hotkey reference guide](features/WEBUIHOTKEYS.md)
 - [WebUI Unified Canvas for Img2Img, inpainting and outpainting](features/UNIFIED_CANVAS.md)
+
 <!-- separator -->
-### The InvokeAI Command Line Interface
-- [Command Line Interace Reference Guide](features/CLI.md)
-<!-- separator -->
+
 ### Image Management
 - [Image2Image](features/IMG2IMG.md)
-- [Inpainting](features/INPAINTING.md)
-- [Outpainting](features/OUTPAINTING.md)
 - [Adding custom styles and subjects](features/CONCEPTS.md)
 - [Upscaling and Face Reconstruction](features/POSTPROCESS.md)
-- [Embiggen upscaling](features/EMBIGGEN.md)
 - [Other Features](features/OTHER.md)
 
 <!-- separator -->
@@ -156,83 +153,60 @@ This method is recommended for those familiar with running Docker containers
 - [Prompt Syntax](features/PROMPTS.md)
 - [Generating Variations](features/VARIATIONS.md)
 
-## :octicons-log-16: Latest Changes
+## :octicons-log-16: Important Changes Since Version 2.3
 
-### v2.3.0 <small>(9 February 2023)</small>
+### Nodes
 
-#### Migration to Stable Diffusion `diffusers` models
+Behind the scenes, InvokeAI has been completely rewritten to support
+"nodes," small unitary operations that can be combined into graphs to
+form arbitrary workflows. For example, there is a prompt node that
+processes the prompt string and feeds it to a text2latent node that
+generates a latent image. The latents are then fed to a latent2image
+node that translates the latent image into a PNG.
 
-Previous versions of InvokeAI supported the original model file format introduced with Stable Diffusion 1.4. In the original format, known variously as "checkpoint", or "legacy" format, there is a single large weights file ending with `.ckpt` or `.safetensors`. Though this format has served the community well, it has a number of disadvantages, including file size, slow loading times, and a variety of non-standard variants that require special-case code to handle. In addition, because checkpoint files are actually a bundle of multiple machine learning sub-models, it is hard to swap different sub-models in and out, or to share common sub-models. A new format, introduced by the StabilityAI company in collaboration with HuggingFace, is called `diffusers` and consists of a directory of individual models. The most immediate benefit of `diffusers` is that they load from disk very quickly. A longer term benefit is that in the near future `diffusers` models will be able to share common sub-models, dramatically reducing disk space when you have multiple fine-tune models derived from the same base.
+The WebGUI has a node editor that allows you to graphically design and
+execute custom node graphs. The ability to save and load graphs is
+still a work in progress, but coming soon.
 
-When you perform a new install of version 2.3.0, you will be offered the option to install the `diffusers` versions of a number of popular SD models, including Stable Diffusion versions 1.5 and 2.1 (including the 768x768 pixel version of 2.1). These will act and work just like the checkpoint versions. Do not be concerned if you already have a lot of ".ckpt" or ".safetensors" models on disk! InvokeAI 2.3.0 can still load these and generate images from them without any extra intervention on your part.
+### Command-Line Interface Retired
 
-To take advantage of the optimized loading times of `diffusers` models, InvokeAI offers options to convert legacy checkpoint models into optimized `diffusers` models. If you use the `invokeai` command line interface, the relevant commands are:
+The original "invokeai" command-line interface has been retired. The
+`invokeai` command will now launch a new command-line client that can
+be used by developers to create and test nodes. It is not intended to
+be used for routine image generation or manipulation.
 
-* `!convert_model` -- Take the path to a local checkpoint file or a URL that is pointing to one, convert it into a `diffusers` model, and import it into InvokeAI's models registry file.
-* `!optimize_model` -- If you already have a checkpoint model in your InvokeAI models file, this command will accept its short name and convert it into a like-named `diffusers` model, optionally deleting the original checkpoint file.
-* `!import_model` -- Take the local path of either a checkpoint file or a `diffusers` model directory and import it into InvokeAI's registry file. You may also provide the ID of any diffusers model that has been published on the [HuggingFace models repository](https://huggingface.co/models?pipeline_tag=text-to-image&sort=downloads) and it will be downloaded and installed automatically.
+To launch the Web GUI from the command-line, use the command
+`invokeai-web` rather than the traditional `invokeai --web`.
 
-The WebGUI offers similar functionality for model management.
+### ControlNet
 
-For advanced users, new command-line options provide additional functionality. Launching `invokeai` with the argument `--autoconvert <path to directory>` takes the path to a directory of checkpoint files, automatically converts them into `diffusers` models and imports them. Each time the script is launched, the directory will be scanned for new checkpoint files to be loaded. Alternatively, the `--ckpt_convert` argument will cause any checkpoint or safetensors model that is already registered with InvokeAI to be converted into a `diffusers` model on the fly, allowing you to take advantage of future diffusers-only features without explicitly converting the model and saving it to disk.
+This version of InvokeAI features ControlNet, a system that allows you
+to achieve exact poses for human and animal figures by providing a
+model to follow. Full details are found in [ControlNet](features/CONTROLNET.md)
 
-Please see [INSTALLING MODELS](https://invoke-ai.github.io/InvokeAI/installation/050_INSTALLING_MODELS/) for more information on model management in both the command-line and Web interfaces.
+### New Schedulers
 
-#### Support for the `XFormers` Memory-Efficient Crossattention Package
+The list of schedulers has been completely revamped and brought up to date:
 
-On CUDA (Nvidia) systems, version 2.3.0 supports the `XFormers` library. Once installed,  the`xformers` package dramatically reduces the memory footprint of loaded Stable Diffusion models files and modestly increases image generation speed. `xformers` will be installed and activated automatically if you specify a CUDA system at install time.
+| **Short Name** | **Scheduler**                   | **Notes**                   |
+|----------------|---------------------------------|-----------------------------|
+| **ddim**       | DDIMScheduler                   |                             |
+| **ddpm**       | DDPMScheduler                   |                             |
+| **deis**       | DEISMultistepScheduler          |                             |
+| **lms**        | LMSDiscreteScheduler            |                             |
+| **pndm**       | PNDMScheduler                   |                             |
+| **heun**       | HeunDiscreteScheduler           | original noise schedule     |
+| **heun_k**     | HeunDiscreteScheduler           | using karras noise schedule |
+| **euler**      | EulerDiscreteScheduler          | original noise schedule     |
+| **euler_k**    | EulerDiscreteScheduler          | using karras noise schedule |
+| **kdpm_2**     | KDPM2DiscreteScheduler          |                             |
+| **kdpm_2_a**   | KDPM2AncestralDiscreteScheduler |                             |
+| **dpmpp_2s**   | DPMSolverSinglestepScheduler    |                             |
+| **dpmpp_2m**   | DPMSolverMultistepScheduler     | original noise scnedule     |
+| **dpmpp_2m_k** | DPMSolverMultistepScheduler     | using karras noise schedule |
+| **unipc**      | UniPCMultistepScheduler         | CPU only                    |
 
-The caveat with using `xformers` is that it introduces slightly non-deterministic behavior, and images generated using the same seed and other settings will be subtly different between invocations. Generally the changes are unnoticeable unless you rapidly shift back and forth between images, but to disable `xformers` and restore fully deterministic behavior, you may launch InvokeAI using the `--no-xformers` option. This is most conveniently done by opening the file `invokeai/invokeai.init` with a text editor, and adding the line `--no-xformers` at the bottom.
-
-#### A Negative Prompt Box in the WebUI
-
-There is now a separate text input box for negative prompts in the WebUI. This is convenient for stashing frequently-used negative prompts ("mangled limbs, bad anatomy"). The `[negative prompt]` syntax continues to work in the main prompt box as well.
-
-To see exactly how your prompts are being parsed, launch `invokeai` with the `--log_tokenization` option. The console window will then display the tokenization process for both positive and negative prompts.
-
-#### Model Merging
-
-Version 2.3.0 offers an intuitive user interface for merging up to three Stable Diffusion models using an intuitive user interface. Model merging allows you to mix the behavior of models to achieve very interesting effects. To use this, each of the models must already be imported into InvokeAI and saved in `diffusers` format, then launch the merger using a new menu item in the InvokeAI launcher script (`invoke.sh`, `invoke.bat`) or directly from the command line with `invokeai-merge --gui`. You will be prompted to select the models to merge, the proportions in which to mix them, and the mixing algorithm. The script will create a new merged `diffusers` model and import it into InvokeAI for your use.
-
-See [MODEL MERGING](https://invoke-ai.github.io/InvokeAI/features/MODEL_MERGING/) for more details.
-
-#### Textual Inversion Training
-
-Textual Inversion (TI) is a technique for training a Stable Diffusion model to emit a particular subject or style when triggered by a keyword phrase. You can perform TI training by placing a small number of images of the subject or style in a directory, and choosing a distinctive trigger phrase, such as "pointillist-style". After successful training, The subject or style will be activated by including `<pointillist-style>` in your prompt.
-
-Previous versions of InvokeAI were able to perform TI, but it required using a command-line script with dozens of obscure command-line arguments. Version 2.3.0 features an intuitive TI frontend that will build a TI model on top of any `diffusers` model. To access training you can launch from a new item in the launcher script or from the command line using `invokeai-ti --gui`.
-
-See [TEXTUAL INVERSION](https://invoke-ai.github.io/InvokeAI/features/TEXTUAL_INVERSION/) for further details.
-
-#### A New Installer Experience
-
-The InvokeAI installer has been upgraded in order to provide a smoother and hopefully more glitch-free experience. In addition, InvokeAI is now packaged as a PyPi project, allowing developers and power-users to install InvokeAI with the command `pip install InvokeAI  --use-pep517`. Please see [Installation](#installation) for details.
-
-Developers should be aware that the `pip` installation procedure has been simplified and that the `conda` method is no longer supported at all. Accordingly, the `environments_and_requirements` directory has been deleted from the repository.
-
-#### Command-line name changes
-
-All of InvokeAI's functionality, including the WebUI, command-line interface, textual inversion training and model merging, can all be accessed from the `invoke.sh` and `invoke.bat` launcher scripts. The menu of options has been expanded to add the new functionality. For the convenience of developers and power users, we have normalized the names of the InvokeAI command-line scripts:
-
-* `invokeai` -- Command-line client
-* `invokeai --web` -- Web GUI
-* `invokeai-merge --gui` -- Model merging script with graphical front end
-* `invokeai-ti --gui` -- Textual inversion script with graphical front end
-* `invokeai-configure` -- Configuration tool for initializing the `invokeai` directory and selecting popular starter models.
-
-For backward compatibility, the old command names are also recognized, including `invoke.py` and `configure-invokeai.py`. However, these are deprecated and will eventually be removed.
-
-Developers should be aware that the locations of the script's source code has been moved. The new locations are:
-* `invokeai` =>  `ldm/invoke/CLI.py`
-* `invokeai-configure` => `ldm/invoke/config/configure_invokeai.py`
-* `invokeai-ti`=> `ldm/invoke/training/textual_inversion.py`
-* `invokeai-merge` => `ldm/invoke/merge_diffusers`
-
-Developers are strongly encouraged to perform an "editable" install of InvokeAI using `pip install -e .  --use-pep517` in the Git repository, and then to call the scripts using their 2.3.0 names, rather than executing the scripts directly. Developers should also be aware that the several important data files have been relocated into a new directory named `invokeai`. This includes the WebGUI's `frontend` and `backend` directories, and the `INITIAL_MODELS.yaml` files used by the installer to select starter models. Eventually all InvokeAI modules will be in subdirectories of `invokeai`.
-
-Please see [2.3.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v2.3.0) for further details.
-For older changelogs, please visit the
-**[CHANGELOG](CHANGELOG/#v223-2-december-2022)**.
+Please see [3.0.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v3.0.0) for further details.
 
 ## :material-target: Troubleshooting
 
@@ -268,8 +242,3 @@ free to send me an email if you use and like the script.
 Original portions of the software are Copyright (c) 2022-23
 by [The InvokeAI Team](https://github.com/invoke-ai).
 
-## :octicons-book-24: Further Reading
-
-Please see the original README for more information on this software and
-underlying algorithm, located in the file
-[README-CompViz.md](other/README-CompViz.md).

docs/installation/060_INSTALL_PATCHMATCH.md

@@ -87,18 +87,18 @@ Prior to installing PyPatchMatch, you need to take the following steps:
     sudo pacman -S --needed base-devel
     ```
 
-2. Install `opencv`:
+2. Install `opencv` and `blas`:
 
     ```sh
-    sudo pacman -S opencv
+    sudo pacman -S opencv blas
     ```
 
     or for CUDA support
 
     ```sh
-    sudo pacman -S opencv-cuda
+    sudo pacman -S opencv-cuda blas
     ```
-
+    
 3. Fix the naming of the `opencv` package configuration file:
 
     ```sh

installer/install.bat.in

@@ -38,6 +38,7 @@ echo    https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist
 echo.
 echo See %INSTRUCTIONS% for more details.
 echo.
+echo "For the best user experience we suggest enlarging or maximizing this window now."
 pause
 
 @rem ---------------------------- check Python version ---------------

installer/install.sh.in

@@ -25,7 +25,8 @@ done
 
 if [ -z "$PYTHON" ]; then
     echo "A suitable Python interpreter could not be found"
-    echo "Please install Python 3.9 or higher before running this script. See instructions at $INSTRUCTIONS for help."
+    echo "Please install Python $MINIMUM_PYTHON_VERSION or higher (maximum $MAXIMUM_PYTHON_VERSION) before running this script. See instructions at $INSTRUCTIONS for help."
+    echo "For the best user experience we suggest enlarging or maximizing this window now."
     read -p "Press any key to exit"
     exit -1
 fi

installer/lib/installer.py

@@ -149,7 +149,7 @@ class Installer:
 
         return venv_dir
 
-    def install(self, root: str = "~/invokeai", version: str = "latest", yes_to_all=False, find_links: Path = None) -> None:
+    def install(self, root: str = "~/invokeai-3", version: str = "latest", yes_to_all=False, find_links: Path = None) -> None:
         """
         Install the InvokeAI application into the given runtime path
 

installer/lib/messages.py

@@ -293,6 +293,8 @@ def introduction() -> None:
                 "3. Create initial configuration files.",
                 "",
                 "[i]At any point you may interrupt this program and resume later.",
+                "",
+                "[b]For the best user experience, please enlarge or maximize this window",
             ),
         )
     )

installer/templates/invoke.bat.in

@@ -14,7 +14,7 @@ echo 3. Run textual inversion training
 echo 4. Merge models (diffusers type only)
 echo 5. Download and install models
 echo 6. Change InvokeAI startup options
-echo 7. Re-run the configure script to fix a broken install
+echo 7. Re-run the configure script to fix a broken install or to complete a major upgrade
 echo 8. Open the developer console
 echo 9. Update InvokeAI
 echo 10. Command-line help

installer/templates/invoke.sh.in

@@ -81,7 +81,7 @@ do_choice() {
         ;;
     7)
         clear
-        printf "Re-run the configure script to fix a broken install\n"
+        printf "Re-run the configure script to fix a broken install or to complete a major upgrade\n"
         invokeai-configure --root ${INVOKEAI_ROOT} --yes --default_only
         ;;
     8)
@@ -118,12 +118,12 @@ do_choice() {
 do_dialog() {
     options=(
         1 "Generate images with a browser-based interface"
-        2 "Generate images using a command-line interface"
+        2 "Explore InvokeAI nodes using a command-line interface"
         3 "Textual inversion training"
         4 "Merge models (diffusers type only)"
         5 "Download and install models"
         6 "Change InvokeAI startup options"
-        7 "Re-run the configure script to fix a broken install"
+        7 "Re-run the configure script to fix a broken install or to complete a major upgrade"
         8 "Open the developer console"
         9 "Update InvokeAI")
 

invokeai/app/api/routers/boards.py

@@ -5,6 +5,7 @@ from invokeai.app.services.board_record_storage import BoardChanges
 from invokeai.app.services.image_record_storage import OffsetPaginatedResults
 from invokeai.app.services.models.board_record import BoardDTO
 
+
 from ..dependencies import ApiDependencies
 
 boards_router = APIRouter(prefix="/v1/boards", tags=["boards"])
@@ -71,11 +72,19 @@ async def update_board(
 @boards_router.delete("/{board_id}", operation_id="delete_board")
 async def delete_board(
     board_id: str = Path(description="The id of board to delete"),
+    include_images: Optional[bool] = Query(
+        description="Permanently delete all images on the board", default=False
+    ),
 ) -> None:
     """Deletes a board"""
-
     try:
-        ApiDependencies.invoker.services.boards.delete(board_id=board_id)
+        if include_images is True:
+            ApiDependencies.invoker.services.images.delete_images_on_board(
+                board_id=board_id
+            )
+            ApiDependencies.invoker.services.boards.delete(board_id=board_id)
+        else:
+            ApiDependencies.invoker.services.boards.delete(board_id=board_id)
     except Exception as e:
         # TODO: Does this need any exception handling at all?
         pass

invokeai/app/api/routers/models.py

@@ -1,13 +1,13 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) and 2023 Kent Keirsey (https://github.com/hipsterusername)
 
-from typing import Annotated, Literal, Optional, Union, Dict
+from typing import Literal, Optional, Union
 
 from fastapi import Query
 from fastapi.routing import APIRouter, HTTPException
 from pydantic import BaseModel, Field, parse_obj_as
 from ..dependencies import ApiDependencies
 from invokeai.backend import BaseModelType, ModelType
-from invokeai.backend.model_management.models import OPENAPI_MODEL_CONFIGS
+from invokeai.backend.model_management.models import OPENAPI_MODEL_CONFIGS, SchedulerPredictionType
 MODEL_CONFIGS = Union[tuple(OPENAPI_MODEL_CONFIGS)]
 
 models_router = APIRouter(prefix="/v1/models", tags=["models"])
@@ -51,11 +51,14 @@ class CreateModelResponse(BaseModel):
     info: Union[CkptModelInfo, DiffusersModelInfo] = Field(discriminator="format", description="The model info")
     status: str = Field(description="The status of the API response")
 
+class ImportModelRequest(BaseModel):
+    name: str = Field(description="A model path, repo_id or URL to import")
+    prediction_type: Optional[Literal['epsilon','v_prediction','sample']] = Field(description='Prediction type for SDv2 checkpoint files')
+
 class ConversionRequest(BaseModel):
     name: str = Field(description="The name of the new model")
     info: CkptModelInfo = Field(description="The converted model info")
     save_location: str = Field(description="The path to save the converted model weights")
-    
 
 class ConvertedModelResponse(BaseModel):
     name: str = Field(description="The name of the new model")
@@ -105,6 +108,28 @@ async def update_model(
 
     return model_response
 
+@models_router.post(
+    "/",
+    operation_id="import_model",
+    responses={200: {"status": "success"}},
+)
+async def import_model(
+    model_request: ImportModelRequest
+) -> None:
+    """ Add Model """
+    items_to_import = set([model_request.name])
+    prediction_types = { x.value: x for x in SchedulerPredictionType }
+    logger = ApiDependencies.invoker.services.logger
+    
+    installed_models = ApiDependencies.invoker.services.model_manager.heuristic_import(
+        items_to_import = items_to_import,
+        prediction_type_helper = lambda x: prediction_types.get(model_request.prediction_type)
+    )
+    if len(installed_models) > 0:
+        logger.info(f'Successfully imported {model_request.name}')
+    else:
+        logger.error(f'Model {model_request.name} not imported')
+        raise HTTPException(status_code=500, detail=f'Model {model_request.name} not imported')
 
 @models_router.delete(
     "/{model_name}",

invokeai/app/cli_app.py

@@ -18,8 +18,17 @@ config = InvokeAIAppConfig.get_config()
 config.parse_args()
 logger = InvokeAILogger().getLogger(config=config)
 
+from invokeai.app.services.board_image_record_storage import (
+    SqliteBoardImageRecordStorage,
+)
+from invokeai.app.services.board_images import (
+    BoardImagesService,
+    BoardImagesServiceDependencies,
+)
+from invokeai.app.services.board_record_storage import SqliteBoardRecordStorage
+from invokeai.app.services.boards import BoardService, BoardServiceDependencies
 from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
-from invokeai.app.services.images import ImageService
+from invokeai.app.services.images import ImageService, ImageServiceDependencies
 from invokeai.app.services.metadata import CoreMetadataService
 from invokeai.app.services.resource_name import SimpleNameService
 from invokeai.app.services.urls import LocalUrlService
@@ -230,21 +239,49 @@ def invoke_cli():
     image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
     names = SimpleNameService()
 
-    images = ImageService(
-        image_record_storage=image_record_storage,
-        image_file_storage=image_file_storage,
-        metadata=metadata,
-        url=urls,
-        logger=logger,
-        names=names,
-        graph_execution_manager=graph_execution_manager,
+    board_record_storage = SqliteBoardRecordStorage(db_location)
+    board_image_record_storage = SqliteBoardImageRecordStorage(db_location)
+
+    boards = BoardService(
+        services=BoardServiceDependencies(
+            board_image_record_storage=board_image_record_storage,
+            board_record_storage=board_record_storage,
+            image_record_storage=image_record_storage,
+            url=urls,
+            logger=logger,
+        )
     )
 
+    board_images = BoardImagesService(
+        services=BoardImagesServiceDependencies(
+            board_image_record_storage=board_image_record_storage,
+            board_record_storage=board_record_storage,
+            image_record_storage=image_record_storage,
+            url=urls,
+            logger=logger,
+        )
+    )
+
+    images = ImageService(
+        services=ImageServiceDependencies(
+            board_image_record_storage=board_image_record_storage,
+            image_record_storage=image_record_storage,
+            image_file_storage=image_file_storage,
+            metadata=metadata,
+            url=urls,
+            logger=logger,
+            names=names,
+            graph_execution_manager=graph_execution_manager,
+        )
+    )
+        
     services = InvocationServices(
         model_manager=model_manager,
         events=events,
         latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f'{output_folder}/latents')),
         images=images,
+        boards=boards,
+        board_images=board_images,
         queue=MemoryInvocationQueue(),
         graph_library=SqliteItemStorage[LibraryGraph](
             filename=db_location, table_name="graphs"

invokeai/app/invocations/compel.py

@@ -65,23 +65,20 @@ class CompelInvocation(BaseInvocation):
             **self.clip.text_encoder.dict(),
         )
         with tokenizer_info as orig_tokenizer,\
-             text_encoder_info as text_encoder,\
-             ExitStack() as stack:
+             text_encoder_info as text_encoder:
 
-            loras = [(stack.enter_context(context.services.model_manager.get_model(**lora.dict(exclude={"weight"}))), lora.weight) for lora in self.clip.loras]
+            loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
             ti_list = []
             for trigger in re.findall(r"<[a-zA-Z0-9., _-]+>", self.prompt):
                 name = trigger[1:-1]
                 try:
                     ti_list.append(
-                        stack.enter_context(
-                            context.services.model_manager.get_model(
-                                model_name=name,
-                                base_model=self.clip.text_encoder.base_model,
-                                model_type=ModelType.TextualInversion,
-                            )
-                        )
+                        context.services.model_manager.get_model(
+                            model_name=name,
+                            base_model=self.clip.text_encoder.base_model,
+                            model_type=ModelType.TextualInversion,
+                        ).context.model
                     )
                 except Exception:
                     #print(e)

invokeai/app/invocations/controlnet_image_processors.py

@@ -1,10 +1,11 @@
-# InvokeAI nodes for ControlNet image preprocessors
+# Invocations for ControlNet image preprocessors
 # initial implementation by Gregg Helt, 2023
 # heavily leverages controlnet_aux package: https://github.com/patrickvonplaten/controlnet_aux
-from builtins import float
+from builtins import float, bool
 
+import cv2
 import numpy as np
-from typing import Literal, Optional, Union, List
+from typing import Literal, Optional, Union, List, Dict
 from PIL import Image, ImageFilter, ImageOps
 from pydantic import BaseModel, Field, validator
 
@@ -29,8 +30,13 @@ from controlnet_aux import (
     ContentShuffleDetector,
     ZoeDetector,
     MediapipeFaceDetector,
+    SamDetector,
+    LeresDetector,
 )
 
+from controlnet_aux.util import HWC3, ade_palette
+
+
 from .image import ImageOutput, PILInvocationConfig
 
 CONTROLNET_DEFAULT_MODELS = [
@@ -94,6 +100,10 @@ CONTROLNET_DEFAULT_MODELS = [
 ]
 
 CONTROLNET_NAME_VALUES = Literal[tuple(CONTROLNET_DEFAULT_MODELS)]
+CONTROLNET_MODE_VALUES = Literal[tuple(["balanced", "more_prompt", "more_control", "unbalanced"])]
+# crop and fill options not ready yet
+# CONTROLNET_RESIZE_VALUES = Literal[tuple(["just_resize", "crop_resize", "fill_resize"])]
+
 
 class ControlField(BaseModel):
     image: ImageField = Field(default=None, description="The control image")
@@ -104,6 +114,9 @@ class ControlField(BaseModel):
                                       description="When the ControlNet is first applied (% of total steps)")
     end_step_percent: float = Field(default=1, ge=0, le=1,
                                     description="When the ControlNet is last applied (% of total steps)")
+    control_mode: CONTROLNET_MODE_VALUES = Field(default="balanced", description="The control mode to use")
+    # resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
+
     @validator("control_weight")
     def abs_le_one(cls, v):
         """validate that all abs(values) are <=1"""
@@ -144,11 +157,11 @@ class ControlNetInvocation(BaseInvocation):
     control_model: CONTROLNET_NAME_VALUES = Field(default="lllyasviel/sd-controlnet-canny",
                                                   description="control model used")
     control_weight: Union[float, List[float]] = Field(default=1.0, description="The weight given to the ControlNet")
-    # TODO: add support in backend core for begin_step_percent, end_step_percent, guess_mode
     begin_step_percent: float = Field(default=0, ge=0, le=1,
                                       description="When the ControlNet is first applied (% of total steps)")
     end_step_percent: float = Field(default=1, ge=0, le=1,
                                     description="When the ControlNet is last applied (% of total steps)")
+    control_mode: CONTROLNET_MODE_VALUES = Field(default="balanced", description="The control mode used")
     # fmt: on
 
     class Config(InvocationConfig):
@@ -166,7 +179,6 @@ class ControlNetInvocation(BaseInvocation):
         }
 
     def invoke(self, context: InvocationContext) -> ControlOutput:
-
         return ControlOutput(
             control=ControlField(
                 image=self.image,
@@ -174,10 +186,11 @@ class ControlNetInvocation(BaseInvocation):
                 control_weight=self.control_weight,
                 begin_step_percent=self.begin_step_percent,
                 end_step_percent=self.end_step_percent,
+                control_mode=self.control_mode,
             ),
         )
 
-# TODO: move image processors to separate file (image_analysis.py
+
 class ImageProcessorInvocation(BaseInvocation, PILInvocationConfig):
     """Base class for invocations that preprocess images for ControlNet"""
 
@@ -449,6 +462,104 @@ class MediapipeFaceProcessorInvocation(ImageProcessorInvocation, PILInvocationCo
     # fmt: on
 
     def run_processor(self, image):
+        # MediaPipeFaceDetector throws an error if image has alpha channel
+        #     so convert to RGB if needed
+        if image.mode == 'RGBA':
+            image = image.convert('RGB')
         mediapipe_face_processor = MediapipeFaceDetector()
         processed_image = mediapipe_face_processor(image, max_faces=self.max_faces, min_confidence=self.min_confidence)
         return processed_image
+
+class LeresImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies leres processing to image"""
+    # fmt: off
+    type: Literal["leres_image_processor"] = "leres_image_processor"
+    # Inputs
+    thr_a: float = Field(default=0, description="Leres parameter `thr_a`")
+    thr_b: float = Field(default=0, description="Leres parameter `thr_b`")
+    boost: bool = Field(default=False, description="Whether to use boost mode")
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    # fmt: on
+
+    def run_processor(self, image):
+        leres_processor = LeresDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = leres_processor(image,
+                                          thr_a=self.thr_a,
+                                          thr_b=self.thr_b,
+                                          boost=self.boost,
+                                          detect_resolution=self.detect_resolution,
+                                          image_resolution=self.image_resolution)
+        return processed_image
+
+
+class TileResamplerProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+
+    # fmt: off
+    type: Literal["tile_image_processor"] = "tile_image_processor"
+    # Inputs
+    #res: int = Field(default=512, ge=0, le=1024, description="The pixel resolution for each tile")
+    down_sampling_rate: float = Field(default=1.0, ge=1.0, le=8.0, description="Down sampling rate")
+    # fmt: on
+
+    # tile_resample copied from sd-webui-controlnet/scripts/processor.py
+    def tile_resample(self,
+                      np_img: np.ndarray,
+                      res=512,   # never used?
+                      down_sampling_rate=1.0,
+                      ):
+        np_img = HWC3(np_img)
+        if down_sampling_rate < 1.1:
+            return np_img
+        H, W, C = np_img.shape
+        H = int(float(H) / float(down_sampling_rate))
+        W = int(float(W) / float(down_sampling_rate))
+        np_img = cv2.resize(np_img, (W, H), interpolation=cv2.INTER_AREA)
+        return np_img
+
+    def run_processor(self, img):
+        np_img = np.array(img, dtype=np.uint8)
+        processed_np_image = self.tile_resample(np_img,
+                                                #res=self.tile_size,
+                                                down_sampling_rate=self.down_sampling_rate
+                                                )
+        processed_image = Image.fromarray(processed_np_image)
+        return processed_image
+
+
+
+
+class SegmentAnythingProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies segment anything processing to image"""
+    # fmt: off
+    type: Literal["segment_anything_processor"] = "segment_anything_processor"
+    # fmt: on
+
+    def run_processor(self, image):
+        # segment_anything_processor = SamDetector.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")
+        segment_anything_processor = SamDetectorReproducibleColors.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")
+        np_img = np.array(image, dtype=np.uint8)
+        processed_image = segment_anything_processor(np_img)
+        return processed_image
+
+class SamDetectorReproducibleColors(SamDetector):
+
+    # overriding SamDetector.show_anns() method to use reproducible colors for segmentation image
+    #     base class show_anns() method randomizes colors,
+    #     which seems to also lead to non-reproducible image generation
+    # so using ADE20k color palette instead
+    def show_anns(self, anns: List[Dict]):
+        if len(anns) == 0:
+            return
+        sorted_anns = sorted(anns, key=(lambda x: x['area']), reverse=True)
+        h, w = anns[0]['segmentation'].shape
+        final_img = Image.fromarray(np.zeros((h, w, 3), dtype=np.uint8), mode="RGB")
+        palette = ade_palette()
+        for i, ann in enumerate(sorted_anns):
+            m = ann['segmentation']
+            img = np.empty((m.shape[0], m.shape[1], 3), dtype=np.uint8)
+            # doing modulo just in case number of annotated regions exceeds number of colors in palette
+            ann_color = palette[i % len(palette)]
+            img[:, :] = ann_color
+            final_img.paste(Image.fromarray(img, mode="RGB"), (0, 0), Image.fromarray(np.uint8(m * 255)))
+        return np.array(final_img, dtype=np.uint8)

invokeai/app/invocations/latent.py

@@ -23,7 +23,7 @@ from ...backend.stable_diffusion.diffusers_pipeline import (
 from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import \
     PostprocessingSettings
 from ...backend.stable_diffusion.schedulers import SCHEDULER_MAP
-from ...backend.util.devices import choose_torch_device, torch_dtype
+from ...backend.util.devices import torch_dtype
 from ...backend.model_management.lora import ModelPatcher
 from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
                              InvocationConfig, InvocationContext)
@@ -59,31 +59,12 @@ def build_latents_output(latents_name: str, latents: torch.Tensor):
           height=latents.size()[2] * 8,
       )
 
-class NoiseOutput(BaseInvocationOutput):
-    """Invocation noise output"""
-    #fmt: off
-    type:  Literal["noise_output"] = "noise_output"
-
-    # Inputs
-    noise: LatentsField            = Field(default=None, description="The output noise")
-    width:                     int = Field(description="The width of the noise in pixels")
-    height:                    int = Field(description="The height of the noise in pixels")
-    #fmt: on
-
-def build_noise_output(latents_name: str, latents: torch.Tensor):
-      return NoiseOutput(
-          noise=LatentsField(latents_name=latents_name),
-          width=latents.size()[3] * 8,
-          height=latents.size()[2] * 8,
-      )
-
 
 SAMPLER_NAME_VALUES = Literal[
     tuple(list(SCHEDULER_MAP.keys()))
 ]
 
 
-
 def get_scheduler(
     context: InvocationContext,
     scheduler_info: ModelInfo,
@@ -105,62 +86,6 @@ def get_scheduler(
     return scheduler
 
 
-def get_noise(width:int, height:int, device:torch.device, seed:int = 0, latent_channels:int=4, use_mps_noise:bool=False, downsampling_factor:int = 8):
-    # limit noise to only the diffusion image channels, not the mask channels
-    input_channels = min(latent_channels, 4)
-    use_device = "cpu" if (use_mps_noise or device.type == "mps") else device
-    generator = torch.Generator(device=use_device).manual_seed(seed)
-    x = torch.randn(
-        [
-            1,
-            input_channels,
-            height // downsampling_factor,
-            width //  downsampling_factor,
-        ],
-        dtype=torch_dtype(device),
-        device=use_device,
-        generator=generator,
-    ).to(device)
-    # if self.perlin > 0.0:
-    #     perlin_noise = self.get_perlin_noise(
-    #         width // self.downsampling_factor, height // self.downsampling_factor
-    #     )
-    #     x = (1 - self.perlin) * x + self.perlin * perlin_noise
-    return x
-
-class NoiseInvocation(BaseInvocation):
-    """Generates latent noise."""
-
-    type: Literal["noise"] = "noise"
-
-    # Inputs
-    seed:       int = Field(ge=0, le=SEED_MAX, description="The seed to use", default_factory=get_random_seed)
-    width:       int = Field(default=512, multiple_of=8, gt=0, description="The width of the resulting noise", )
-    height:      int = Field(default=512, multiple_of=8, gt=0, description="The height of the resulting noise", )
-
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["latents", "noise"],
-            },
-        }
-
-    @validator("seed", pre=True)
-    def modulo_seed(cls, v):
-        """Returns the seed modulo SEED_MAX to ensure it is within the valid range."""
-        return v % SEED_MAX
-
-    def invoke(self, context: InvocationContext) -> NoiseOutput:
-        device = torch.device(choose_torch_device())
-        noise = get_noise(self.width, self.height, device, self.seed)
-
-        name = f'{context.graph_execution_state_id}__{self.id}'
-        context.services.latents.save(name, noise)
-        return build_noise_output(latents_name=name, latents=noise)
-
-
 # Text to image
 class TextToLatentsInvocation(BaseInvocation):
     """Generates latents from conditionings."""
@@ -287,19 +212,14 @@ class TextToLatentsInvocation(BaseInvocation):
         control_height_resize = latents_shape[2] * 8
         control_width_resize = latents_shape[3] * 8
         if control_input is None:
-            # print("control input is None")
             control_list = None
         elif isinstance(control_input, list) and len(control_input) == 0:
-            # print("control input is empty list")
             control_list = None
         elif isinstance(control_input, ControlField):
-            # print("control input is ControlField")
             control_list = [control_input]
         elif isinstance(control_input, list) and len(control_input) > 0 and isinstance(control_input[0], ControlField):
-            # print("control input is list[ControlField]")
             control_list = control_input
         else:
-            # print("input control is unrecognized:", type(self.control))
             control_list = None
         if (control_list is None):
             control_data = None
@@ -341,12 +261,15 @@ class TextToLatentsInvocation(BaseInvocation):
                     # num_images_per_prompt=num_images_per_prompt,
                     device=control_model.device,
                     dtype=control_model.dtype,
+                    control_mode=control_info.control_mode,
                 )
                 control_item = ControlNetData(model=control_model,
                                               image_tensor=control_image,
                                               weight=control_info.control_weight,
                                               begin_step_percent=control_info.begin_step_percent,
-                                              end_step_percent=control_info.end_step_percent)
+                                              end_step_percent=control_info.end_step_percent,
+                                              control_mode=control_info.control_mode,
+                                              )
                 control_data.append(control_item)
                 # MultiControlNetModel has been refactored out, just need list[ControlNetData]
         return control_data
@@ -362,8 +285,7 @@ class TextToLatentsInvocation(BaseInvocation):
             self.dispatch_progress(context, source_node_id, state)
 
         unet_info = context.services.model_manager.get_model(**self.unet.unet.dict())
-        with unet_info as unet,\
-             ExitStack() as stack:
+        with unet_info as unet:
 
             scheduler = get_scheduler(
                 context=context,
@@ -374,7 +296,7 @@ class TextToLatentsInvocation(BaseInvocation):
             pipeline = self.create_pipeline(unet, scheduler)
             conditioning_data = self.get_conditioning_data(context, scheduler)
 
-            loras = [(stack.enter_context(context.services.model_manager.get_model(**lora.dict(exclude={"weight"}))), lora.weight) for lora in self.unet.loras]
+            loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.unet.loras]
 
             control_data = self.prep_control_data(
                 model=pipeline, context=context, control_input=self.control,
@@ -438,8 +360,7 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
             **self.unet.unet.dict(),
         )
 
-        with unet_info as unet,\
-             ExitStack() as stack:
+        with unet_info as unet:
 
             scheduler = get_scheduler(
                 context=context,
@@ -468,7 +389,7 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
                 device=unet.device,
             )
 
-            loras = [(stack.enter_context(context.services.model_manager.get_model(**lora.dict(exclude={"weight"}))), lora.weight) for lora in self.unet.loras]
+            loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.unet.loras]
 
             with ModelPatcher.apply_lora_unet(pipeline.unet, loras):
                 result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
@@ -543,6 +464,7 @@ class LatentsToImageInvocation(BaseInvocation):
             image_category=ImageCategory.GENERAL,
             node_id=self.id,
             session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate
         )
 
         return ImageOutput(

invokeai/app/invocations/model.py

@@ -73,7 +73,7 @@ class PipelineModelLoaderInvocation(BaseInvocation):
 
         base_model = self.model.base_model
         model_name = self.model.model_name
-        model_type = ModelType.Pipeline
+        model_type = ModelType.Main
 
         # TODO: not found exceptions
         if not context.services.model_manager.model_exists(
@@ -177,9 +177,13 @@ class LoraLoaderInvocation(BaseInvocation):
 
     def invoke(self, context: InvocationContext) -> LoraLoaderOutput:
 
+        # TODO: ui rewrite
+        base_model = BaseModelType.StableDiffusion1
+
         if not context.services.model_manager.model_exists(
+            base_model=base_model,
             model_name=self.lora_name,
-            model_type=SDModelType.Lora,
+            model_type=ModelType.Lora,
         ):
             raise Exception(f"Unkown lora name: {self.lora_name}!")
 
@@ -195,8 +199,9 @@ class LoraLoaderInvocation(BaseInvocation):
             output.unet = copy.deepcopy(self.unet)
             output.unet.loras.append(
                 LoraInfo(
+                    base_model=base_model,
                     model_name=self.lora_name,
-                    model_type=SDModelType.Lora,
+                    model_type=ModelType.Lora,
                     submodel=None,
                     weight=self.weight,
                 )
@@ -206,8 +211,9 @@ class LoraLoaderInvocation(BaseInvocation):
             output.clip = copy.deepcopy(self.clip)
             output.clip.loras.append(
                 LoraInfo(
+                    base_model=base_model,
                     model_name=self.lora_name,
-                    model_type=SDModelType.Lora,
+                    model_type=ModelType.Lora,
                     submodel=None,
                     weight=self.weight,
                 )

invokeai/app/invocations/noise.py

@@ -0,0 +1,134 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) & the InvokeAI Team
+
+import math
+from typing import Literal
+
+from pydantic import Field, validator
+import torch
+from invokeai.app.invocations.latent import LatentsField
+
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+from ...backend.util.devices import choose_torch_device, torch_dtype
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    InvocationConfig,
+    InvocationContext,
+)
+
+"""
+Utilities
+"""
+
+
+def get_noise(
+    width: int,
+    height: int,
+    device: torch.device,
+    seed: int = 0,
+    latent_channels: int = 4,
+    downsampling_factor: int = 8,
+    use_cpu: bool = True,
+    perlin: float = 0.0,
+):
+    """Generate noise for a given image size."""
+    noise_device_type = "cpu" if (use_cpu or device.type == "mps") else device.type
+
+    # limit noise to only the diffusion image channels, not the mask channels
+    input_channels = min(latent_channels, 4)
+    generator = torch.Generator(device=noise_device_type).manual_seed(seed)
+
+    noise_tensor = torch.randn(
+        [
+            1,
+            input_channels,
+            height // downsampling_factor,
+            width // downsampling_factor,
+        ],
+        dtype=torch_dtype(device),
+        device=noise_device_type,
+        generator=generator,
+    ).to(device)
+
+    return noise_tensor
+
+
+"""
+Nodes
+"""
+
+
+class NoiseOutput(BaseInvocationOutput):
+    """Invocation noise output"""
+
+    # fmt: off
+    type:  Literal["noise_output"] = "noise_output"
+
+    # Inputs
+    noise: LatentsField            = Field(default=None, description="The output noise")
+    width:                     int = Field(description="The width of the noise in pixels")
+    height:                    int = Field(description="The height of the noise in pixels")
+    # fmt: on
+
+
+def build_noise_output(latents_name: str, latents: torch.Tensor):
+    return NoiseOutput(
+        noise=LatentsField(latents_name=latents_name),
+        width=latents.size()[3] * 8,
+        height=latents.size()[2] * 8,
+    )
+
+
+class NoiseInvocation(BaseInvocation):
+    """Generates latent noise."""
+
+    type: Literal["noise"] = "noise"
+
+    # Inputs
+    seed: int = Field(
+        ge=0,
+        le=SEED_MAX,
+        description="The seed to use",
+        default_factory=get_random_seed,
+    )
+    width: int = Field(
+        default=512,
+        multiple_of=8,
+        gt=0,
+        description="The width of the resulting noise",
+    )
+    height: int = Field(
+        default=512,
+        multiple_of=8,
+        gt=0,
+        description="The height of the resulting noise",
+    )
+    use_cpu: bool = Field(
+        default=True,
+        description="Use CPU for noise generation (for reproducible results across platforms)",
+    )
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents", "noise"],
+            },
+        }
+
+    @validator("seed", pre=True)
+    def modulo_seed(cls, v):
+        """Returns the seed modulo SEED_MAX to ensure it is within the valid range."""
+        return v % SEED_MAX
+
+    def invoke(self, context: InvocationContext) -> NoiseOutput:
+        noise = get_noise(
+            width=self.width,
+            height=self.height,
+            device=choose_torch_device(),
+            seed=self.seed,
+            use_cpu=self.use_cpu,
+        )
+        name = f"{context.graph_execution_state_id}__{self.id}"
+        context.services.latents.save(name, noise)
+        return build_noise_output(latents_name=name, latents=noise)

invokeai/app/invocations/param_easing.py

@@ -133,20 +133,19 @@ class StepParamEasingInvocation(BaseInvocation):
         postlist = list(num_poststeps * [self.post_end_value])
 
         if log_diagnostics:
-            logger = InvokeAILogger.getLogger(name="StepParamEasing")
-            logger.debug("start_step: " + str(start_step))
-            logger.debug("end_step: " + str(end_step))
-            logger.debug("num_easing_steps: " + str(num_easing_steps))
-            logger.debug("num_presteps: " + str(num_presteps))
-            logger.debug("num_poststeps: " + str(num_poststeps))
-            logger.debug("prelist size: " + str(len(prelist)))
-            logger.debug("postlist size: " + str(len(postlist)))
-            logger.debug("prelist: " + str(prelist))
-            logger.debug("postlist: " + str(postlist))
+            context.services.logger.debug("start_step: " + str(start_step))
+            context.services.logger.debug("end_step: " + str(end_step))
+            context.services.logger.debug("num_easing_steps: " + str(num_easing_steps))
+            context.services.logger.debug("num_presteps: " + str(num_presteps))
+            context.services.logger.debug("num_poststeps: " + str(num_poststeps))
+            context.services.logger.debug("prelist size: " + str(len(prelist)))
+            context.services.logger.debug("postlist size: " + str(len(postlist)))
+            context.services.logger.debug("prelist: " + str(prelist))
+            context.services.logger.debug("postlist: " + str(postlist))
 
         easing_class = EASING_FUNCTIONS_MAP[self.easing]
         if log_diagnostics:
-            logger.debug("easing class: " + str(easing_class))
+            context.services.logger.debug("easing class: " + str(easing_class))
         easing_list = list()
         if self.mirror:  # "expected" mirroring
             # if number of steps is even, squeeze duration down to (number_of_steps)/2
@@ -156,7 +155,7 @@ class StepParamEasingInvocation(BaseInvocation):
             # but if even then number_of_steps/2 === ceil(number_of_steps/2), so can just use ceil always
 
             base_easing_duration = int(np.ceil(num_easing_steps/2.0))
-            if log_diagnostics: logger.debug("base easing duration: " + str(base_easing_duration))
+            if log_diagnostics: context.services.logger.debug("base easing duration: " + str(base_easing_duration))
             even_num_steps = (num_easing_steps % 2 == 0)  # even number of steps
             easing_function = easing_class(start=self.start_value,
                                            end=self.end_value,
@@ -166,14 +165,14 @@ class StepParamEasingInvocation(BaseInvocation):
                 easing_val = easing_function.ease(step_index)
                 base_easing_vals.append(easing_val)
                 if log_diagnostics:
-                    logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(easing_val))
+                    context.services.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(easing_val))
             if even_num_steps:
                 mirror_easing_vals = list(reversed(base_easing_vals))
             else:
                 mirror_easing_vals = list(reversed(base_easing_vals[0:-1]))
             if log_diagnostics:
-                logger.debug("base easing vals: " + str(base_easing_vals))
-                logger.debug("mirror easing vals: " + str(mirror_easing_vals))
+                context.services.logger.debug("base easing vals: " + str(base_easing_vals))
+                context.services.logger.debug("mirror easing vals: " + str(mirror_easing_vals))
             easing_list = base_easing_vals + mirror_easing_vals
 
         # FIXME: add alt_mirror option (alternative to default or mirror), or remove entirely
@@ -206,12 +205,12 @@ class StepParamEasingInvocation(BaseInvocation):
                 step_val = easing_function.ease(step_index)
                 easing_list.append(step_val)
                 if log_diagnostics:
-                    logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(step_val))
+                    context.services.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(step_val))
 
         if log_diagnostics:
-            logger.debug("prelist size: " + str(len(prelist)))
-            logger.debug("easing_list size: " + str(len(easing_list)))
-            logger.debug("postlist size: " + str(len(postlist)))
+            context.services.logger.debug("prelist size: " + str(len(prelist)))
+            context.services.logger.debug("easing_list size: " + str(len(easing_list)))
+            context.services.logger.debug("postlist size: " + str(len(postlist)))
 
         param_list = prelist + easing_list + postlist
 

invokeai/app/services/config.py

@@ -15,7 +15,7 @@ InvokeAI:
     conf_path: configs/models.yaml
     legacy_conf_dir: configs/stable-diffusion
     outdir: outputs
-    autoconvert_dir: null
+    autoimport_dir: null
   Models:
     model: stable-diffusion-1.5
     embeddings: true
@@ -367,16 +367,19 @@ setting environment variables INVOKEAI_<setting>.
 
     always_use_cpu      : bool = Field(default=False, description="If true, use the CPU for rendering even if a GPU is available.", category='Memory/Performance')
     free_gpu_mem        : bool = Field(default=False, description="If true, purge model from GPU after each generation.", category='Memory/Performance')
-    max_loaded_models   : int = Field(default=2, gt=0, description="Maximum number of models to keep in memory for rapid switching", category='Memory/Performance')
+    max_loaded_models   : int = Field(default=3, gt=0, description="Maximum number of models to keep in memory for rapid switching", category='Memory/Performance')
     precision           : Literal[tuple(['auto','float16','float32','autocast'])] = Field(default='float16',description='Floating point precision', category='Memory/Performance')
     sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", category='Memory/Performance')
     xformers_enabled    : bool = Field(default=True, description="Enable/disable memory-efficient attention", category='Memory/Performance')
     tiled_decode        : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", category='Memory/Performance')
 
     root                : Path = Field(default=_find_root(), description='InvokeAI runtime root directory', category='Paths')
-    autoconvert_dir     : Path = Field(default=None, description='Path to a directory of ckpt files to be converted into diffusers and imported on startup.', category='Paths')
+    autoimport_dir      : Path = Field(default='autoimport/main', description='Path to a directory of models files to be imported on startup.', category='Paths')
+    lora_dir            : Path = Field(default='autoimport/lora', description='Path to a directory of LoRA/LyCORIS models to be imported on startup.', category='Paths')
+    embedding_dir       : Path = Field(default='autoimport/embedding', description='Path to a directory of Textual Inversion embeddings to be imported on startup.', category='Paths')
+    controlnet_dir      : Path = Field(default='autoimport/controlnet', description='Path to a directory of ControlNet embeddings to be imported on startup.', category='Paths')
     conf_path           : Path = Field(default='configs/models.yaml', description='Path to models definition file', category='Paths')
-    models_dir          : Path = Field(default='./models', description='Path to the models directory', category='Paths')
+    models_dir          : Path = Field(default='models', description='Path to the models directory', category='Paths')
     legacy_conf_dir     : Path = Field(default='configs/stable-diffusion', description='Path to directory of legacy checkpoint config files', category='Paths')
     db_dir              : Path = Field(default='databases', description='Path to InvokeAI databases directory', category='Paths')
     outdir              : Path = Field(default='outputs', description='Default folder for output images', category='Paths')

invokeai/app/services/default_graphs.py

@@ -1,4 +1,5 @@
-from ..invocations.latent import LatentsToImageInvocation, NoiseInvocation, TextToLatentsInvocation
+from ..invocations.latent import LatentsToImageInvocation, TextToLatentsInvocation
+from ..invocations.noise import NoiseInvocation
 from ..invocations.compel import CompelInvocation
 from ..invocations.params import ParamIntInvocation
 from .graph import Edge, EdgeConnection, ExposedNodeInput, ExposedNodeOutput, Graph, LibraryGraph

invokeai/app/services/image_file_storage.py

@@ -85,8 +85,10 @@ class DiskImageFileStorage(ImageFileStorageBase):
         self.__cache_ids = Queue()
         self.__max_cache_size = 10  # TODO: get this from config
 
-        self.__output_folder: Path = output_folder if isinstance(output_folder, Path) else Path(output_folder)
-        self.__thumbnails_folder = self.__output_folder / 'thumbnails'
+        self.__output_folder: Path = (
+            output_folder if isinstance(output_folder, Path) else Path(output_folder)
+        )
+        self.__thumbnails_folder = self.__output_folder / "thumbnails"
 
         # Validate required output folders at launch
         self.__validate_storage_folders()
@@ -94,7 +96,7 @@ class DiskImageFileStorage(ImageFileStorageBase):
     def get(self, image_name: str) -> PILImageType:
         try:
             image_path = self.get_path(image_name)
-            
+
             cache_item = self.__get_cache(image_path)
             if cache_item:
                 return cache_item
@@ -155,7 +157,7 @@ class DiskImageFileStorage(ImageFileStorageBase):
     # TODO: make this a bit more flexible for e.g. cloud storage
     def get_path(self, image_name: str, thumbnail: bool = False) -> Path:
         path = self.__output_folder / image_name
-        
+
         if thumbnail:
             thumbnail_name = get_thumbnail_name(image_name)
             path = self.__thumbnails_folder / thumbnail_name
@@ -166,7 +168,7 @@ class DiskImageFileStorage(ImageFileStorageBase):
         """Validates the path given for an image or thumbnail."""
         path = path if isinstance(path, Path) else Path(path)
         return path.exists()
-    
+
     def __validate_storage_folders(self) -> None:
         """Checks if the required output folders exist and create them if they don't"""
         folders: list[Path] = [self.__output_folder, self.__thumbnails_folder]
@@ -179,7 +181,9 @@ class DiskImageFileStorage(ImageFileStorageBase):
     def __set_cache(self, image_name: Path, image: PILImageType):
         if not image_name in self.__cache:
             self.__cache[image_name] = image
-            self.__cache_ids.put(image_name)  # TODO: this should refresh position for LRU cache
+            self.__cache_ids.put(
+                image_name
+            )  # TODO: this should refresh position for LRU cache
             if len(self.__cache) > self.__max_cache_size:
                 cache_id = self.__cache_ids.get()
                 if cache_id in self.__cache:

invokeai/app/services/image_record_storage.py

@@ -94,6 +94,11 @@ class ImageRecordStorageBase(ABC):
         """Deletes an image record."""
         pass
 
+    @abstractmethod
+    def delete_many(self, image_names: list[str]) -> None:
+        """Deletes many image records."""
+        pass
+
     @abstractmethod
     def save(
         self,
@@ -385,6 +390,25 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
         finally:
             self._lock.release()
 
+    def delete_many(self, image_names: list[str]) -> None:
+        try:
+            placeholders = ",".join("?" for _ in image_names)
+
+            self._lock.acquire()
+
+            # Construct the SQLite query with the placeholders
+            query = f"DELETE FROM images WHERE image_name IN ({placeholders})"
+
+            # Execute the query with the list of IDs as parameters
+            self._cursor.execute(query, image_names)
+
+            self._conn.commit()
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise ImageRecordDeleteException from e
+        finally:
+            self._lock.release()
+
     def save(
         self,
         image_name: str,

invokeai/app/services/images.py

@@ -112,6 +112,11 @@ class ImageServiceABC(ABC):
         """Deletes an image."""
         pass
 
+    @abstractmethod
+    def delete_images_on_board(self, board_id: str):
+        """Deletes all images on a board."""
+        pass
+
 
 class ImageServiceDependencies:
     """Service dependencies for the ImageService."""
@@ -341,6 +346,28 @@ class ImageService(ImageServiceABC):
             self._services.logger.error("Problem deleting image record and file")
             raise e
 
+    def delete_images_on_board(self, board_id: str):
+        try:
+            images = self._services.board_image_records.get_images_for_board(board_id)
+            image_name_list = list(
+                map(
+                    lambda r: r.image_name,
+                    images.items,
+                )
+            )
+            for image_name in image_name_list:
+                self._services.image_files.delete(image_name)
+            self._services.image_records.delete_many(image_name_list)
+        except ImageRecordDeleteException:
+            self._services.logger.error(f"Failed to delete image records")
+            raise
+        except ImageFileDeleteException:
+            self._services.logger.error(f"Failed to delete image files")
+            raise
+        except Exception as e:
+            self._services.logger.error("Problem deleting image records and files")
+            raise e
+
     def _get_metadata(
         self, session_id: Optional[str] = None, node_id: Optional[str] = None
     ) -> Union[ImageMetadata, None]:

invokeai/app/services/model_manager_service.py

@@ -168,6 +168,8 @@ class ModelManagerService(ModelManagerServiceBase):
         logger.debug(f'config file={config_file}')
 
         device = torch.device(choose_torch_device())
+        logger.debug(f'GPU device = {device}')
+
         precision = config.precision
         if precision == "auto":
             precision = choose_precision(device)

invokeai/backend/install/invokeai_configure.py

@@ -7,8 +7,6 @@
 # Coauthor: Kevin Turner http://github.com/keturn
 #
 import sys
-print("Loading Python libraries...\n",file=sys.stderr)
-
 import argparse
 import io
 import os
@@ -16,6 +14,7 @@ import shutil
 import textwrap
 import traceback
 import warnings
+import yaml
 from argparse import Namespace
 from pathlib import Path
 from shutil import get_terminal_size
@@ -25,6 +24,7 @@ from urllib import request
 import npyscreen
 import transformers
 from diffusers import AutoencoderKL
+from diffusers.pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker
 from huggingface_hub import HfFolder
 from huggingface_hub import login as hf_hub_login
 from omegaconf import OmegaConf
@@ -34,6 +34,8 @@ from transformers import (
     CLIPSegForImageSegmentation,
     CLIPTextModel,
     CLIPTokenizer,
+    AutoFeatureExtractor,
+    BertTokenizerFast,
 )
 import invokeai.configs as configs
 
@@ -43,6 +45,7 @@ from invokeai.app.services.config import (
 from invokeai.backend.util.logging import InvokeAILogger
 from invokeai.frontend.install.model_install import addModelsForm, process_and_execute
 from invokeai.frontend.install.widgets import (
+    SingleSelectColumns,
     CenteredButtonPress,
     IntTitleSlider,
     set_min_terminal_size,
@@ -52,12 +55,13 @@ from invokeai.frontend.install.widgets import (
 )
 from invokeai.backend.install.legacy_arg_parsing import legacy_parser
 from invokeai.backend.install.model_install_backend import (
-    default_dataset,
-    download_from_hf,
-    hf_download_with_resume,
-    recommended_datasets,
-    UserSelections,
+    hf_download_from_pretrained,
+    InstallSelections,
+    ModelInstall,
 )
+from invokeai.backend.model_management.model_probe import (
+    ModelType, BaseModelType
+    )
 
 warnings.filterwarnings("ignore")
 transformers.logging.set_verbosity_error()
@@ -73,7 +77,7 @@ Weights_dir = "ldm/stable-diffusion-v1/"
 Default_config_file = config.model_conf_path
 SD_Configs = config.legacy_conf_path
 
-PRECISION_CHOICES = ['auto','float16','float32','autocast']
+PRECISION_CHOICES = ['auto','float16','float32']
 
 INIT_FILE_PREAMBLE = """# InvokeAI initialization file
 # This is the InvokeAI initialization file, which contains command-line default values.
@@ -81,7 +85,7 @@ INIT_FILE_PREAMBLE = """# InvokeAI initialization file
 # or renaming it and then running invokeai-configure again.
 """
 
-logger=None
+logger=InvokeAILogger.getLogger()
 
 # --------------------------------------------
 def postscript(errors: None):
@@ -162,75 +166,91 @@ class ProgressBar:
 # ---------------------------------------------
 def download_with_progress_bar(model_url: str, model_dest: str, label: str = "the"):
     try:
-        print(f"Installing {label} model file {model_url}...", end="", file=sys.stderr)
+        logger.info(f"Installing {label} model file {model_url}...")
         if not os.path.exists(model_dest):
             os.makedirs(os.path.dirname(model_dest), exist_ok=True)
             request.urlretrieve(
                 model_url, model_dest, ProgressBar(os.path.basename(model_dest))
             )
-            print("...downloaded successfully", file=sys.stderr)
+            logger.info("...downloaded successfully")
         else:
-            print("...exists", file=sys.stderr)
+            logger.info("...exists")
     except Exception:
-        print("...download failed", file=sys.stderr)
-        print(f"Error downloading {label} model", file=sys.stderr)
+        logger.info("...download failed")
+        logger.info(f"Error downloading {label} model")
         print(traceback.format_exc(), file=sys.stderr)
 
 
-# ---------------------------------------------
-# this will preload the Bert tokenizer fles
-def download_bert():
-    print("Installing bert tokenizer...", file=sys.stderr)
-    with warnings.catch_warnings():
-        warnings.filterwarnings("ignore", category=DeprecationWarning)
-        from transformers import BertTokenizerFast
+def download_conversion_models():
+    target_dir = config.root_path / 'models/core/convert'
+    kwargs = dict()  # for future use
+    try:
+        logger.info('Downloading core tokenizers and text encoders')
 
-        download_from_hf(BertTokenizerFast, "bert-base-uncased")
+        # bert
+        with warnings.catch_warnings():
+            warnings.filterwarnings("ignore", category=DeprecationWarning)
+            bert = BertTokenizerFast.from_pretrained("bert-base-uncased", **kwargs)
+            bert.save_pretrained(target_dir / 'bert-base-uncased', safe_serialization=True)
+        
+        # sd-1
+        repo_id = 'openai/clip-vit-large-patch14'
+        hf_download_from_pretrained(CLIPTokenizer, repo_id, target_dir / 'clip-vit-large-patch14')
+        hf_download_from_pretrained(CLIPTextModel, repo_id, target_dir / 'clip-vit-large-patch14')
 
+        # sd-2
+        repo_id = "stabilityai/stable-diffusion-2"
+        pipeline = CLIPTokenizer.from_pretrained(repo_id, subfolder="tokenizer", **kwargs)
+        pipeline.save_pretrained(target_dir / 'stable-diffusion-2-clip' / 'tokenizer', safe_serialization=True)
 
-# ---------------------------------------------
-def download_sd1_clip():
-    print("Installing SD1 clip model...", file=sys.stderr)
-    version = "openai/clip-vit-large-patch14"
-    download_from_hf(CLIPTokenizer, version)
-    download_from_hf(CLIPTextModel, version)
+        pipeline = CLIPTextModel.from_pretrained(repo_id, subfolder="text_encoder", **kwargs)
+        pipeline.save_pretrained(target_dir / 'stable-diffusion-2-clip' / 'text_encoder', safe_serialization=True)
 
+        # VAE
+        logger.info('Downloading stable diffusion VAE')
+        vae = AutoencoderKL.from_pretrained('stabilityai/sd-vae-ft-mse', **kwargs)
+        vae.save_pretrained(target_dir / 'sd-vae-ft-mse', safe_serialization=True)
 
-# ---------------------------------------------
-def download_sd2_clip():
-    version = "stabilityai/stable-diffusion-2"
-    print("Installing SD2 clip model...", file=sys.stderr)
-    download_from_hf(CLIPTokenizer, version, subfolder="tokenizer")
-    download_from_hf(CLIPTextModel, version, subfolder="text_encoder")
+        # safety checking
+        logger.info('Downloading safety checker')
+        repo_id = "CompVis/stable-diffusion-safety-checker"
+        pipeline = AutoFeatureExtractor.from_pretrained(repo_id,**kwargs)
+        pipeline.save_pretrained(target_dir / 'stable-diffusion-safety-checker', safe_serialization=True)
 
+        pipeline = StableDiffusionSafetyChecker.from_pretrained(repo_id,**kwargs)
+        pipeline.save_pretrained(target_dir / 'stable-diffusion-safety-checker', safe_serialization=True)
+    except KeyboardInterrupt:
+        raise
+    except Exception as e:
+        logger.error(str(e))
 
 # ---------------------------------------------
 def download_realesrgan():
-    print("Installing models from RealESRGAN...", file=sys.stderr)
+    logger.info("Installing models from RealESRGAN...")
     model_url = "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth"
     wdn_model_url = "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-wdn-x4v3.pth"
 
-    model_dest = config.root_path / "models/realesrgan/realesr-general-x4v3.pth"
-    wdn_model_dest = config.root_path / "models/realesrgan/realesr-general-wdn-x4v3.pth"
+    model_dest = config.root_path / "models/core/upscaling/realesrgan/realesr-general-x4v3.pth"
+    wdn_model_dest = config.root_path / "models/core/upscaling/realesrgan/realesr-general-wdn-x4v3.pth"
 
     download_with_progress_bar(model_url, str(model_dest), "RealESRGAN")
     download_with_progress_bar(wdn_model_url, str(wdn_model_dest), "RealESRGANwdn")
 
 
 def download_gfpgan():
-    print("Installing GFPGAN models...", file=sys.stderr)
+    logger.info("Installing GFPGAN models...")
     for model in (
         [
             "https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth",
-            "./models/gfpgan/GFPGANv1.4.pth",
+            "./models/core/face_restoration/gfpgan/GFPGANv1.4.pth",
         ],
         [
             "https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_Resnet50_Final.pth",
-            "./models/gfpgan/weights/detection_Resnet50_Final.pth",
+            "./models/core/face_restoration/gfpgan/weights/detection_Resnet50_Final.pth",
         ],
         [
             "https://github.com/xinntao/facexlib/releases/download/v0.2.2/parsing_parsenet.pth",
-            "./models/gfpgan/weights/parsing_parsenet.pth",
+            "./models/core/face_restoration/gfpgan/weights/parsing_parsenet.pth",
         ],
     ):
         model_url, model_dest = model[0], config.root_path / model[1]
@@ -239,70 +259,32 @@ def download_gfpgan():
 
 # ---------------------------------------------
 def download_codeformer():
-    print("Installing CodeFormer model file...", file=sys.stderr)
+    logger.info("Installing CodeFormer model file...")
     model_url = (
         "https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth"
     )
-    model_dest = config.root_path / "models/codeformer/codeformer.pth"
+    model_dest = config.root_path / "models/core/face_restoration/codeformer/codeformer.pth"
     download_with_progress_bar(model_url, str(model_dest), "CodeFormer")
 
 
 # ---------------------------------------------
 def download_clipseg():
-    print("Installing clipseg model for text-based masking...", file=sys.stderr)
+    logger.info("Installing clipseg model for text-based masking...")
     CLIPSEG_MODEL = "CIDAS/clipseg-rd64-refined"
     try:
-        download_from_hf(AutoProcessor, CLIPSEG_MODEL)
-        download_from_hf(CLIPSegForImageSegmentation, CLIPSEG_MODEL)
+        hf_download_from_pretrained(AutoProcessor, CLIPSEG_MODEL, config.root_path / 'models/core/misc/clipseg')
+        hf_download_from_pretrained(CLIPSegForImageSegmentation, CLIPSEG_MODEL, config.root_path / 'models/core/misc/clipseg')
     except Exception:
-        print("Error installing clipseg model:")
-        print(traceback.format_exc())
+        logger.info("Error installing clipseg model:")
+        logger.info(traceback.format_exc())
 
 
-# -------------------------------------
-def download_safety_checker():
-    print("Installing model for NSFW content detection...", file=sys.stderr)
-    try:
-        from diffusers.pipelines.stable_diffusion.safety_checker import (
-            StableDiffusionSafetyChecker,
-        )
-        from transformers import AutoFeatureExtractor
-    except ModuleNotFoundError:
-        print("Error installing NSFW checker model:")
-        print(traceback.format_exc())
-        return
-    safety_model_id = "CompVis/stable-diffusion-safety-checker"
-    print("AutoFeatureExtractor...", file=sys.stderr)
-    download_from_hf(AutoFeatureExtractor, safety_model_id)
-    print("StableDiffusionSafetyChecker...", file=sys.stderr)
-    download_from_hf(StableDiffusionSafetyChecker, safety_model_id)
-
-
-# -------------------------------------
-def download_vaes():
-    print("Installing stabilityai VAE...", file=sys.stderr)
-    try:
-        # first the diffusers version
-        repo_id = "stabilityai/sd-vae-ft-mse"
-        args = dict(
-            cache_dir=config.cache_dir,
-        )
-        if not AutoencoderKL.from_pretrained(repo_id, **args):
-            raise Exception(f"download of {repo_id} failed")
-
-        repo_id = "stabilityai/sd-vae-ft-mse-original"
-        model_name = "vae-ft-mse-840000-ema-pruned.ckpt"
-        # next the legacy checkpoint version
-        if not hf_download_with_resume(
-            repo_id=repo_id,
-            model_name=model_name,
-            model_dir=str(config.root_path / Model_dir / Weights_dir),
-        ):
-            raise Exception(f"download of {model_name} failed")
-    except Exception as e:
-        print(f"Error downloading StabilityAI standard VAE: {str(e)}", file=sys.stderr)
-        print(traceback.format_exc(), file=sys.stderr)
-
+def download_support_models():
+    download_realesrgan()
+    download_gfpgan()
+    download_codeformer()
+    download_clipseg()
+    download_conversion_models()
 
 # -------------------------------------
 def get_root(root: str = None) -> str:
@@ -378,9 +360,7 @@ Use cursor arrows to make a checkbox selection, and space to toggle.
             scroll_exit=True,
         )
         self.nextrely += 1
-        label = """If you have an account at HuggingFace you may optionally paste your access token here
-to allow InvokeAI to download restricted styles & subjects from the "Concept Library". See https://huggingface.co/settings/tokens.
-"""
+        label = """HuggingFace access token (OPTIONAL) for automatic model downloads. See https://huggingface.co/settings/tokens."""
         for line in textwrap.wrap(label,width=window_width-6):
             self.add_widget_intelligent(
                 npyscreen.FixedText,
@@ -442,6 +422,7 @@ to allow InvokeAI to download restricted styles & subjects from the "Concept Lib
         )
         self.precision = self.add_widget_intelligent(
             npyscreen.TitleSelectOne,
+            columns = 2,
             name="Precision",
             values=PRECISION_CHOICES,
             value=PRECISION_CHOICES.index(precision),
@@ -465,39 +446,19 @@ to allow InvokeAI to download restricted styles & subjects from the "Concept Lib
             editable=False,
             color="CONTROL",
         )
-        self.embedding_dir = self.add_widget_intelligent(
-            npyscreen.TitleFilename,
-            name=" Textual Inversion Embeddings:",
-            value=str(default_embedding_dir()),
-            select_dir=True,
-            must_exist=False,
-            use_two_lines=False,
-            labelColor="GOOD",
-            begin_entry_at=32,
-            scroll_exit=True,
-        )
-        self.lora_dir = self.add_widget_intelligent(
-            npyscreen.TitleFilename,
-            name="             LoRA and LyCORIS:",
-            value=str(default_lora_dir()),
-            select_dir=True,
-            must_exist=False,
-            use_two_lines=False,
-            labelColor="GOOD",
-            begin_entry_at=32,
-            scroll_exit=True,
-        )
-        self.controlnet_dir = self.add_widget_intelligent(
-            npyscreen.TitleFilename,
-            name="             ControlNets:",
-            value=str(default_controlnet_dir()),
-            select_dir=True,
-            must_exist=False,
-            use_two_lines=False,
-            labelColor="GOOD",
-            begin_entry_at=32,
-            scroll_exit=True,
-        )
+        self.autoimport_dirs = {}
+        for description, config_name, path in autoimport_paths(old_opts):
+            self.autoimport_dirs[config_name] = self.add_widget_intelligent(
+                npyscreen.TitleFilename,
+                name=description+':',
+                value=str(path),
+                select_dir=True,
+                must_exist=False,
+                use_two_lines=False,
+                labelColor="GOOD",
+                begin_entry_at=32,
+                scroll_exit=True
+            )
         self.nextrely += 1
         self.add_widget_intelligent(
             npyscreen.TitleFixedText,
@@ -562,10 +523,6 @@ https://huggingface.co/spaces/CompVis/stable-diffusion-license
             bad_fields.append(
                 f"The output directory does not seem to be valid. Please check that {str(Path(opt.outdir).parent)} is an existing directory."
             )
-        if not Path(opt.embedding_dir).parent.exists():
-            bad_fields.append(
-                f"The embedding directory does not seem to be valid. Please check that {str(Path(opt.embedding_dir).parent)} is an existing directory."
-            )
         if len(bad_fields) > 0:
             message = "The following problems were detected and must be corrected:\n"
             for problem in bad_fields:
@@ -585,12 +542,15 @@ https://huggingface.co/spaces/CompVis/stable-diffusion-license
                 "max_loaded_models",
                 "xformers_enabled",
                 "always_use_cpu",
-                "embedding_dir",
-                "lora_dir",
-                "controlnet_dir",
         ]:
             setattr(new_opts, attr, getattr(self, attr).value)
 
+        for attr in self.autoimport_dirs:
+            directory = Path(self.autoimport_dirs[attr].value)
+            if directory.is_relative_to(config.root_path):
+                directory = directory.relative_to(config.root_path)
+            setattr(new_opts, attr, directory)
+
         new_opts.hf_token = self.hf_token.value
         new_opts.license_acceptance = self.license_acceptance.value
         new_opts.precision = PRECISION_CHOICES[self.precision.value[0]]
@@ -607,7 +567,8 @@ class EditOptApplication(npyscreen.NPSAppManaged):
         self.program_opts = program_opts
         self.invokeai_opts = invokeai_opts
         self.user_cancelled = False
-        self.user_selections = default_user_selections(program_opts)
+        self.autoload_pending = True
+        self.install_selections = default_user_selections(program_opts)
 
     def onStart(self):
         npyscreen.setTheme(npyscreen.Themes.DefaultTheme)
@@ -642,41 +603,62 @@ def default_startup_options(init_file: Path) -> Namespace:
         opts.nsfw_checker = True
     return opts
 
-def default_user_selections(program_opts: Namespace) -> UserSelections:
-    return UserSelections(
-        install_models=default_dataset()
+def default_user_selections(program_opts: Namespace) -> InstallSelections:
+    installer = ModelInstall(config)
+    models = installer.all_models()
+    return InstallSelections(
+        install_models=[models[installer.default_model()].path or models[installer.default_model()].repo_id]
         if program_opts.default_only
-        else recommended_datasets()
+        else [models[x].path or models[x].repo_id for x in installer.recommended_models()]
         if program_opts.yes_to_all
-        else dict(),
-        purge_deleted_models=False,
-        scan_directory=None,
-        autoscan_on_startup=None,
+        else list(),
+#        scan_directory=None,
+#        autoscan_on_startup=None,
     )
 
-
+# -------------------------------------
+def autoimport_paths(config: InvokeAIAppConfig):
+    return [
+        ('Checkpoints & diffusers models', 'autoimport_dir', config.root_path / config.autoimport_dir),
+        ('LoRA/LyCORIS models',            'lora_dir',       config.root_path / config.lora_dir),
+        ('Controlnet models',              'controlnet_dir', config.root_path / config.controlnet_dir),
+        ('Textual Inversion Embeddings',   'embedding_dir',  config.root_path / config.embedding_dir),
+    ]
+    
 # -------------------------------------
 def initialize_rootdir(root: Path, yes_to_all: bool = False):
-    print("** INITIALIZING INVOKEAI RUNTIME DIRECTORY **")
-
+    logger.info("** INITIALIZING INVOKEAI RUNTIME DIRECTORY **")
     for name in (
             "models",
-            "configs",
-            "embeddings",
             "databases",
-            "loras",
-            "controlnets",
             "text-inversion-output",
             "text-inversion-training-data",
+            "configs"
     ):
         os.makedirs(os.path.join(root, name), exist_ok=True)
+    for model_type in ModelType:
+        Path(root, 'autoimport', model_type.value).mkdir(parents=True, exist_ok=True)
 
     configs_src = Path(configs.__path__[0])
     configs_dest = root / "configs"
     if not os.path.samefile(configs_src, configs_dest):
         shutil.copytree(configs_src, configs_dest, dirs_exist_ok=True)
 
+    dest = root / 'models'
+    for model_base in BaseModelType:
+        for model_type in ModelType:
+            path = dest / model_base.value / model_type.value
+            path.mkdir(parents=True, exist_ok=True)
+    path = dest / 'core'
+    path.mkdir(parents=True, exist_ok=True)
 
+    with open(root / 'configs' / 'models.yaml','w') as yaml_file:
+        yaml_file.write(yaml.dump({'__metadata__':
+                                   {'version':'3.0.0'}
+                                   }
+                                  )
+                        )
+        
 # -------------------------------------
 def run_console_ui(
     program_opts: Namespace, initfile: Path = None
@@ -699,7 +681,7 @@ def run_console_ui(
     if editApp.user_cancelled:
         return (None, None)
     else:
-        return (editApp.new_opts, editApp.user_selections)
+        return (editApp.new_opts, editApp.install_selections)
 
 
 # -------------------------------------
@@ -722,18 +704,6 @@ def write_opts(opts: Namespace, init_file: Path):
 def default_output_dir() -> Path:
     return config.root_path / "outputs"
 
-# -------------------------------------
-def default_embedding_dir() -> Path:
-    return config.root_path / "embeddings"
-
-# -------------------------------------
-def default_lora_dir() -> Path:
-    return config.root_path / "loras"
-
-# -------------------------------------
-def default_controlnet_dir() -> Path:
-    return config.root_path / "controlnets"
-
 # -------------------------------------
 def write_default_options(program_opts: Namespace, initfile: Path):
     opt = default_startup_options(initfile)
@@ -758,14 +728,42 @@ def migrate_init_file(legacy_format:Path):
     new.nsfw_checker = old.safety_checker
     new.xformers_enabled = old.xformers
     new.conf_path = old.conf
-    new.embedding_dir = old.embedding_path
+    new.root = legacy_format.parent.resolve()
 
     invokeai_yaml = legacy_format.parent / 'invokeai.yaml'
     with open(invokeai_yaml,"w", encoding="utf-8") as outfile:
         outfile.write(new.to_yaml())
 
-    legacy_format.replace(legacy_format.parent / 'invokeai.init.old')
+    legacy_format.replace(legacy_format.parent / 'invokeai.init.orig')
 
+# -------------------------------------
+def migrate_models(root: Path):
+    from invokeai.backend.install.migrate_to_3 import do_migrate
+    do_migrate(root, root)
+
+def migrate_if_needed(opt: Namespace, root: Path)->bool:
+    # We check for to see if the runtime directory is correctly initialized.
+    old_init_file = root / 'invokeai.init'
+    new_init_file = root / 'invokeai.yaml'
+    old_hub = root / 'models/hub'
+    migration_needed =  old_init_file.exists() and not new_init_file.exists() or old_hub.exists()
+    
+    if migration_needed:
+        if opt.yes_to_all or \
+            yes_or_no(f'{str(config.root_path)} appears to be a 2.3 format root directory. Convert to version 3.0?'):
+
+            logger.info('** Migrating invokeai.init to invokeai.yaml')
+            migrate_init_file(old_init_file)
+            config.parse_args(argv=[],conf=OmegaConf.load(new_init_file))
+
+            if old_hub.exists():
+                migrate_models(config.root_path)
+        else:
+            print('Cannot continue without conversion. Aborting.')
+    
+    return migration_needed
+
+    
 # -------------------------------------
 def main():
     parser = argparse.ArgumentParser(description="InvokeAI model downloader")
@@ -831,20 +829,16 @@ def main():
     errors = set()
 
     try:
-        models_to_download = default_user_selections(opt)
-
-        # We check for to see if the runtime directory is correctly initialized.
-        old_init_file = config.root_path / 'invokeai.init'
-        new_init_file = config.root_path / 'invokeai.yaml'
-        if old_init_file.exists() and not new_init_file.exists():
-            print('** Migrating invokeai.init to invokeai.yaml')
-            migrate_init_file(old_init_file)
-            # Load new init file into config
-            config.parse_args(argv=[],conf=OmegaConf.load(new_init_file))
+        # if we do a root migration/upgrade, then we are keeping previous
+        # configuration and we are done.
+        if migrate_if_needed(opt, config.root_path):
+            sys.exit(0)
 
         if not config.model_conf_path.exists():
             initialize_rootdir(config.root_path, opt.yes_to_all)
 
+        models_to_download = default_user_selections(opt)
+        new_init_file = config.root_path / 'invokeai.yaml'
         if opt.yes_to_all:
             write_default_options(opt, new_init_file)
             init_options = Namespace(
@@ -855,29 +849,21 @@ def main():
             if init_options:
                 write_opts(init_options, new_init_file)
             else:
-                print(
+                logger.info(
                     '\n** CANCELLED AT USER\'S REQUEST. USE THE "invoke.sh" LAUNCHER TO RUN LATER **\n'
                 )
                 sys.exit(0)
-
+                
         if opt.skip_support_models:
-            print("\n** SKIPPING SUPPORT MODEL DOWNLOADS PER USER REQUEST **")
+            logger.info("SKIPPING SUPPORT MODEL DOWNLOADS PER USER REQUEST")
         else:
-            print("\n** CHECKING/UPDATING SUPPORT MODELS **")
-            download_bert()
-            download_sd1_clip()
-            download_sd2_clip()
-            download_realesrgan()
-            download_gfpgan()
-            download_codeformer()
-            download_clipseg()
-            download_safety_checker()
-            download_vaes()
+            logger.info("CHECKING/UPDATING SUPPORT MODELS")
+            download_support_models()
 
         if opt.skip_sd_weights:
-            print("\n** SKIPPING DIFFUSION WEIGHTS DOWNLOAD PER USER REQUEST **")
+            logger.info("\n** SKIPPING DIFFUSION WEIGHTS DOWNLOAD PER USER REQUEST **")
         elif models_to_download:
-            print("\n** DOWNLOADING DIFFUSION WEIGHTS **")
+            logger.info("\n** DOWNLOADING DIFFUSION WEIGHTS **")
             process_and_execute(opt, models_to_download)
 
         postscript(errors=errors)

invokeai/backend/install/legacy_arg_parsing.py

@@ -4,6 +4,8 @@ import argparse
 import shlex
 from argparse import ArgumentParser
 
+# note that this includes both old sampler names and new scheduler names
+# in order to be able to parse both 2.0 and 3.0-pre-nodes versions of invokeai.init
 SAMPLER_CHOICES = [
     "ddim",
     "ddpm",
@@ -27,6 +29,15 @@ SAMPLER_CHOICES = [
     "dpmpp_sde",
     "dpmpp_sde_k",
     "unipc",
+    "k_dpm_2_a",
+    "k_dpm_2",
+    "k_dpmpp_2_a",
+    "k_dpmpp_2",
+    "k_euler_a",
+    "k_euler",
+    "k_heun",
+    "k_lms",
+    "plms",
 ]
 
 PRECISION_CHOICES = [

invokeai/backend/install/migrate_to_3.py

@@ -0,0 +1,585 @@
+'''
+Migrate the models directory and models.yaml file from an existing
+InvokeAI 2.3 installation to 3.0.0.
+'''
+
+import io
+import os
+import argparse
+import shutil
+import yaml
+
+import transformers
+import diffusers
+import warnings
+
+from dataclasses import dataclass
+from pathlib import Path
+from omegaconf import OmegaConf, DictConfig
+from typing import Union
+
+from diffusers import StableDiffusionPipeline, AutoencoderKL
+from diffusers.pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker
+from transformers import (
+    CLIPTextModel,
+    CLIPTokenizer,
+    AutoFeatureExtractor,
+    BertTokenizerFast,
+)
+
+import invokeai.backend.util.logging as logger
+from invokeai.backend.model_management import ModelManager
+from invokeai.backend.model_management.model_probe import (
+    ModelProbe, ModelType, BaseModelType, SchedulerPredictionType, ModelProbeInfo
+    )
+
+warnings.filterwarnings("ignore")
+transformers.logging.set_verbosity_error()
+diffusers.logging.set_verbosity_error()
+
+# holder for paths that we will migrate
+@dataclass
+class ModelPaths:
+    models: Path
+    embeddings: Path
+    loras: Path
+    controlnets: Path
+
+class MigrateTo3(object):
+    def __init__(self,
+                 root_directory: Path,
+                 dest_models: Path,
+                 yaml_file: io.TextIOBase,
+                 src_paths: ModelPaths,
+                 ):
+        self.root_directory = root_directory
+        self.dest_models = dest_models
+        self.dest_yaml = yaml_file
+        self.model_names = set()
+        self.src_paths = src_paths
+        
+        self._initialize_yaml()
+
+    def _initialize_yaml(self):
+        self.dest_yaml.write(
+            yaml.dump(
+                {
+                    '__metadata__':
+                    {
+                        'version':'3.0.0'}
+                }
+            )
+        )
+    
+    def unique_name(self,name,info)->str:
+        '''
+        Create a unique name for a model for use within models.yaml.
+        '''
+        done = False
+        
+        # some model names have slashes in them, which really screws things up
+        name = name.replace('/','_')
+        
+        key = ModelManager.create_key(name,info.base_type,info.model_type)
+        unique_name = key
+        counter = 1
+        while not done:
+            if unique_name in self.model_names:
+                unique_name = f'{key}-{counter:0>2d}'
+                counter += 1
+            else:
+                done = True
+        self.model_names.add(unique_name)
+        name,_,_ = ModelManager.parse_key(unique_name)
+        return name
+
+    def create_directory_structure(self):
+        '''
+        Create the basic directory structure for the models folder.
+        '''
+        for model_base in [BaseModelType.StableDiffusion1,BaseModelType.StableDiffusion2]:
+            for model_type in [ModelType.Main, ModelType.Vae, ModelType.Lora,
+                               ModelType.ControlNet,ModelType.TextualInversion]:
+                path = self.dest_models / model_base.value / model_type.value
+                path.mkdir(parents=True, exist_ok=True)
+        path = self.dest_models / 'core'
+        path.mkdir(parents=True, exist_ok=True)
+
+    @staticmethod
+    def copy_file(src:Path,dest:Path):
+        '''
+        copy a single file with logging
+        '''
+        if dest.exists():
+            logger.info(f'Skipping existing {str(dest)}')
+            return
+        logger.info(f'Copying {str(src)} to {str(dest)}')
+        try:
+            shutil.copy(src, dest)
+        except Exception as e:
+            logger.error(f'COPY FAILED: {str(e)}')
+
+    @staticmethod
+    def copy_dir(src:Path,dest:Path):
+        '''
+        Recursively copy a directory with logging
+        '''
+        if dest.exists():
+            logger.info(f'Skipping existing {str(dest)}')
+            return
+        
+        logger.info(f'Copying {str(src)} to {str(dest)}')
+        try:
+            shutil.copytree(src, dest)
+        except Exception as e:
+            logger.error(f'COPY FAILED: {str(e)}')
+
+    def migrate_models(self, src_dir: Path):
+        '''
+        Recursively walk through src directory, probe anything
+        that looks like a model, and copy the model into the
+        appropriate location within the destination models directory.
+        '''
+        for root, dirs, files in os.walk(src_dir):
+            for f in files:
+                # hack - don't copy raw learned_embeds.bin, let them
+                # be copied as part of a tree copy operation
+                if f == 'learned_embeds.bin':
+                    continue
+                try:
+                    model = Path(root,f)
+                    info = ModelProbe().heuristic_probe(model)
+                    if not info:
+                        continue
+                    dest = self._model_probe_to_path(info) / f
+                    self.copy_file(model, dest)
+                except KeyboardInterrupt:
+                    raise
+                except Exception as e:
+                    logger.error(str(e))
+            for d in dirs:
+                try:
+                    model = Path(root,d)
+                    info = ModelProbe().heuristic_probe(model)
+                    if not info:
+                        continue
+                    dest = self._model_probe_to_path(info) / model.name
+                    self.copy_dir(model, dest)
+                except KeyboardInterrupt:
+                    raise
+                except Exception as e:
+                    logger.error(str(e))
+
+    def migrate_support_models(self):
+        '''
+        Copy the clipseg, upscaler, and restoration models to their new
+        locations.
+        '''
+        dest_directory = self.dest_models
+        if (self.root_directory / 'models/clipseg').exists():
+            self.copy_dir(self.root_directory / 'models/clipseg', dest_directory / 'core/misc/clipseg')
+        if (self.root_directory / 'models/realesrgan').exists():
+            self.copy_dir(self.root_directory / 'models/realesrgan', dest_directory / 'core/upscaling/realesrgan')
+        for d in ['codeformer','gfpgan']:
+            path = self.root_directory / 'models' / d
+            if path.exists():
+                self.copy_dir(path,dest_directory / f'core/face_restoration/{d}')
+
+    def migrate_tuning_models(self):
+        '''
+        Migrate the embeddings, loras and controlnets directories to their new homes.
+        '''
+        for src in [self.src_paths.embeddings, self.src_paths.loras, self.src_paths.controlnets]:
+            if not src:
+                continue
+            if src.is_dir():
+                logger.info(f'Scanning {src}')
+                self.migrate_models(src)
+            else:
+                logger.info(f'{src} directory not found; skipping')
+                continue
+
+    def migrate_conversion_models(self):
+        '''
+        Migrate all the models that are needed by the ckpt_to_diffusers conversion
+        script.
+        '''
+
+        dest_directory = self.dest_models
+        kwargs = dict(
+            cache_dir = self.root_directory / 'models/hub',
+            #local_files_only = True
+        )
+        try:
+            logger.info('Migrating core tokenizers and text encoders')
+            target_dir = dest_directory / 'core' / 'convert'
+
+            self._migrate_pretrained(BertTokenizerFast,
+                                     repo_id='bert-base-uncased',
+                                     dest = target_dir / 'bert-base-uncased',
+                                     **kwargs)
+
+            # sd-1
+            repo_id = 'openai/clip-vit-large-patch14'
+            self._migrate_pretrained(CLIPTokenizer,
+                                     repo_id= repo_id,
+                                     dest= target_dir / 'clip-vit-large-patch14' / 'tokenizer',
+                                     **kwargs)
+            self._migrate_pretrained(CLIPTextModel,
+                                     repo_id = repo_id,
+                                     dest = target_dir / 'clip-vit-large-patch14' / 'text_encoder',
+                                     **kwargs)
+
+            # sd-2
+            repo_id = "stabilityai/stable-diffusion-2"
+            self._migrate_pretrained(CLIPTokenizer,
+                                     repo_id = repo_id,
+                                     dest = target_dir / 'stable-diffusion-2-clip' / 'tokenizer',
+                                     **{'subfolder':'tokenizer',**kwargs}
+                                     )
+            self._migrate_pretrained(CLIPTextModel,
+                                     repo_id = repo_id,
+                                     dest = target_dir / 'stable-diffusion-2-clip' / 'text_encoder',
+                                     **{'subfolder':'text_encoder',**kwargs}
+                                     )
+
+            # VAE
+            logger.info('Migrating stable diffusion VAE')
+            self._migrate_pretrained(AutoencoderKL,
+                                     repo_id = 'stabilityai/sd-vae-ft-mse',
+                                     dest = target_dir / 'sd-vae-ft-mse',
+                                     **kwargs)
+            
+            # safety checking
+            logger.info('Migrating safety checker')
+            repo_id = "CompVis/stable-diffusion-safety-checker"
+            self._migrate_pretrained(AutoFeatureExtractor,
+                                     repo_id = repo_id,
+                                     dest = target_dir / 'stable-diffusion-safety-checker',
+                                     **kwargs)
+            self._migrate_pretrained(StableDiffusionSafetyChecker,
+                                     repo_id = repo_id,
+                                     dest = target_dir / 'stable-diffusion-safety-checker',
+                                     **kwargs)
+        except KeyboardInterrupt:
+            raise
+        except Exception as e:
+            logger.error(str(e))
+
+    def write_yaml(self, model_name: str, path:Path, info:ModelProbeInfo, **kwargs):
+        '''
+        Write a stanza for a moved model into the new models.yaml file.
+        '''
+        name = self.unique_name(model_name, info)
+        stanza = {
+            f'{info.base_type.value}/{info.model_type.value}/{name}': {
+                'name': model_name,
+                'path': str(path),
+                'description': f'A {info.base_type.value} {info.model_type.value} model',
+                'format': info.format,
+                'image_size': info.image_size,
+                'base': info.base_type.value,
+                'variant': info.variant_type.value,
+                'prediction_type': info.prediction_type.value,
+                'upcast_attention': info.prediction_type == SchedulerPredictionType.VPrediction,
+                **kwargs,
+            }
+        }
+        self.dest_yaml.write(yaml.dump(stanza))
+        self.dest_yaml.flush()
+        
+    def _model_probe_to_path(self, info: ModelProbeInfo)->Path:
+        return Path(self.dest_models, info.base_type.value, info.model_type.value)
+
+    def _migrate_pretrained(self, model_class, repo_id: str, dest: Path, **kwargs):
+        if dest.exists():
+            logger.info(f'Skipping existing {dest}')
+            return
+        model = model_class.from_pretrained(repo_id, **kwargs)
+        self._save_pretrained(model, dest)
+
+    def _save_pretrained(self, model, dest: Path):
+        if dest.exists():
+            logger.info(f'Skipping existing {dest}')
+            return
+        model_name = dest.name
+        download_path = dest.with_name(f'{model_name}.downloading')
+        model.save_pretrained(download_path, safe_serialization=True)
+        download_path.replace(dest)
+
+    def _download_vae(self, repo_id: str, subfolder:str=None)->Path:
+        vae = AutoencoderKL.from_pretrained(repo_id, cache_dir=self.root_directory / 'models/hub', subfolder=subfolder)
+        info = ModelProbe().heuristic_probe(vae)
+        _, model_name = repo_id.split('/')
+        dest = self._model_probe_to_path(info) / self.unique_name(model_name, info)
+        vae.save_pretrained(dest, safe_serialization=True)
+        return dest
+
+    def _vae_path(self, vae: Union[str,dict])->Path:
+        '''
+        Convert 2.3 VAE stanza to a straight path.
+        '''
+        vae_path = None
+        
+        # First get a path
+        if isinstance(vae,str):
+            vae_path = vae
+
+        elif isinstance(vae,DictConfig):
+            if p := vae.get('path'):
+                vae_path = p
+            elif repo_id := vae.get('repo_id'):
+                if repo_id=='stabilityai/sd-vae-ft-mse':  # this guy is already downloaded
+                    vae_path = 'models/core/convert/sd-vae-ft-mse'
+                else:
+                    vae_path = self._download_vae(repo_id, vae.get('subfolder'))
+
+        assert vae_path is not None, "Couldn't find VAE for this model"
+
+        # if the VAE is in the old models directory, then we must move it into the new
+        # one. VAEs outside of this directory can stay where they are.
+        vae_path = Path(vae_path)
+        if vae_path.is_relative_to(self.src_paths.models):
+            info = ModelProbe().heuristic_probe(vae_path)
+            dest = self._model_probe_to_path(info) / vae_path.name
+            if not dest.exists():
+                self.copy_dir(vae_path,dest)
+            vae_path = dest
+
+        if vae_path.is_relative_to(self.dest_models):
+            rel_path = vae_path.relative_to(self.dest_models)
+            return Path('models',rel_path)
+        else:
+            return vae_path
+
+    def migrate_repo_id(self, repo_id: str, model_name :str=None, **extra_config):
+        '''
+        Migrate a locally-cached diffusers pipeline identified with a repo_id
+        '''
+        dest_dir = self.dest_models
+        
+        cache = self.root_directory / 'models/hub'
+        kwargs = dict(
+            cache_dir = cache,
+            safety_checker = None,
+            # local_files_only = True,
+        )
+
+        owner,repo_name = repo_id.split('/')
+        model_name = model_name or repo_name
+        model = cache / '--'.join(['models',owner,repo_name])
+        
+        if len(list(model.glob('snapshots/**/model_index.json')))==0:
+            return
+        revisions = [x.name for x in model.glob('refs/*')]
+
+        # if an fp16 is available we use that
+        revision = 'fp16' if len(revisions) > 1 and 'fp16' in revisions else revisions[0]
+        pipeline = StableDiffusionPipeline.from_pretrained(
+            repo_id,
+            revision=revision,
+            **kwargs)
+
+        info = ModelProbe().heuristic_probe(pipeline)
+        if not info:
+            return
+
+        dest = self._model_probe_to_path(info) / repo_name
+        self._save_pretrained(pipeline, dest)
+            
+        rel_path = Path('models',dest.relative_to(dest_dir))
+        self.write_yaml(model_name, path=rel_path, info=info, **extra_config)
+
+    def migrate_path(self, location: Path, model_name: str=None, **extra_config):
+        '''
+        Migrate a model referred to using 'weights' or 'path'
+        '''
+
+        # handle relative paths
+        dest_dir = self.dest_models
+        location = self.root_directory / location
+        
+        info = ModelProbe().heuristic_probe(location)
+        if not info:
+            return
+
+        # uh oh, weights is in the old models directory - move it into the new one
+        if Path(location).is_relative_to(self.src_paths.models):
+            dest = Path(dest_dir, info.base_type.value, info.model_type.value, location.name)
+            self.copy_dir(location,dest)
+            location = Path('models', info.base_type.value, info.model_type.value, location.name)
+        model_name = model_name or location.stem
+        model_name = self.unique_name(model_name, info)
+        self.write_yaml(model_name, path=location, info=info, **extra_config)
+
+    def migrate_defined_models(self):
+        '''
+        Migrate models defined in models.yaml
+        '''
+        # find any models referred to in old models.yaml
+        conf = OmegaConf.load(self.root_directory / 'configs/models.yaml')
+        
+        for model_name, stanza in conf.items():
+
+            try:
+                passthru_args = {}
+                
+                if vae := stanza.get('vae'):
+                    try:
+                        passthru_args['vae'] = str(self._vae_path(vae))
+                    except Exception as e:
+                        logger.warning(f'Could not find a VAE matching "{vae}" for model "{model_name}"')
+                        logger.warning(str(e))
+
+                if config := stanza.get('config'):
+                    passthru_args['config'] = config
+                
+                if repo_id := stanza.get('repo_id'):
+                    logger.info(f'Migrating diffusers model {model_name}')
+                    self.migrate_repo_id(repo_id, model_name, **passthru_args)
+
+                elif location := stanza.get('weights'):
+                    logger.info(f'Migrating checkpoint model {model_name}')
+                    self.migrate_path(Path(location), model_name, **passthru_args)
+                    
+                elif location := stanza.get('path'):
+                    logger.info(f'Migrating diffusers model {model_name}')
+                    self.migrate_path(Path(location), model_name, **passthru_args)
+                    
+            except KeyboardInterrupt:
+                raise
+            except Exception as e:
+                logger.error(str(e))
+                    
+    def migrate(self):
+        self.create_directory_structure()
+        # the configure script is doing this
+        self.migrate_support_models()
+        self.migrate_conversion_models()
+        self.migrate_tuning_models()
+        self.migrate_defined_models()
+
+def _parse_legacy_initfile(root: Path, initfile: Path)->ModelPaths:
+    '''
+    Returns tuple of (embedding_path, lora_path, controlnet_path)
+    '''
+    parser = argparse.ArgumentParser(fromfile_prefix_chars='@')
+    parser.add_argument(
+        '--embedding_directory',
+        '--embedding_path',
+        type=Path,
+        dest='embedding_path',
+        default=Path('embeddings'),
+    )
+    parser.add_argument(
+        '--lora_directory',
+        dest='lora_path',
+        type=Path,
+        default=Path('loras'),
+    )
+    opt,_ = parser.parse_known_args([f'@{str(initfile)}'])
+    return ModelPaths(
+        models = root / 'models',
+        embeddings = root / str(opt.embedding_path).strip('"'),
+        loras = root / str(opt.lora_path).strip('"'),
+        controlnets = root / 'controlnets',
+    )
+
+def _parse_legacy_yamlfile(root: Path, initfile: Path)->ModelPaths:
+    '''
+    Returns tuple of (embedding_path, lora_path, controlnet_path)
+    '''
+    # Don't use the config object because it is unforgiving of version updates
+    # Just use omegaconf directly
+    opt = OmegaConf.load(initfile)
+    paths = opt.InvokeAI.Paths
+    models = paths.get('models_dir','models')
+    embeddings = paths.get('embedding_dir','embeddings')
+    loras = paths.get('lora_dir','loras')
+    controlnets = paths.get('controlnet_dir','controlnets')
+    return ModelPaths(
+        models = root / models,
+        embeddings = root / embeddings,
+        loras = root /loras,
+        controlnets = root / controlnets,
+    )
+    
+def get_legacy_embeddings(root: Path) -> ModelPaths:
+    path = root / 'invokeai.init'
+    if path.exists():
+        return _parse_legacy_initfile(root, path)
+    path = root / 'invokeai.yaml'
+    if path.exists():
+        return _parse_legacy_yamlfile(root, path)
+
+def do_migrate(src_directory: Path, dest_directory: Path):
+    
+    dest_models = dest_directory / 'models-3.0'
+    dest_yaml = dest_directory / 'configs/models.yaml-3.0'
+
+    paths = get_legacy_embeddings(src_directory)
+
+    with open(dest_yaml,'w') as yaml_file:
+        migrator = MigrateTo3(src_directory,
+                              dest_models,
+                              yaml_file,
+                              src_paths = paths,
+                              )
+        migrator.migrate()
+
+    shutil.rmtree(dest_directory / 'models.orig', ignore_errors=True)
+    (dest_directory / 'models').replace(dest_directory / 'models.orig')
+    dest_models.replace(dest_directory / 'models')
+
+    (dest_directory /'configs/models.yaml').replace(dest_directory / 'configs/models.yaml.orig')
+    dest_yaml.replace(dest_directory / 'configs/models.yaml')
+    print(f"""Migration successful.
+Original models directory moved to {dest_directory}/models.orig
+Original models.yaml file moved to {dest_directory}/configs/models.yaml.orig
+""")
+
+def main():
+    parser = argparse.ArgumentParser(prog="invokeai-migrate3",
+                                     description="""
+This will copy and convert the models directory and the configs/models.yaml from the InvokeAI 2.3 format 
+'--from-directory' root to the InvokeAI 3.0 '--to-directory' root. These may be abbreviated '--from' and '--to'.a
+
+The old models directory and config file will be renamed 'models.orig' and 'models.yaml.orig' respectively.
+It is safe to provide the same directory for both arguments, but it is better to use the invokeai_configure
+script, which will perform a full upgrade in place."""
+                                     )
+    parser.add_argument('--from-directory',
+                        dest='root_directory',
+                        type=Path,
+                        required=True,
+                        help='Source InvokeAI 2.3 root directory (containing "invokeai.init" or "invokeai.yaml")'
+                        )
+    parser.add_argument('--to-directory',
+                        dest='dest_directory',
+                        type=Path,
+                        required=True,
+                        help='Destination InvokeAI 3.0 directory (containing "invokeai.yaml")'
+                        )
+# TO DO: Implement full directory scanning
+#    parser.add_argument('--all-models',
+#                        action="store_true",
+#                        help='Migrate all models found in `models` directory, not just those mentioned in models.yaml',
+#                        )
+    args = parser.parse_args()
+    root_directory = args.root_directory
+    assert root_directory.is_dir(), f"{root_directory} is not a valid directory"
+    assert (root_directory / 'models').is_dir(), f"{root_directory} does not contain a 'models' subdirectory"
+    assert (root_directory / 'invokeai.init').exists() or (root_directory / 'invokeai.yaml').exists(), f"{root_directory} does not contain an InvokeAI init file."
+
+    dest_directory = args.dest_directory
+    assert dest_directory.is_dir(), f"{dest_directory} is not a valid directory"
+    assert (dest_directory / 'models').is_dir(), f"{dest_directory} does not contain a 'models' subdirectory"
+    assert (dest_directory / 'invokeai.yaml').exists(), f"{dest_directory} does not contain an InvokeAI init file."
+
+    do_migrate(root_directory,dest_directory)
+
+if __name__ == '__main__':
+    main()
+
+
+

invokeai/backend/install/model_install_backend.py

@@ -2,46 +2,37 @@
 Utility (backend) functions used by model_install.py
 """
 import os
-import re
 import shutil
-import sys
 import warnings
 from dataclasses import dataclass,field
 from pathlib import Path
-from tempfile import TemporaryFile
-from typing import List, Dict, Callable
+from tempfile import TemporaryDirectory
+from typing import List, Dict, Callable, Union, Set
 
 import requests
-from diffusers import AutoencoderKL
-from huggingface_hub import hf_hub_url, HfFolder
+from diffusers import StableDiffusionPipeline
+from diffusers import logging as dlogging
+from huggingface_hub import hf_hub_url, HfFolder, HfApi
 from omegaconf import OmegaConf
-from omegaconf.dictconfig import DictConfig
 from tqdm import tqdm
 
 import invokeai.configs as configs
 
-
 from invokeai.app.services.config import InvokeAIAppConfig
-from ..stable_diffusion import StableDiffusionGeneratorPipeline
+from invokeai.backend.model_management import ModelManager, ModelType, BaseModelType, ModelVariantType
+from invokeai.backend.model_management.model_probe import ModelProbe, SchedulerPredictionType, ModelProbeInfo
+from invokeai.backend.util import download_with_resume
 from ..util.logging import InvokeAILogger
 
 warnings.filterwarnings("ignore")
 
 # --------------------------globals-----------------------
 config = InvokeAIAppConfig.get_config()
-
-Model_dir = "models"
-Weights_dir = "ldm/stable-diffusion-v1/"
+logger = InvokeAILogger.getLogger(name='InvokeAI')
 
 # the initial "configs" dir is now bundled in the `invokeai.configs` package
 Dataset_path = Path(configs.__path__[0]) / "INITIAL_MODELS.yaml"
 
-# initial models omegaconf
-Datasets = None
-
-# logger
-logger = InvokeAILogger.getLogger(name='InvokeAI')
-
 Config_preamble = """
 # This file describes the alternative machine learning models
 # available to InvokeAI script.
@@ -52,6 +43,24 @@ Config_preamble = """
 # was trained on.
 """
 
+LEGACY_CONFIGS = {
+    BaseModelType.StableDiffusion1: {
+        ModelVariantType.Normal: 'v1-inference.yaml',
+        ModelVariantType.Inpaint: 'v1-inpainting-inference.yaml',
+    },
+
+    BaseModelType.StableDiffusion2: {
+        ModelVariantType.Normal: {
+            SchedulerPredictionType.Epsilon: 'v2-inference.yaml',
+            SchedulerPredictionType.VPrediction: 'v2-inference-v.yaml',
+        },
+        ModelVariantType.Inpaint: {
+            SchedulerPredictionType.Epsilon: 'v2-inpainting-inference.yaml',
+            SchedulerPredictionType.VPrediction: 'v2-inpainting-inference-v.yaml',
+        }
+    }
+}
+
 @dataclass
 class ModelInstallList:
     '''Class for listing models to be installed/removed'''
@@ -59,133 +68,328 @@ class ModelInstallList:
     remove_models: List[str] = field(default_factory=list)
 
 @dataclass
-class UserSelections():
+class InstallSelections():
     install_models: List[str]= field(default_factory=list)
     remove_models: List[str]=field(default_factory=list)
-    purge_deleted_models: bool=field(default_factory=list)
-    install_cn_models: List[str] = field(default_factory=list)
-    remove_cn_models: List[str] = field(default_factory=list)
-    install_lora_models: List[str] = field(default_factory=list)
-    remove_lora_models: List[str] = field(default_factory=list)
-    install_ti_models: List[str] = field(default_factory=list)
-    remove_ti_models: List[str] = field(default_factory=list)
-    scan_directory: Path = None
-    autoscan_on_startup: bool=False
-    import_model_paths: str=None
+#    scan_directory: Path = None
+#    autoscan_on_startup: bool=False
+
+@dataclass
+class ModelLoadInfo():
+    name: str
+    model_type: ModelType
+    base_type: BaseModelType
+    path: Path = None
+    repo_id: str = None
+    description: str = ''
+    installed: bool = False
+    recommended: bool = False
+    default: bool = False
+
+class ModelInstall(object):
+    def __init__(self,
+                 config:InvokeAIAppConfig,
+                 prediction_type_helper: Callable[[Path],SchedulerPredictionType]=None,
+                 model_manager: ModelManager = None,
+                 access_token:str = None):
+        self.config = config
+        self.mgr = model_manager or ModelManager(config.model_conf_path)
+        self.datasets = OmegaConf.load(Dataset_path)
+        self.prediction_helper = prediction_type_helper
+        self.access_token = access_token or HfFolder.get_token()
+        self.reverse_paths = self._reverse_paths(self.datasets)
+
+    def all_models(self)->Dict[str,ModelLoadInfo]:
+        '''
+        Return dict of model_key=>ModelLoadInfo objects.
+        This method consolidates and simplifies the entries in both
+        models.yaml and INITIAL_MODELS.yaml so that they can
+        be treated uniformly. It also sorts the models alphabetically
+        by their name, to improve the display somewhat.
+        '''
+        model_dict = dict()
         
-def default_config_file():
-    return config.model_conf_path
+        # first populate with the entries in INITIAL_MODELS.yaml
+        for key, value in self.datasets.items():
+            name,base,model_type = ModelManager.parse_key(key)
+            value['name'] = name
+            value['base_type'] = base
+            value['model_type'] = model_type
+            model_dict[key] = ModelLoadInfo(**value)
 
-def sd_configs():
-    return config.legacy_conf_path
-
-def initial_models():
-    global Datasets
-    if Datasets:
-        return Datasets
-    return (Datasets := OmegaConf.load(Dataset_path)['diffusers'])
-
-def install_requested_models(
-        diffusers: ModelInstallList = None,
-        controlnet: ModelInstallList = None,
-        lora: ModelInstallList = None,
-        ti: ModelInstallList = None,
-        cn_model_map: Dict[str,str] = None, # temporary - move to model manager
-        scan_directory: Path = None,
-        external_models: List[str] = None,
-        scan_at_startup: bool = False,
-        precision: str = "float16",
-        purge_deleted: bool = False,
-        config_file_path: Path = None,
-        model_config_file_callback:  Callable[[Path],Path] = None
-):
-    """
-    Entry point for installing/deleting starter models, or installing external models.
-    """
-    access_token = HfFolder.get_token()
-    config_file_path = config_file_path or default_config_file()
-    if not config_file_path.exists():
-        open(config_file_path, "w")
-
-    # prevent circular import here
-    from ..model_management import ModelManager
-    model_manager = ModelManager(OmegaConf.load(config_file_path), precision=precision)
-    if controlnet:
-        model_manager.install_controlnet_models(controlnet.install_models, access_token=access_token)
-        model_manager.delete_controlnet_models(controlnet.remove_models)
-
-    if lora:
-        model_manager.install_lora_models(lora.install_models, access_token=access_token)
-        model_manager.delete_lora_models(lora.remove_models)
-
-    if ti:
-        model_manager.install_ti_models(ti.install_models, access_token=access_token)
-        model_manager.delete_ti_models(ti.remove_models)
-
-    if diffusers:
-        # TODO: Replace next three paragraphs with calls into new model manager
-        if diffusers.remove_models and len(diffusers.remove_models) > 0:
-            logger.info("Processing requested deletions")
-            for model in diffusers.remove_models:
-                logger.info(f"{model}...")
-                model_manager.del_model(model, delete_files=purge_deleted)
-            model_manager.commit(config_file_path)
-
-        if diffusers.install_models and len(diffusers.install_models) > 0:
-            logger.info("Installing requested models")
-            downloaded_paths = download_weight_datasets(
-                models=diffusers.install_models,
-                access_token=None,
-                precision=precision,
-            )
-            successful = {x:v for x,v in downloaded_paths.items() if v is not None}
-            if len(successful) > 0:
-                update_config_file(successful, config_file_path)
-            if len(successful) < len(diffusers.install_models):
-                unsuccessful = [x for x in downloaded_paths if downloaded_paths[x] is None]
-                logger.warning(f"Some of the model downloads were not successful: {unsuccessful}")
-
-    # due to above, we have to reload the model manager because conf file
-    # was changed behind its back
-    model_manager = ModelManager(OmegaConf.load(config_file_path), precision=precision)
-
-    external_models = external_models or list()
-    if scan_directory:
-        external_models.append(str(scan_directory))
-
-    if len(external_models) > 0:
-        logger.info("INSTALLING EXTERNAL MODELS")
-        for path_url_or_repo in external_models:
-            try:
-                logger.debug(f'In install_requested_models; callback = {model_config_file_callback}')
-                model_manager.heuristic_import(
-                    path_url_or_repo,
-                    commit_to_conf=config_file_path,
-                    config_file_callback = model_config_file_callback,
+        # supplement with entries in models.yaml
+        installed_models = self.mgr.list_models()
+        for md in installed_models:
+            base = md['base_model']
+            model_type = md['type']
+            name = md['name']
+            key = ModelManager.create_key(name, base, model_type)
+            if key in model_dict:
+                model_dict[key].installed = True
+            else:
+                model_dict[key] = ModelLoadInfo(
+                    name = name,
+                    base_type = base,
+                    model_type = model_type,
+                    path = value.get('path'),
+                    installed = True,
                 )
-            except KeyboardInterrupt:
-                sys.exit(-1)
-            except Exception:
+        return {x : model_dict[x] for x in sorted(model_dict.keys(),key=lambda y: model_dict[y].name.lower())}
+
+    def starter_models(self)->Set[str]:
+        models = set()
+        for key, value in self.datasets.items():
+            name,base,model_type = ModelManager.parse_key(key)
+            if model_type==ModelType.Main:
+                models.add(key)
+        return models
+
+    def recommended_models(self)->Set[str]:
+        starters = self.starter_models()
+        return set([x for x in starters if self.datasets[x].get('recommended',False)])
+    
+    def default_model(self)->str:
+        starters = self.starter_models()
+        defaults = [x for x in starters if self.datasets[x].get('default',False)]
+        return defaults[0]
+
+    def install(self, selections: InstallSelections):
+        verbosity = dlogging.get_verbosity()  # quench NSFW nags
+        dlogging.set_verbosity_error()
+
+        job = 1
+        jobs = len(selections.remove_models) + len(selections.install_models)
+        
+        # remove requested models
+        for key in selections.remove_models:
+            name,base,mtype = self.mgr.parse_key(key)
+            logger.info(f'Deleting {mtype} model {name} [{job}/{jobs}]')
+            try:
+                self.mgr.del_model(name,base,mtype)
+            except FileNotFoundError as e:
+                logger.warning(e)
+            job += 1
+            
+        # add requested models
+        for path in selections.install_models:
+            logger.info(f'Installing {path} [{job}/{jobs}]')
+            self.heuristic_install(path)
+            job += 1
+            
+        dlogging.set_verbosity(verbosity)
+        self.mgr.commit()
+
+    def heuristic_install(self,
+                          model_path_id_or_url: Union[str,Path],
+                          models_installed: Set[Path]=None)->Set[Path]:
+
+        if not models_installed:
+            models_installed = set()
+            
+        # A little hack to allow nested routines to retrieve info on the requested ID
+        self.current_id = model_path_id_or_url
+        path = Path(model_path_id_or_url)
+        
+        try:
+            # checkpoint file, or similar
+            if path.is_file():
+                models_installed.add(self._install_path(path))
+
+            # folders style or similar
+            elif path.is_dir() and any([(path/x).exists() for x in {'config.json','model_index.json','learned_embeds.bin'}]):
+                models_installed.add(self._install_path(path))
+
+            # recursive scan
+            elif path.is_dir():
+                for child in path.iterdir():
+                    self.heuristic_install(child, models_installed=models_installed)
+
+            # huggingface repo
+            elif len(str(model_path_id_or_url).split('/')) == 2:
+                models_installed.add(self._install_repo(str(model_path_id_or_url)))
+
+            # a URL
+            elif model_path_id_or_url.startswith(("http:", "https:", "ftp:")):
+                models_installed.add(self._install_url(model_path_id_or_url))
+
+            else:
+                logger.warning(f'{str(model_path_id_or_url)} is not recognized as a local path, repo ID or URL. Skipping')
+            
+        except ValueError as e:
+            logger.error(str(e))
+
+        return models_installed
+
+    # install a model from a local path. The optional info parameter is there to prevent
+    # the model from being probed twice in the event that it has already been probed.
+    def _install_path(self, path: Path, info: ModelProbeInfo=None)->Path:
+        try:
+            # logger.debug(f'Probing {path}')
+            info = info or ModelProbe().heuristic_probe(path,self.prediction_helper)
+            model_name = path.stem if info.format=='checkpoint' else path.name
+            if self.mgr.model_exists(model_name, info.base_type, info.model_type):
+                raise ValueError(f'A model named "{model_name}" is already installed.')
+            attributes = self._make_attributes(path,info)
+            self.mgr.add_model(model_name = model_name,
+                               base_model = info.base_type,
+                               model_type = info.model_type,
+                               model_attributes = attributes,
+                               )
+        except Exception as e:
+            logger.warning(f'{str(e)} Skipping registration.')
+        return path
+
+    def _install_url(self, url: str)->Path:
+        # copy to a staging area, probe, import and delete
+        with TemporaryDirectory(dir=self.config.models_path) as staging:
+            location = download_with_resume(url,Path(staging))
+            if not location:
+                logger.error(f'Unable to download {url}. Skipping.')
+            info = ModelProbe().heuristic_probe(location)
+            dest = self.config.models_path / info.base_type.value / info.model_type.value / location.name
+            models_path = shutil.move(location,dest)
+
+        # staged version will be garbage-collected at this time
+        return self._install_path(Path(models_path), info)
+
+    def _install_repo(self, repo_id: str)->Path:
+        hinfo = HfApi().model_info(repo_id)
+        
+        # we try to figure out how to download this most economically
+        # list all the files in the repo
+        files = [x.rfilename for x in hinfo.siblings]
+        location = None
+
+        with TemporaryDirectory(dir=self.config.models_path) as staging:
+            staging = Path(staging)
+            if 'model_index.json' in files:
+                location = self._download_hf_pipeline(repo_id, staging)   # pipeline
+            else:
+                for suffix in ['safetensors','bin']:
+                    if f'pytorch_lora_weights.{suffix}' in files:
+                        location = self._download_hf_model(repo_id, ['pytorch_lora_weights.bin'], staging)  # LoRA
+                        break
+                    elif self.config.precision=='float16' and f'diffusion_pytorch_model.fp16.{suffix}' in files: # vae, controlnet or some other standalone
+                        files = ['config.json', f'diffusion_pytorch_model.fp16.{suffix}']
+                        location = self._download_hf_model(repo_id, files, staging)
+                        break
+                    elif f'diffusion_pytorch_model.{suffix}' in files:
+                        files = ['config.json', f'diffusion_pytorch_model.{suffix}']
+                        location = self._download_hf_model(repo_id, files, staging)
+                        break
+                    elif f'learned_embeds.{suffix}' in files:
+                        location = self._download_hf_model(repo_id, ['learned_embeds.suffix'], staging)
+                        break
+            if not location:
+                logger.warning(f'Could not determine type of repo {repo_id}. Skipping install.')
+                return
+            
+            info = ModelProbe().heuristic_probe(location, self.prediction_helper)
+            if not info:
+                logger.warning(f'Could not probe {location}. Skipping install.')
+                return
+            dest = self.config.models_path / info.base_type.value / info.model_type.value / self._get_model_name(repo_id,location)
+            if dest.exists():
+                shutil.rmtree(dest)
+            shutil.copytree(location,dest)
+            return self._install_path(dest, info)
+
+    def _get_model_name(self,path_name: str, location: Path)->str:
+        '''
+        Calculate a name for the model - primitive implementation.
+        '''
+        if key := self.reverse_paths.get(path_name):
+            (name, base, mtype) = ModelManager.parse_key(key)
+            return name
+        else:
+            return location.stem
+
+    def _make_attributes(self, path: Path, info: ModelProbeInfo)->dict:
+        model_name = path.name if path.is_dir() else path.stem
+        description = f'{info.base_type.value} {info.model_type.value} model {model_name}'
+        if key := self.reverse_paths.get(self.current_id):
+            if key in self.datasets:
+                description = self.datasets[key].get('description') or description
+
+        rel_path = self.relative_to_root(path)
+
+        attributes = dict(
+            path = str(rel_path),
+            description = str(description),
+            model_format = info.format,
+            )
+        if info.model_type == ModelType.Main:
+            attributes.update(dict(variant = info.variant_type,))
+            if info.format=="checkpoint":
+                try:
+                    possible_conf = path.with_suffix('.yaml')
+                    if possible_conf.exists():
+                        legacy_conf = str(self.relative_to_root(possible_conf))
+                    elif info.base_type == BaseModelType.StableDiffusion2:
+                        legacy_conf = Path(self.config.legacy_conf_dir, LEGACY_CONFIGS[info.base_type][info.variant_type][info.prediction_type])
+                    else:
+                        legacy_conf = Path(self.config.legacy_conf_dir, LEGACY_CONFIGS[info.base_type][info.variant_type])
+                except KeyError:
+                    legacy_conf = Path(self.config.legacy_conf_dir, 'v1-inference.yaml')  # best guess
+                    
+                attributes.update(
+                    dict(
+                        config = str(legacy_conf)
+                    )
+                )
+        return attributes
+
+    def relative_to_root(self, path: Path)->Path:
+        root = self.config.root_path
+        if path.is_relative_to(root):
+            return path.relative_to(root)
+        else:
+            return path
+
+    def _download_hf_pipeline(self, repo_id: str, staging: Path)->Path:
+        '''
+        This retrieves a StableDiffusion model from cache or remote and then
+        does a save_pretrained() to the indicated staging area.
+        '''
+        _,name = repo_id.split("/")
+        revisions = ['fp16','main'] if self.config.precision=='float16' else ['main']
+        model = None
+        for revision in revisions:
+            try:
+                model = StableDiffusionPipeline.from_pretrained(repo_id,revision=revision,safety_checker=None)
+            except:  # most errors are due to fp16 not being present. Fix this to catch other errors
                 pass
+            if model:
+                break
+        if not model:
+            logger.error(f'Diffusers model {repo_id} could not be downloaded. Skipping.')
+            return None
+        model.save_pretrained(staging / name, safe_serialization=True)
+        return staging / name
 
-    if scan_at_startup and scan_directory.is_dir():
-        update_autoconvert_dir(scan_directory)
-    else:
-        update_autoconvert_dir(None)
-
-def update_autoconvert_dir(autodir: Path):
-    '''
-    Update the "autoconvert_dir" option in invokeai.yaml
-    '''
-    invokeai_config_path = config.init_file_path
-    conf = OmegaConf.load(invokeai_config_path)
-    conf.InvokeAI.Paths.autoconvert_dir = str(autodir) if autodir else None
-    yaml = OmegaConf.to_yaml(conf)
-    tmpfile = invokeai_config_path.parent / "new_config.tmp"
-    with open(tmpfile, "w", encoding="utf-8") as outfile:
-        outfile.write(yaml)
-    tmpfile.replace(invokeai_config_path)
+    def _download_hf_model(self, repo_id: str, files: List[str], staging: Path)->Path:
+        _,name = repo_id.split("/")
+        location = staging / name
+        paths = list()
+        for filename in files:
+            p = hf_download_with_resume(repo_id,
+                                        model_dir=location,
+                                        model_name=filename,
+                                        access_token = self.access_token
+                                        )
+            if p:
+                paths.append(p)
+            else:
+                logger.warning(f'Could not download {filename} from {repo_id}.')
+            
+        return location if len(paths)>0 else None
 
+    @classmethod
+    def _reverse_paths(cls,datasets)->dict:
+        '''
+        Reverse mapping from repo_id/path to destination name.
+        '''
+        return {v.get('path') or v.get('repo_id') : k for k, v in datasets.items()}
 
 # -------------------------------------
 def yes_or_no(prompt: str, default_yes=True):
@@ -197,133 +401,19 @@ def yes_or_no(prompt: str, default_yes=True):
         return response[0] in ("y", "Y")
 
 # ---------------------------------------------
-def recommended_datasets() -> List['str']:
-    datasets = set()
-    for ds in initial_models().keys():
-        if initial_models()[ds].get("recommended", False):
-            datasets.add(ds)
-    return list(datasets)
-
-# ---------------------------------------------
-def default_dataset() -> dict:
-    datasets = set()
-    for ds in initial_models().keys():
-        if initial_models()[ds].get("default", False):
-            datasets.add(ds)
-    return list(datasets)
-
-
-# ---------------------------------------------
-def all_datasets() -> dict:
-    datasets = dict()
-    for ds in initial_models().keys():
-        datasets[ds] = True
-    return datasets
-
-
-# ---------------------------------------------
-# look for legacy model.ckpt in models directory and offer to
-# normalize its name
-def migrate_models_ckpt():
-    model_path = os.path.join(config.root_dir, Model_dir, Weights_dir)
-    if not os.path.exists(os.path.join(model_path, "model.ckpt")):
-        return
-    new_name = initial_models()["stable-diffusion-1.4"]["file"]
-    logger.warning(
-        'The Stable Diffusion v4.1 "model.ckpt" is already installed. The name will be changed to {new_name} to avoid confusion.'
-    )
-    logger.warning(f"model.ckpt => {new_name}")
-    os.replace(
-        os.path.join(model_path, "model.ckpt"), os.path.join(model_path, new_name)
-    )
-
-
-# ---------------------------------------------
-def download_weight_datasets(
-    models: List[str], access_token: str, precision: str = "float32"
-):
-    migrate_models_ckpt()
-    successful = dict()
-    for mod in models:
-        logger.info(f"Downloading {mod}:")
-        successful[mod] = _download_repo_or_file(
-            initial_models()[mod], access_token, precision=precision
-        )
-    return successful
-
-
-def _download_repo_or_file(
-    mconfig: DictConfig, access_token: str, precision: str = "float32"
-) -> Path:
-    path = None
-    if mconfig["format"] == "ckpt":
-        path = _download_ckpt_weights(mconfig, access_token)
-    else:
-        path = _download_diffusion_weights(mconfig, access_token, precision=precision)
-        if "vae" in mconfig and "repo_id" in mconfig["vae"]:
-            _download_diffusion_weights(
-                mconfig["vae"], access_token, precision=precision
-            )
-    return path
-
-def _download_ckpt_weights(mconfig: DictConfig, access_token: str) -> Path:
-    repo_id = mconfig["repo_id"]
-    filename = mconfig["file"]
-    cache_dir = os.path.join(config.root_dir, Model_dir, Weights_dir)
-    return hf_download_with_resume(
-        repo_id=repo_id,
-        model_dir=cache_dir,
-        model_name=filename,
-        access_token=access_token,
-    )
-
-
-# ---------------------------------------------
-def download_from_hf(
-    model_class: object, model_name: str, **kwargs
+def hf_download_from_pretrained(
+        model_class: object, model_name: str, destination: Path, **kwargs
 ):
     logger = InvokeAILogger.getLogger('InvokeAI')
     logger.addFilter(lambda x: 'fp16 is not a valid' not in x.getMessage())
     
-    path = config.cache_dir
     model = model_class.from_pretrained(
         model_name,
-        cache_dir=path,
         resume_download=True,
         **kwargs,
     )
-    model_name = "--".join(("models", *model_name.split("/")))
-    return path / model_name if model else None
-
-
-def _download_diffusion_weights(
-    mconfig: DictConfig, access_token: str, precision: str = "float32"
-):
-    repo_id = mconfig["repo_id"]
-    model_class = (
-        StableDiffusionGeneratorPipeline
-        if mconfig.get("format", None) == "diffusers"
-        else AutoencoderKL
-    )
-    extra_arg_list = [{"revision": "fp16"}, {}] if precision == "float16" else [{}]
-    path = None
-    for extra_args in extra_arg_list:
-        try:
-            path = download_from_hf(
-                model_class,
-                repo_id,
-                safety_checker=None,
-                **extra_args,
-            )
-        except OSError as e:
-            if 'Revision Not Found' in str(e):
-                pass
-            else:
-                logger.error(str(e))
-        if path:
-            break
-    return path
-
+    model.save_pretrained(destination, safe_serialization=True)
+    return destination
 
 # ---------------------------------------------
 def hf_download_with_resume(
@@ -383,128 +473,3 @@ def hf_download_with_resume(
     return model_dest
 
 
-# ---------------------------------------------
-def update_config_file(successfully_downloaded: dict, config_file: Path):
-    config_file = (
-        Path(config_file) if config_file is not None else default_config_file()
-    )
-
-    # In some cases (incomplete setup, etc), the default configs directory might be missing.
-    # Create it if it doesn't exist.
-    # this check is ignored if opt.config_file is specified - user is assumed to know what they
-    # are doing if they are passing a custom config file from elsewhere.
-    if config_file is default_config_file() and not config_file.parent.exists():
-        configs_src = Dataset_path.parent
-        configs_dest = default_config_file().parent
-        shutil.copytree(configs_src, configs_dest, dirs_exist_ok=True)
-
-    yaml = new_config_file_contents(successfully_downloaded, config_file)
-
-    try:
-        backup = None
-        if os.path.exists(config_file):
-            logger.warning(
-                f"{config_file.name} exists. Renaming to {config_file.stem}.yaml.orig"
-            )
-            backup = config_file.with_suffix(".yaml.orig")
-            ## Ugh. Windows is unable to overwrite an existing backup file, raises a WinError 183
-            if sys.platform == "win32" and backup.is_file():
-                backup.unlink()
-            config_file.rename(backup)
-
-        with TemporaryFile() as tmp:
-            tmp.write(Config_preamble.encode())
-            tmp.write(yaml.encode())
-
-            with open(str(config_file.expanduser().resolve()), "wb") as new_config:
-                tmp.seek(0)
-                new_config.write(tmp.read())
-
-    except Exception as e:
-        logger.error(f"Error creating config file {config_file}: {str(e)}")
-        if backup is not None:
-            logger.info("restoring previous config file")
-            ## workaround, for WinError 183, see above
-            if sys.platform == "win32" and config_file.is_file():
-                config_file.unlink()
-            backup.rename(config_file)
-        return
-    
-    logger.info(f"Successfully created new configuration file {config_file}")
-
-
-# ---------------------------------------------
-def new_config_file_contents(
-    successfully_downloaded: dict,
-    config_file: Path,
-) -> str:
-    if config_file.exists():
-        conf = OmegaConf.load(str(config_file.expanduser().resolve()))
-    else:
-        conf = OmegaConf.create()
-
-    default_selected = None
-    for model in successfully_downloaded:
-        # a bit hacky - what we are doing here is seeing whether a checkpoint
-        # version of the model was previously defined, and whether the current
-        # model is a diffusers (indicated with a path)
-        if conf.get(model) and Path(successfully_downloaded[model]).is_dir():
-            delete_weights(model, conf[model])
-
-        stanza = {}
-        mod = initial_models()[model]
-        stanza["description"] = mod["description"]
-        stanza["repo_id"] = mod["repo_id"]
-        stanza["format"] = mod["format"]
-        # diffusers don't need width and height (probably .ckpt doesn't either)
-        # so we no longer require these in INITIAL_MODELS.yaml
-        if "width" in mod:
-            stanza["width"] = mod["width"]
-        if "height" in mod:
-            stanza["height"] = mod["height"]
-        if "file" in mod:
-            stanza["weights"] = os.path.relpath(
-                successfully_downloaded[model], start=config.root_dir
-            )
-            stanza["config"] = os.path.normpath(
-                os.path.join(sd_configs(), mod["config"])
-            )
-        if "vae" in mod:
-            if "file" in mod["vae"]:
-                stanza["vae"] = os.path.normpath(
-                    os.path.join(Model_dir, Weights_dir, mod["vae"]["file"])
-                )
-            else:
-                stanza["vae"] = mod["vae"]
-        if mod.get("default", False):
-            stanza["default"] = True
-            default_selected = True
-
-        conf[model] = stanza
-
-    # if no default model was chosen, then we select the first
-    # one in the list
-    if not default_selected:
-        conf[list(successfully_downloaded.keys())[0]]["default"] = True
-
-    return OmegaConf.to_yaml(conf)
-
-
-# ---------------------------------------------
-def delete_weights(model_name: str, conf_stanza: dict):
-    if not (weights := conf_stanza.get("weights")):
-        return
-    if re.match("/VAE/", conf_stanza.get("config")):
-        return
-
-    logger.warning(
-        f"\nThe checkpoint version of {model_name} is superseded by the diffusers version. Deleting the original file {weights}?"
-    )
-
-    weights = Path(weights)
-    if not weights.is_absolute():
-        weights = config.root_dir / weights
-        try:
-            weights.unlink()
-        except OSError as e:
-            logger.error(str(e))

invokeai/backend/model_management/__init__.py

@@ -4,3 +4,4 @@ Initialization file for invokeai.backend.model_management
 from .model_manager import ModelManager, ModelInfo
 from .model_cache import ModelCache
 from .models import BaseModelType, ModelType, SubModelType, ModelVariantType
+

invokeai/backend/model_management/convert_ckpt_to_diffusers.py

@@ -30,7 +30,7 @@ from invokeai.app.services.config import InvokeAIAppConfig
 
 from .model_manager import ModelManager
 from .model_cache import ModelCache
-from .models import SchedulerPredictionType, BaseModelType, ModelVariantType
+from .models import BaseModelType, ModelVariantType
 
 try:
     from omegaconf import OmegaConf
@@ -73,7 +73,9 @@ from transformers import (
 
 from ..stable_diffusion import StableDiffusionGeneratorPipeline
 
-MODEL_ROOT = None
+# TODO: redo in future
+#CONVERT_MODEL_ROOT = InvokeAIAppConfig.get_config().models_path / "core" / "convert"
+CONVERT_MODEL_ROOT = InvokeAIAppConfig.get_config().root_path / "models" / "core" / "convert"
 
 def shave_segments(path, n_shave_prefix_segments=1):
     """
@@ -159,17 +161,17 @@ def renew_vae_attention_paths(old_list, n_shave_prefix_segments=0):
         new_item = new_item.replace("norm.weight", "group_norm.weight")
         new_item = new_item.replace("norm.bias", "group_norm.bias")
 
-        new_item = new_item.replace("q.weight", "query.weight")
-        new_item = new_item.replace("q.bias", "query.bias")
+        new_item = new_item.replace("q.weight", "to_q.weight")
+        new_item = new_item.replace("q.bias", "to_q.bias")
 
-        new_item = new_item.replace("k.weight", "key.weight")
-        new_item = new_item.replace("k.bias", "key.bias")
+        new_item = new_item.replace("k.weight", "to_k.weight")
+        new_item = new_item.replace("k.bias", "to_k.bias")
 
-        new_item = new_item.replace("v.weight", "value.weight")
-        new_item = new_item.replace("v.bias", "value.bias")
+        new_item = new_item.replace("v.weight", "to_v.weight")
+        new_item = new_item.replace("v.bias", "to_v.bias")
 
-        new_item = new_item.replace("proj_out.weight", "proj_attn.weight")
-        new_item = new_item.replace("proj_out.bias", "proj_attn.bias")
+        new_item = new_item.replace("proj_out.weight", "to_out.0.weight")
+        new_item = new_item.replace("proj_out.bias", "to_out.0.bias")
 
         new_item = shave_segments(
             new_item, n_shave_prefix_segments=n_shave_prefix_segments
@@ -184,7 +186,6 @@ def assign_to_checkpoint(
     paths,
     checkpoint,
     old_checkpoint,
-    attention_paths_to_split=None,
     additional_replacements=None,
     config=None,
 ):
@@ -199,35 +200,9 @@ def assign_to_checkpoint(
         paths, list
     ), "Paths should be a list of dicts containing 'old' and 'new' keys."
 
-    # Splits the attention layers into three variables.
-    if attention_paths_to_split is not None:
-        for path, path_map in attention_paths_to_split.items():
-            old_tensor = old_checkpoint[path]
-            channels = old_tensor.shape[0] // 3
-
-            target_shape = (-1, channels) if len(old_tensor.shape) == 3 else (-1)
-
-            num_heads = old_tensor.shape[0] // config["num_head_channels"] // 3
-
-            old_tensor = old_tensor.reshape(
-                (num_heads, 3 * channels // num_heads) + old_tensor.shape[1:]
-            )
-            query, key, value = old_tensor.split(channels // num_heads, dim=1)
-
-            checkpoint[path_map["query"]] = query.reshape(target_shape)
-            checkpoint[path_map["key"]] = key.reshape(target_shape)
-            checkpoint[path_map["value"]] = value.reshape(target_shape)
-
     for path in paths:
         new_path = path["new"]
 
-        # These have already been assigned
-        if (
-            attention_paths_to_split is not None
-            and new_path in attention_paths_to_split
-        ):
-            continue
-
         # Global renaming happens here
         new_path = new_path.replace("middle_block.0", "mid_block.resnets.0")
         new_path = new_path.replace("middle_block.1", "mid_block.attentions.0")
@@ -246,14 +221,14 @@ def assign_to_checkpoint(
 
 def conv_attn_to_linear(checkpoint):
     keys = list(checkpoint.keys())
-    attn_keys = ["query.weight", "key.weight", "value.weight"]
+    attn_keys = ["to_q.weight", "to_k.weight", "to_v.weight"]
     for key in keys:
         if ".".join(key.split(".")[-2:]) in attn_keys:
             if checkpoint[key].ndim > 2:
                 checkpoint[key] = checkpoint[key][:, :, 0, 0]
-        elif "proj_attn.weight" in key:
+        elif "to_out.0.weight" in key:
             if checkpoint[key].ndim > 2:
-                checkpoint[key] = checkpoint[key][:, :, 0]
+                checkpoint[key] = checkpoint[key][:, :, 0, 0]
 
 
 def create_unet_diffusers_config(original_config, image_size: int):
@@ -632,7 +607,7 @@ def convert_ldm_vae_checkpoint(checkpoint, config):
     else:
         vae_state_dict = checkpoint
         
-    new_checkpoint = convert_ldm_vae_state_dict(vae_state_dict,config)
+    new_checkpoint = convert_ldm_vae_state_dict(vae_state_dict, config)
     return new_checkpoint
 
 def convert_ldm_vae_state_dict(vae_state_dict, config):
@@ -855,7 +830,7 @@ def convert_ldm_bert_checkpoint(checkpoint, config):
 
 
 def convert_ldm_clip_checkpoint(checkpoint):
-    text_model = CLIPTextModel.from_pretrained(MODEL_ROOT / 'clip-vit-large-patch14')
+    text_model = CLIPTextModel.from_pretrained(CONVERT_MODEL_ROOT / 'clip-vit-large-patch14')
     keys = list(checkpoint.keys())
 
     text_model_dict = {}
@@ -909,7 +884,7 @@ textenc_pattern = re.compile("|".join(protected.keys()))
 
 def convert_open_clip_checkpoint(checkpoint):
     text_model = CLIPTextModel.from_pretrained(
-        MODEL_ROOT / 'stable-diffusion-2-clip',
+        CONVERT_MODEL_ROOT / 'stable-diffusion-2-clip',
         subfolder='text_encoder',
     )
 
@@ -976,7 +951,7 @@ def convert_open_clip_checkpoint(checkpoint):
 
     return text_model
 
-def replace_checkpoint_vae(checkpoint, vae_path:str):
+def replace_checkpoint_vae(checkpoint, vae_path: str):
     if vae_path.endswith(".safetensors"):
         vae_ckpt = load_file(vae_path)
     else:
@@ -986,7 +961,7 @@ def replace_checkpoint_vae(checkpoint, vae_path:str):
         new_key = f'first_stage_model.{vae_key}'
         checkpoint[new_key] = state_dict[vae_key]
 
-def convert_ldm_vae_to_diffusers(checkpoint, vae_config: DictConfig, image_size: int)->AutoencoderKL:
+def convert_ldm_vae_to_diffusers(checkpoint, vae_config: DictConfig, image_size: int) -> AutoencoderKL:
     vae_config = create_vae_diffusers_config(
         vae_config, image_size=image_size
     )
@@ -1006,8 +981,6 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
     original_config_file: str,
     extract_ema: bool = True,
     precision: torch.dtype = torch.float32,
-    upcast_attention: bool = False,
-    prediction_type: SchedulerPredictionType = SchedulerPredictionType.Epsilon,
     scan_needed: bool = True,
 ) -> StableDiffusionPipeline:
     """
@@ -1021,8 +994,6 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
     :param checkpoint_path: Path to `.ckpt` file.
     :param original_config_file: Path to `.yaml` config file corresponding to the original architecture.
       If `None`, will be automatically inferred by looking for a key that only exists in SD2.0 models.
-    :param prediction_type: The prediction type that the model was trained on. Use `'epsilon'` for Stable Diffusion
-     v1.X and Stable Diffusion v2 Base. Use `'v-prediction'` for Stable Diffusion v2.
     :param scheduler_type: Type of scheduler to use. Should be one of `["pndm", "lms", "heun", "euler",
      "euler-ancestral", "dpm", "ddim"]`. :param model_type: The pipeline type. `None` to automatically infer, or one of
      `["FrozenOpenCLIPEmbedder", "FrozenCLIPEmbedder"]`. :param extract_ema: Only relevant for
@@ -1030,17 +1001,16 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
      or not. Defaults to `False`. Pass `True` to extract the EMA weights. EMA weights usually yield higher
      quality images for inference. Non-EMA weights are usually better to continue fine-tuning.
     :param precision: precision to use - torch.float16, torch.float32 or torch.autocast
-    :param upcast_attention: Whether the attention computation should always be upcasted. This is necessary when
-    running stable diffusion 2.1.
     """
-    config = InvokeAIAppConfig.get_config()
+    if not isinstance(checkpoint_path, Path):
+        checkpoint_path = Path(checkpoint_path)
 
     with warnings.catch_warnings():
         warnings.simplefilter("ignore")
         verbosity = dlogging.get_verbosity()
         dlogging.set_verbosity_error()
 
-        if str(checkpoint_path).endswith(".safetensors"):
+        if checkpoint_path.suffix == ".safetensors":
             checkpoint = load_file(checkpoint_path)
         else:
             if scan_needed:
@@ -1053,9 +1023,13 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
 
         original_config = OmegaConf.load(original_config_file)
 
-        if model_version == BaseModelType.StableDiffusion2 and prediction_type == SchedulerPredictionType.VPrediction:
+        if model_version == BaseModelType.StableDiffusion2 and original_config["model"]["params"]["parameterization"] == "v":
+            prediction_type = "v_prediction"
+            upcast_attention = True
             image_size = 768
         else:
+            prediction_type = "epsilon"
+            upcast_attention = False
             image_size = 512
 
         #
@@ -1110,7 +1084,7 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
         if model_type == "FrozenOpenCLIPEmbedder":
             text_model = convert_open_clip_checkpoint(checkpoint)
             tokenizer = CLIPTokenizer.from_pretrained(
-                MODEL_ROOT / 'stable-diffusion-2-clip',
+                CONVERT_MODEL_ROOT / 'stable-diffusion-2-clip',
                 subfolder='tokenizer',
             )
             pipe = StableDiffusionPipeline(
@@ -1126,9 +1100,9 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
 
         elif model_type in ["FrozenCLIPEmbedder", "WeightedFrozenCLIPEmbedder"]:
             text_model = convert_ldm_clip_checkpoint(checkpoint)
-            tokenizer = CLIPTokenizer.from_pretrained(MODEL_ROOT / 'clip-vit-large-patch14')
-            safety_checker = StableDiffusionSafetyChecker.from_pretrained(MODEL_ROOT / 'stable-diffusion-safety-checker')
-            feature_extractor = AutoFeatureExtractor.from_pretrained(MODEL_ROOT / 'stable-diffusion-safety-checker')
+            tokenizer = CLIPTokenizer.from_pretrained(CONVERT_MODEL_ROOT / 'clip-vit-large-patch14')
+            safety_checker = StableDiffusionSafetyChecker.from_pretrained(CONVERT_MODEL_ROOT / 'stable-diffusion-safety-checker')
+            feature_extractor = AutoFeatureExtractor.from_pretrained(CONVERT_MODEL_ROOT / 'stable-diffusion-safety-checker')
             pipe = StableDiffusionPipeline(
                 vae=vae.to(precision),
                 text_encoder=text_model.to(precision),
@@ -1142,7 +1116,7 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
         else:
             text_config = create_ldm_bert_config(original_config)
             text_model = convert_ldm_bert_checkpoint(checkpoint, text_config)
-            tokenizer = BertTokenizerFast.from_pretrained(MODEL_ROOT / "bert-base-uncased")
+            tokenizer = BertTokenizerFast.from_pretrained(CONVERT_MODEL_ROOT / "bert-base-uncased")
             pipe = LDMTextToImagePipeline(
                 vqvae=vae,
                 bert=text_model,
@@ -1158,7 +1132,6 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
 def convert_ckpt_to_diffusers(
         checkpoint_path: Union[str, Path],
         dump_path: Union[str, Path],
-        model_root: Union[str, Path],
         **kwargs,
 ):
     """
@@ -1166,9 +1139,6 @@ def convert_ckpt_to_diffusers(
     and in addition a path-like object indicating the location of the desired diffusers
     model to be written.
     """
-    # setting global here to avoid massive changes late at night
-    global MODEL_ROOT
-    MODEL_ROOT = Path(model_root) / 'core/convert'
     pipe = load_pipeline_from_original_stable_diffusion_ckpt(checkpoint_path, **kwargs)
 
     pipe.save_pretrained(

invokeai/backend/model_management/lora.py

@@ -70,7 +70,7 @@ class LoRALayerBase:
             op = torch.nn.functional.linear
             extra_args = {}
 
-        weight = self.get_weight(module)
+        weight = self.get_weight()
 
         bias = self.bias if self.bias is not None else 0
         scale = self.alpha / self.rank if (self.alpha and self.rank) else 1.0
@@ -81,7 +81,7 @@ class LoRALayerBase:
             **extra_args,
         ) * multiplier * scale
 
-    def get_weight(self, module: torch.nn.Module):
+    def get_weight(self):
         raise NotImplementedError()
 
     def calc_size(self) -> int:
@@ -122,7 +122,7 @@ class LoRALayer(LoRALayerBase):
 
         self.rank = self.down.shape[0]
 
-    def get_weight(self, module: torch.nn.Module):
+    def get_weight(self):
         if self.mid is not None:
             up = self.up.reshape(up.shape[0], up.shape[1])
             down = self.down.reshape(up.shape[0], up.shape[1])
@@ -166,7 +166,7 @@ class LoHALayer(LoRALayerBase):
         layer_key: str,
         values: dict,
     ):
-        super().__init__(module_key, rank, alpha, bias)
+        super().__init__(layer_key, values)
 
         self.w1_a = values["hada_w1_a"]
         self.w1_b = values["hada_w1_b"]
@@ -185,7 +185,7 @@ class LoHALayer(LoRALayerBase):
 
         self.rank = self.w1_b.shape[0]
 
-    def get_weight(self, module: torch.nn.Module):
+    def get_weight(self):
         if self.t1 is None:
             weight = (self.w1_a @ self.w1_b) * (self.w2_a @ self.w2_b)
 
@@ -239,7 +239,7 @@ class LoKRLayer(LoRALayerBase):
         layer_key: str,
         values: dict,
     ):
-        super().__init__(module_key, rank, alpha, bias)        
+        super().__init__(layer_key, values)        
 
         if "lokr_w1" in values:
             self.w1 = values["lokr_w1"]
@@ -271,7 +271,7 @@ class LoKRLayer(LoRALayerBase):
         else:
             self.rank = None # unscaled
 
-    def get_weight(self, module: torch.nn.Module):
+    def get_weight(self):
         w1 = self.w1
         if w1 is None:
             w1 = self.w1_a @ self.w1_b
@@ -286,7 +286,7 @@ class LoKRLayer(LoRALayerBase):
         if len(w2.shape) == 4:
             w1 = w1.unsqueeze(2).unsqueeze(2)
         w2 = w2.contiguous()
-        weight = torch.kron(w1, w2).reshape(module.weight.shape) # TODO: can we remove reshape?
+        weight = torch.kron(w1, w2)
 
         return weight
 
@@ -471,7 +471,7 @@ class ModelPatcher:
                 submodule_name += "_" + key_parts.pop(0)
 
         module = module.get_submodule(submodule_name)
-        module_key = module_key.rstrip(".")
+        module_key = (module_key + "." + submodule_name).lstrip(".")
 
         return (module_key, module)
 
@@ -525,23 +525,36 @@ class ModelPatcher:
         loras: List[Tuple[LoraModel, float]],
         prefix: str,
     ):
-        hooks = dict()
+        original_weights = dict()
         try:
-            for lora, lora_weight in loras:
-                for layer_key, layer in lora.layers.items():
-                    if not layer_key.startswith(prefix):
-                        continue
+            with torch.no_grad():
+                for lora, lora_weight in loras:
+                    #assert lora.device.type == "cpu"
+                    for layer_key, layer in lora.layers.items():
+                        if not layer_key.startswith(prefix):
+                            continue
 
-                    module_key, module = cls._resolve_lora_key(model, layer_key, prefix)
-                    if module_key not in hooks:
-                        hooks[module_key] = module.register_forward_hook(cls._lora_forward_hook(loras, layer_key))
+                        module_key, module = cls._resolve_lora_key(model, layer_key, prefix)
+                        if module_key not in original_weights:
+                            original_weights[module_key] = module.weight.detach().to(device="cpu", copy=True)
+
+                        # enable autocast to calc fp16 loras on cpu
+                        with torch.autocast(device_type="cpu"):
+                            layer_scale = layer.alpha / layer.rank if (layer.alpha and layer.rank) else 1.0
+                            layer_weight = layer.get_weight() * lora_weight * layer_scale
+
+                        if module.weight.shape != layer_weight.shape:
+                            # TODO: debug on lycoris
+                            layer_weight = layer_weight.reshape(module.weight.shape)
+
+                        module.weight += layer_weight.to(device=module.weight.device, dtype=module.weight.dtype)
 
             yield # wait for context manager exit
 
         finally:
-            for module_key, hook in hooks.items():
-                hook.remove()
-            hooks.clear()
+            with torch.no_grad():
+                for module_key, weight in original_weights.items():
+                    model.get_submodule(module_key).weight.copy_(weight)
 
 
     @classmethod
@@ -591,7 +604,7 @@ class ModelPatcher:
                             f"Cannot load embedding for {trigger}. It was trained on a model with token dimension {embedding.shape[0]}, but the current model has token dimension {model_embeddings.weight.data[token_id].shape[0]}."
                         )
 
-                    model_embeddings.weight.data[token_id] = embedding
+                    model_embeddings.weight.data[token_id] = embedding.to(device=text_encoder.device, dtype=text_encoder.dtype)
                     ti_tokens.append(token_id)
 
                 if len(ti_tokens) > 1:

invokeai/backend/model_management/model_cache.py

@@ -100,8 +100,6 @@ class ModelCache(object):
         :param sha_chunksize: Chunksize to use when calculating sha256 model hash
         '''
         #max_cache_size = 9999
-        execution_device = torch.device('cuda')
-
         self.model_infos: Dict[str, ModelBase] = dict()
         self.lazy_offloading = lazy_offloading
         #self.sequential_offload: bool=sequential_offload
@@ -354,7 +352,9 @@ class ModelCache(object):
         for model_key, cache_entry in self._cached_models.items():
             if not cache_entry.locked and cache_entry.loaded:
                 self.logger.debug(f'Offloading {model_key} from {self.execution_device} into {self.storage_device}')
-                cache_entry.model.to(self.storage_device)
+                with VRAMUsage() as mem:
+                    cache_entry.model.to(self.storage_device)
+                self.logger.debug(f'GPU VRAM freed: {(mem.vram_used/GIG):.2f} GB')
         
     def _local_model_hash(self, model_path: Union[str, Path]) -> str:
         sha = hashlib.sha256()

invokeai/backend/model_management/model_install.py

@@ -1,118 +0,0 @@
-"""
-Routines for downloading and installing models.
-"""
-import json
-import safetensors
-import safetensors.torch
-import shutil
-import tempfile
-import torch
-import traceback
-from dataclasses import dataclass
-from diffusers import ModelMixin
-from enum import Enum
-from typing import Callable
-from pathlib import Path
-
-import invokeai.backend.util.logging as logger
-from invokeai.app.services.config import InvokeAIAppConfig
-from . import ModelManager
-from .models import BaseModelType, ModelType, VariantType
-from .model_probe import ModelProbe, ModelVariantInfo
-from .model_cache import SilenceWarnings
-
-class ModelInstall(object):
-    '''
-    This class is able to download and install several different kinds of 
-    InvokeAI models. The helper function, if provided, is called on to distinguish
-    between v2-base and v2-768 stable diffusion pipelines. This usually involves
-    asking the user to select the proper type, as there is no way of distinguishing
-    the two type of v2 file programmatically (as far as I know).
-    '''
-    def __init__(self,
-                 config: InvokeAIAppConfig,
-                 model_base_helper: Callable[[Path],BaseModelType]=None,
-                 clobber:bool = False
-                 ):
-        '''
-        :param config: InvokeAI configuration object
-        :param model_base_helper: A function call that accepts the Path to a checkpoint model and returns a ModelType enum
-        :param clobber: If true, models with colliding names will be overwritten
-        '''
-        self.config = config
-        self.clogger = clobber
-        self.helper = model_base_helper
-        self.prober = ModelProbe()
-
-    def install_checkpoint_file(self, checkpoint: Path)->dict:
-        '''
-        Install the checkpoint file at path and return a
-        configuration entry that can be added to `models.yaml`.
-        Model checkpoints and VAEs will be converted into 
-        diffusers before installation. Note that the model manager
-        does not hold entries for anything but diffusers pipelines,
-        and the configuration file stanzas returned from such models
-        can be safely ignored.
-        '''
-        model_info = self.prober.probe(checkpoint, self.helper)
-        if not model_info:
-            raise ValueError(f"Unable to determine type of checkpoint file {checkpoint}")
-
-        key = ModelManager.create_key(
-            model_name = checkpoint.stem,
-            base_model = model_info.base_type,
-            model_type = model_info.model_type,
-        )
-        destination_path = self._dest_path(model_info) / checkpoint
-        destination_path.parent.mkdir(parents=True, exist_ok=True)
-        self._check_for_collision(destination_path)
-        stanza = {
-            key: dict(
-                name = checkpoint.stem,
-                description = f'{model_info.model_type} model {checkpoint.stem}',
-                base = model_info.base_model.value,
-                type = model_info.model_type.value,
-                variant = model_info.variant_type.value,
-                path = str(destination_path),
-            )
-       }
-        
-        # non-pipeline; no conversion needed, just copy into right place
-        if model_info.model_type != ModelType.Pipeline:
-            shutil.copyfile(checkpoint, destination_path)
-            stanza[key].update({'format': 'checkpoint'})
-            
-        # pipeline - conversion needed here
-        else:
-            destination_path = self._dest_path(model_info) / checkpoint.stem
-            config_file = self._pipeline_type_to_config_file(model_info.model_type)
-
-            from .convert_ckpt_to_diffusers import convert_ckpt_to_diffusers
-            with SilenceWarnings:
-                convert_ckpt_to_diffusers(
-                    checkpoint,
-                    destination_path,
-                    extract_ema=True,
-                    original_config_file=config_file,
-                    scan_needed=False,
-                )
-            stanza[key].update({'format': 'folder',
-                                'path': destination_path, # no suffix on this
-                                })
-            
-        return stanza
-
-
-    def _check_for_collision(self, path: Path):
-        if not path.exists():
-            return
-        if self.clobber:
-            shutil.rmtree(path)
-        else:
-            raise ValueError(f"Destination {path} already exists. Won't overwrite unless clobber=True.")
-
-    def _staging_directory(self)->tempfile.TemporaryDirectory:
-        return tempfile.TemporaryDirectory(dir=self.config.root_path)
-
-    
-        

invokeai/backend/model_management/model_manager.py

@@ -1,53 +1,209 @@
 """This module manages the InvokeAI `models.yaml` file, mapping
-symbolic diffusers model names to the paths and repo_ids used
-by the underlying `from_pretrained()` call.
+symbolic diffusers model names to the paths and repo_ids used by the
+underlying `from_pretrained()` call.
 
-For fetching models, use manager.get_model('symbolic name'). This will
-return a ModelInfo object that contains the following attributes:
-   
-   * context -- a context manager Generator that loads and locks the 
-                model into GPU VRAM and returns the model for use. 
-                See below for usage.
-   * name -- symbolic name of the model
-   * type -- SubModelType of the model
-   * hash -- unique hash for the model
-   * location -- path or repo_id of the model
-   * revision -- revision of the model if coming from a repo id,
-                e.g. 'fp16'
-   * precision -- torch precision of the model
+SYNOPSIS:
 
-Typical usage:
+ mgr = ModelManager('/home/phi/invokeai/configs/models.yaml')
+ sd1_5 = mgr.get_model('stable-diffusion-v1-5',
+                       model_type=ModelType.Main,
+                       base_model=BaseModelType.StableDiffusion1,
+                       submodel_type=SubModelType.Unet)
+ with sd1_5 as unet:
+    run_some_inference(unet)
 
-   from invokeai.backend import ModelManager
+FETCHING MODELS:
 
-   manager = ModelManager(
-                 config='./configs/models.yaml',
-                 max_cache_size=8
-             ) # gigabytes
+Models are described using four attributes:
 
-   model_info = manager.get_model('stable-diffusion-1.5', SubModelType.Diffusers)
-   with model_info.context as my_model:
-      my_model.latents_from_embeddings(...)
+  1) model_name -- the symbolic name for the model
 
-The manager uses the underlying ModelCache class to keep
-frequently-used models in RAM and move them into GPU as needed for
-generation operations. The optional `max_cache_size` argument
-indicates the maximum size the cache can grow to, in gigabytes. The
-underlying ModelCache object can be accessed using the manager's "cache"
-attribute.
+  2) ModelType  -- an enum describing the type of the model. Currently
+                  defined types are:
+         ModelType.Main -- a full model capable of generating images
+         ModelType.Vae  -- a VAE model
+         ModelType.Lora -- a LoRA or LyCORIS fine-tune
+         ModelType.TextualInversion -- a textual inversion embedding
+         ModelType.ControlNet -- a ControlNet model
 
-Because the model manager can return multiple different types of
-models, you may wish to add additional type checking on the class
-of model returned. To do this, provide the option `model_type`
-parameter:
+  3) BaseModelType -- an enum indicating the stable diffusion base model, one of:
+         BaseModelType.StableDiffusion1
+         BaseModelType.StableDiffusion2
 
-    model_info = manager.get_model(
-                      'clip-tokenizer',
-                       model_type=SubModelType.Tokenizer
-                      )
+  4) SubModelType (optional) -- an enum that refers to one of the submodels contained
+                                within the main model. Values are:
 
-This will raise an InvalidModelError if the format defined in the
-config file doesn't match the requested model type.
+         SubModelType.UNet
+         SubModelType.TextEncoder
+         SubModelType.Tokenizer
+         SubModelType.Scheduler
+         SubModelType.SafetyChecker
+
+To fetch a model, use `manager.get_model()`. This takes the symbolic
+name of the model, the ModelType, the BaseModelType and the
+SubModelType. The latter is required for ModelType.Main.
+
+get_model() will return a ModelInfo object that can then be used in
+context to retrieve the model and move it into GPU VRAM (on GPU
+systems).
+
+A typical example is:
+
+ sd1_5 = mgr.get_model('stable-diffusion-v1-5',
+                       model_type=ModelType.Main,
+                       base_model=BaseModelType.StableDiffusion1,
+                       submodel_type=SubModelType.UNet)
+ with sd1_5 as unet:
+    run_some_inference(unet)
+
+The ModelInfo object provides a number of useful fields describing the
+model, including:
+
+   name  -- symbolic name of the model
+   base_model -- base model (BaseModelType)
+   type -- model type (ModelType)
+   location -- path to the model file
+   precision -- torch precision of the model
+   hash -- unique sha256 checksum for this model
+
+SUBMODELS:
+
+When fetching a main model, you must specify the submodel. Retrieval
+of full pipelines is not supported.
+
+ vae_info = mgr.get_model('stable-diffusion-1.5',
+                          model_type = ModelType.Main,
+                          base_model = BaseModelType.StableDiffusion1,
+                          submodel_type = SubModelType.Vae
+                          )
+ with vae_info as vae:
+    do_something(vae)
+
+This rule does not apply to controlnets, embeddings, loras and standalone
+VAEs, which do not have submodels.
+
+LISTING MODELS
+
+The model_names() method will return a list of Tuples describing each
+model it knows about:
+
+  >> mgr.model_names()
+  [
+    ('stable-diffusion-1.5', <BaseModelType.StableDiffusion1: 'sd-1'>, <ModelType.Main: 'main'>),
+    ('stable-diffusion-2.1', <BaseModelType.StableDiffusion2: 'sd-2'>, <ModelType.Main: 'main'>),
+    ('inpaint', <BaseModelType.StableDiffusion1: 'sd-1'>, <ModelType.ControlNet: 'controlnet'>)
+    ('Ink scenery', <BaseModelType.StableDiffusion1: 'sd-1'>, <ModelType.Lora: 'lora'>)
+    ...
+  ]
+
+The tuple is in the correct order to pass to get_model():
+
+   for m in mgr.model_names():
+       info = get_model(*m)
+
+In contrast, the list_models() method returns a list of dicts, each
+providing information about a model defined in models.yaml. For example:
+
+   >>> models = mgr.list_models()
+   >>> json.dumps(models[0])
+  {"path": "/home/lstein/invokeai-main/models/sd-1/controlnet/canny", 
+    "model_format": "diffusers", 
+    "name": "canny", 
+    "base_model": "sd-1", 
+    "type": "controlnet"
+   }
+
+You can filter by model type and base model as shown here:
+
+  
+  controlnets = mgr.list_models(model_type=ModelType.ControlNet,
+                                base_model=BaseModelType.StableDiffusion1)
+  for c in controlnets:
+     name = c['name']
+     format = c['model_format']
+     path = c['path']
+     type = c['type']
+     # etc
+
+ADDING AND REMOVING MODELS
+
+At startup time, the `models` directory will be scanned for
+checkpoints, diffusers pipelines, controlnets, LoRAs and TI
+embeddings. New entries will be added to the model manager and defunct
+ones removed. Anything that is a main model (ModelType.Main) will be
+added to models.yaml. For scanning to succeed, files need to be in
+their proper places. For example, a controlnet folder built on the
+stable diffusion 2 base, will need to be placed in
+`models/sd-2/controlnet`.
+
+Layout of the `models` directory:
+
+ models
+ ├── sd-1
+ │   ├── controlnet
+ │   ├── lora
+ │   ├── main
+ │   └── embedding
+ ├── sd-2
+ │   ├── controlnet
+ │   ├── lora
+ │   ├── main
+ │   └── embedding
+ └── core
+     ├── face_reconstruction
+     │   ├── codeformer
+     │   └── gfpgan
+     ├── sd-conversion
+     │   ├── clip-vit-large-patch14 - tokenizer, text_encoder subdirs
+     │   ├── stable-diffusion-2 - tokenizer, text_encoder subdirs
+     │   └── stable-diffusion-safety-checker
+     └── upscaling
+         └─── esrgan
+
+
+
+class ConfigMeta(BaseModel):Loras, textual_inversion and controlnet models are not listed
+explicitly in models.yaml, but are added to the in-memory data
+structure at initialization time by scanning the models directory. The
+in-memory data structure can be resynchronized by calling
+`manager.scan_models_directory()`.
+
+Files and folders placed inside the `autoimport` paths (paths
+defined in `invokeai.yaml`) will also be scanned for new models at
+initialization time and added to `models.yaml`. Files will not be
+moved from this location but preserved in-place. These directories
+are:
+
+  configuration    default              description
+  -------------    -------              -----------
+  autoimport_dir  autoimport/main       main models
+  lora_dir        autoimport/lora       LoRA/LyCORIS models
+  embedding_dir   autoimport/embedding  TI embeddings
+  controlnet_dir  autoimport/controlnet ControlNet models
+
+In actuality, models located in any of these directories are scanned
+to determine their type, so it isn't strictly necessary to organize
+the different types in this way. This entry in `invokeai.yaml` will
+recursively scan all subdirectories within `autoimport`, scan models
+files it finds, and import them if recognized.
+
+  Paths:
+     autoimport_dir: autoimport
+
+A model can be manually added using `add_model()` using the model's
+name, base model, type and a dict of model attributes. See
+`invokeai/backend/model_management/models` for the attributes required
+by each model type.
+
+A model can be deleted using `del_model()`, providing the same 
+identifying information as `get_model()`
+
+The `heuristic_import()` method will take a set of strings
+corresponding to local paths, remote URLs, and repo_ids, probe the
+object to determine what type of model it is (if any), and import new
+models into the manager. If passed a directory, it will recursively
+scan it for models to import. The return value is a set of the models
+successfully added.
 
 MODELS.YAML
 
@@ -56,93 +212,18 @@ The general format of a models.yaml section is:
  type-of-model/name-of-model:
      path: /path/to/local/file/or/directory
      description: a description
-     format: folder|ckpt|safetensors|pt
-     base: SD-1|SD-2
-     subfolder: subfolder-name
+     format: diffusers|checkpoint
+     variant: normal|inpaint|depth
 
 The type of model is given in the stanza key, and is one of
-{diffusers, ckpt, vae, text_encoder, tokenizer, unet, scheduler,
-safety_checker, feature_extractor, lora, textual_inversion,
-controlnet}, and correspond to items in the SubModelType enum defined
-in model_cache.py
+{main, vae, lora, controlnet, textual}
 
-The format indicates whether the model is organized as a folder with
-model subdirectories, or is contained in a single checkpoint or
-safetensors file.
+The format indicates whether the model is organized as a diffusers
+folder with model subdirectories, or is contained in a single
+checkpoint or safetensors file.
 
-One, but not both, of repo_id and path are provided. repo_id is the
-HuggingFace repository ID of the model, and path points to the file or
-directory on disk.
-
-If subfolder is provided, then the model exists in a subdirectory of
-the main model. These are usually named after the model type, such as
-"unet".
-
-This example summarizes the two ways of getting a non-diffuser model:
-
- text_encoder/clip-test-1:
-   format: folder
-   path: /path/to/folder
-   description: Returns standalone CLIPTextModel
-
- text_encoder/clip-test-2:
-   format: folder
-   repo_id: /path/to/folder
-   subfolder: text_encoder
-   description: Returns the text_encoder in the subfolder of the diffusers model (just the encoder in RAM)
-
-SUBMODELS:
-
-It is also possible to fetch an isolated submodel from a diffusers
-model. Use the `submodel` parameter to select which part:
-
- vae = manager.get_model('stable-diffusion-1.5',submodel=SubModelType.Vae)
- with vae.context as my_vae:
-    print(type(my_vae))
-    # "AutoencoderKL"
-
-DIRECTORY_SCANNING:
-
-Loras, textual_inversion and controlnet models are usually not listed
-explicitly in models.yaml, but are added to the in-memory data
-structure at initialization time by scanning the models directory. The
-in-memory data structure can be resynchronized by calling
-`manager.scan_models_directory`.
-
-DISAMBIGUATION:
-
-You may wish to use the same name for a related family of models. To
-do this, disambiguate the stanza key with the model and and format
-separated by "/". Example:
-
- tokenizer/clip-large:
-   format: tokenizer
-   path: /path/to/folder
-   description: Returns standalone tokenizer
-
- text_encoder/clip-large:
-   format: text_encoder
-   path: /path/to/folder
-   description: Returns standalone text encoder
-
-You can now use the `model_type` argument to indicate which model you
-want:
-
- tokenizer = mgr.get('clip-large',model_type=SubModelType.Tokenizer)
- encoder = mgr.get('clip-large',model_type=SubModelType.TextEncoder)
-
-OTHER FUNCTIONS:
-
-Other methods provided by ModelManager support importing, editing,
-converting and deleting models.
-
-IMPORTANT CHANGES AND LIMITATIONS SINCE 2.3:
-
-1. Only local paths are supported. Repo_ids are no longer accepted. This
-simplifies the logic.
-
-2. VAEs can't be swapped in and out at load time. They must be baked
-into the model when downloaded or converted.
+The path points to a file or directory on disk. If a relative path,
+the root is the InvokeAI ROOTDIR.
 
 """
 from __future__ import annotations
@@ -151,13 +232,11 @@ import os
 import hashlib
 import textwrap
 from dataclasses import dataclass
-from packaging import version
 from pathlib import Path
-from typing import Dict, Optional, List, Tuple, Union, types
+from typing import Optional, List, Tuple, Union, Set, Callable, types
 from shutil import rmtree
 
 import torch
-from huggingface_hub import scan_cache_dir
 from omegaconf import OmegaConf
 from omegaconf.dictconfig import DictConfig
 
@@ -165,9 +244,13 @@ from pydantic import BaseModel
 
 import invokeai.backend.util.logging as logger
 from invokeai.app.services.config import InvokeAIAppConfig
-from invokeai.backend.util import CUDA_DEVICE, download_with_resume
+from invokeai.backend.util import CUDA_DEVICE, Chdir
 from .model_cache import ModelCache, ModelLocker
-from .models import BaseModelType, ModelType, SubModelType, ModelError, MODEL_CLASSES
+from .models import (
+    BaseModelType, ModelType, SubModelType,
+    ModelError, SchedulerPredictionType, MODEL_CLASSES,
+    ModelConfigBase,
+    )
 
 # We are only starting to number the config file with release 3.
 # The config file version doesn't have to start at release version, but it will help
@@ -183,7 +266,6 @@ class ModelInfo():
     hash: str
     location: Union[Path, str]
     precision: torch.dtype
-    revision: str = None
     _cache: ModelCache = None
 
     def __enter__(self):
@@ -199,31 +281,6 @@ class InvalidModelError(Exception):
 MAX_CACHE_SIZE = 6.0  # GB
 
 
-# layout of the models directory:
-# models
-# ├── sd-1
-# │   ├── controlnet
-# │   ├── lora
-# │   ├── pipeline
-# │   └── textual_inversion
-# ├── sd-2
-# │   ├── controlnet
-# │   ├── lora
-# │   ├── pipeline
-# │   └── textual_inversion
-# └── core
-#     ├── face_reconstruction
-#     │   ├── codeformer
-#     │   └── gfpgan
-#     ├── sd-conversion
-#     │   ├── clip-vit-large-patch14 - tokenizer, text_encoder subdirs
-#     │   ├── stable-diffusion-2 - tokenizer, text_encoder subdirs
-#     │   └── stable-diffusion-safety-checker
-#     └── upscaling
-#         └─── esrgan
-
-
-
 class ConfigMeta(BaseModel):
     version: str
 
@@ -271,7 +328,7 @@ class ModelManager(object):
             self.models[model_key] = model_class.create_config(**model_config)
 
         # check config version number and update on disk/RAM if necessary
-        self.globals = InvokeAIAppConfig.get_config()
+        self.app_config = InvokeAIAppConfig.get_config()
         self.logger = logger
         self.cache = ModelCache(
             max_cache_size=max_cache_size,
@@ -307,7 +364,8 @@ class ModelManager(object):
     ) -> str:
         return f"{base_model}/{model_type}/{model_name}"
 
-    def parse_key(self, model_key: str) -> Tuple[str, BaseModelType, ModelType]:
+    @classmethod
+    def parse_key(cls, model_key: str) -> Tuple[str, BaseModelType, ModelType]:
         base_model_str, model_type_str, model_name = model_key.split('/', 2)
         try:
             model_type = ModelType(model_type_str)
@@ -321,86 +379,44 @@ class ModelManager(object):
 
         return (model_name, base_model, model_type)
 
+    def _get_model_cache_path(self, model_path):
+        return self.app_config.models_path / ".cache" / hashlib.md5(str(model_path).encode()).hexdigest()
+
     def get_model(
         self,
         model_name: str,
         base_model: BaseModelType,
         model_type: ModelType,
         submodel_type: Optional[SubModelType] = None
-    ):
+    )->ModelInfo:
         """Given a model named identified in models.yaml, return
         an ModelInfo object describing it.
         :param model_name: symbolic name of the model in models.yaml
         :param model_type: ModelType enum indicating the type of model to return
+        :param base_model: BaseModelType enum indicating the base model used by this model
         :param submode_typel: an ModelType enum indicating the portion of 
                the model to retrieve (e.g. ModelType.Vae)
-
-        If not provided, the model_type will be read from the `format` field
-        of the corresponding stanza. If provided, the model_type will be used
-        to disambiguate stanzas in the configuration file. The default is to
-        assume a diffusers pipeline. The behavior is illustrated here:
-
-        [models.yaml]
-        diffusers/test1:
-           repo_id: foo/bar
-           description: Typical diffusers pipeline
-
-        lora/test1:
-           repo_id: /tmp/loras/test1.safetensors
-           description: Typical lora file
-
-        test1_pipeline = mgr.get_model('test1')
-        # returns a StableDiffusionGeneratorPipeline
-
-        test1_vae1 = mgr.get_model('test1', submodel=ModelType.Vae)
-        # returns the VAE part of a diffusers model as an AutoencoderKL
-
-        test1_vae2 = mgr.get_model('test1', model_type=ModelType.Diffusers, submodel=ModelType.Vae)
-        # does the same thing as the previous  statement. Note that model_type
-        # is for the parent model, and submodel is for the part
-
-        test1_lora = mgr.get_model('test1', model_type=ModelType.Lora)
-        # returns a LoRA embed (as a 'dict' of tensors)
-
-        test1_encoder = mgr.get_modelI('test1', model_type=ModelType.TextEncoder)
-        # raises an InvalidModelError
-
         """
         model_class = MODEL_CLASSES[base_model][model_type]
         model_key = self.create_key(model_name, base_model, model_type)
 
         # if model not found try to find it (maybe file just pasted)
         if model_key not in self.models:
-            # TODO: find by mask or try rescan?
-            path_mask = f"/models/{base_model}/{model_type}/{model_name}*"
-            if False: # model_path = next(find_by_mask(path_mask)):
-                model_path = None # TODO:
-                model_config = model_class.probe_config(model_path)
-                self.models[model_key] = model_config
-            else:
+            self.scan_models_directory(base_model=base_model, model_type=model_type)
+            if model_key not in self.models:
                 raise Exception(f"Model not found - {model_key}")
 
-        # if it known model check that target path exists (if manualy deleted)
-        else:
-            # logic repeated twice(in rescan too) any way to optimize?
-            if not os.path.exists(self.models[model_key].path):
-                if model_class.save_to_config:
-                    self.models[model_key].error = ModelError.NotFound
-                    raise Exception(f"Files for model \"{model_key}\" not found")
-
-                else:
-                    self.models.pop(model_key, None)
-                    raise Exception(f"Model not found - {model_key}")
-
-            # reset model errors?
-
-
-
         model_config = self.models[model_key]
+        model_path = self.app_config.root_path / model_config.path
 
-        # /models/{base_model}/{model_type}/{name}.ckpt or .safentesors
-        # /models/{base_model}/{model_type}/{name}/
-        model_path = model_config.path
+        if not model_path.exists():
+            if model_class.save_to_config:
+                self.models[model_key].error = ModelError.NotFound
+                raise Exception(f"Files for model \"{model_key}\" not found")
+
+            else:
+                self.models.pop(model_key, None)
+                raise Exception(f"Model not found - {model_key}")
 
         # vae/movq override
         # TODO: 
@@ -414,10 +430,10 @@ class ModelManager(object):
 
         # TODO: path
         # TODO: is it accurate to use path as id
-        dst_convert_path = self.globals.models_dir / ".cache" / hashlib.md5(model_path.encode()).hexdigest()
+        dst_convert_path = self._get_model_cache_path(model_path)
         model_path = model_class.convert_if_required(
             base_model=base_model,
-            model_path=model_path,
+            model_path=str(model_path), # TODO: refactor str/Path types logic
             output_path=dst_convert_path,
             config=model_config,
         )
@@ -476,11 +492,6 @@ class ModelManager(object):
     ) -> list[dict]:
         """
         Return a list of models.
-
-        Please use model_manager.models() to get all the model names,
-        model_manager.model_info('model-name') to get the stanza for the model
-        named 'model-name', and model_manager.config to get the full OmegaConf
-        object derived from models.yaml
         """
 
         models = []
@@ -507,7 +518,7 @@ class ModelManager(object):
 
     def print_models(self) -> None:
         """
-        Print a table of models, their descriptions
+        Print a table of models and their descriptions. This needs to be redone
         """
         # TODO: redo
         for model_type, model_dict in self.list_models().items():
@@ -515,7 +526,7 @@ class ModelManager(object):
                 line = f'{model_info["name"]:25s} {model_info["type"]:10s} {model_info["description"]}'
                 print(line)
 
-    # TODO: test when ui implemented
+    # Tested - LS
     def del_model(
         self,
         model_name: str,
@@ -525,7 +536,6 @@ class ModelManager(object):
         """
         Delete the named model.
         """
-        raise Exception("TODO: del_model") # TODO: redo
         model_key = self.create_key(model_name, base_model, model_type)
         model_cfg = self.models.pop(model_key, None)
 
@@ -541,14 +551,18 @@ class ModelManager(object):
             self.cache.uncache_model(cache_id)
 
         # if model inside invoke models folder - delete files
-        if model_cfg.path.startswith("models/") or model_cfg.path.startswith("models\\"):
-            model_path = self.globals.root_dir / model_cfg.path
-            if model_path.isdir():
-                shutil.rmtree(str(model_path))
+        model_path = self.app_config.root_path / model_cfg.path
+        cache_path = self._get_model_cache_path(model_path)
+        if cache_path.exists():
+            rmtree(str(cache_path))
+
+        if model_path.is_relative_to(self.app_config.models_path):
+            if model_path.is_dir():
+                rmtree(str(model_path))
             else:
                 model_path.unlink()
 
-    # TODO: test when ui implemented
+    # LS: tested
     def add_model(
         self,
         model_name: str,
@@ -569,18 +583,30 @@ class ModelManager(object):
         model_config = model_class.create_config(**model_attributes)
         model_key = self.create_key(model_name, base_model, model_type)
 
-        assert (
-            clobber or model_key not in self.models
-        ), f'attempt to overwrite existing model definition "{model_key}"'
+        if  model_key in self.models and not clobber:
+            raise Exception(f'Attempt to overwrite existing model definition "{model_key}"')
 
-        self.models[model_key] = model_config
-            
-        if clobber and model_key in self.cache_keys:
+        old_model = self.models.pop(model_key, None)
+        if old_model is not None:
+            # TODO: if path changed and old_model.path inside models folder should we delete this too?
+
+            # remove conversion cache as config changed
+            old_model_path = self.app_config.root_path / old_model.path
+            old_model_cache = self._get_model_cache_path(old_model_path)
+            if old_model_cache.exists():
+                if old_model_cache.is_dir():
+                    rmtree(str(old_model_cache))
+                else:
+                    old_model_cache.unlink()
+
+            # remove in-memory cache
             # note: it not garantie to release memory(model can has other references)
             cache_ids = self.cache_keys.pop(model_key, [])
             for cache_id in cache_ids:
                 self.cache.uncache_model(cache_id)
 
+        self.models[model_key] = model_config
+
     def search_models(self, search_folder):
         self.logger.info(f"Finding Models In: {search_folder}")
         models_folder_ckpt = Path(search_folder).glob("**/*.ckpt")
@@ -621,7 +647,7 @@ class ModelManager(object):
         yaml_str = OmegaConf.to_yaml(data_to_save)
         config_file_path = conf_file or self.config_path
         assert config_file_path is not None,'no config file path to write to'
-        config_file_path = self.globals.root_dir / config_file_path
+        config_file_path = self.app_config.root_path / config_file_path
         tmpfile = os.path.join(os.path.dirname(config_file_path), "new_config.tmp")
         with open(tmpfile, "w", encoding="utf-8") as outfile:
             outfile.write(self.preamble())
@@ -644,42 +670,153 @@ class ModelManager(object):
         """
         )
 
-    def scan_models_directory(self):
+    def scan_models_directory(
+        self,
+        base_model: Optional[BaseModelType] = None,
+        model_type: Optional[ModelType] = None,
+    ):
+
         loaded_files = set()
         new_models_found = False
 
-        for model_key, model_config in list(self.models.items()):
-            model_name, base_model, model_type = self.parse_key(model_key)
-            model_path = str(self.globals.root / model_config.path)
-            if not os.path.exists(model_path):
-                model_class = MODEL_CLASSES[base_model][model_type]
-                if model_class.save_to_config:
-                    model_config.error = ModelError.NotFound
+        self.logger.info(f'scanning {self.app_config.models_path} for new models')
+        with Chdir(self.app_config.root_path):
+            for model_key, model_config in list(self.models.items()):
+                model_name, cur_base_model, cur_model_type = self.parse_key(model_key)
+                model_path = self.app_config.root_path.absolute() / model_config.path
+                if not model_path.exists():
+                    model_class = MODEL_CLASSES[cur_base_model][cur_model_type]
+                    if model_class.save_to_config:
+                        model_config.error = ModelError.NotFound
+                        self.models.pop(model_key, None)
+                    else:
+                        self.models.pop(model_key, None)
                 else:
-                    self.models.pop(model_key, None)
-            else:
-                loaded_files.add(model_path)
+                    loaded_files.add(model_path)
 
-        for base_model in BaseModelType:
-            for model_type in ModelType:
-                model_class = MODEL_CLASSES[base_model][model_type]
-                models_dir = os.path.join(self.globals.models_path, base_model, model_type)
+            for cur_base_model in BaseModelType:
+                if base_model is not None and cur_base_model != base_model:
+                    continue
 
-                if not os.path.exists(models_dir):
-                    continue # TODO: or create all folders?
-                
-                for entry_name in os.listdir(models_dir):
-                    model_path = os.path.join(models_dir, entry_name)
-                    if model_path not in loaded_files: # TODO: check
-                        model_name = Path(model_path).stem
-                        model_key = self.create_key(model_name, base_model, model_type)
+                for cur_model_type in ModelType:
+                    if model_type is not None and cur_model_type != model_type:
+                        continue
+                    model_class = MODEL_CLASSES[cur_base_model][cur_model_type]
+                    models_dir = self.app_config.models_path / cur_base_model.value / cur_model_type.value
 
-                        if model_key in self.models:
-                            raise Exception(f"Model with key {model_key} added twice")
+                    if not models_dir.exists():
+                        continue # TODO: or create all folders?
 
-                        model_config: ModelConfigBase = model_class.probe_config(model_path)
-                        self.models[model_key] = model_config
-                        new_models_found = True
+                    for model_path in models_dir.iterdir():
+                        if model_path not in loaded_files: # TODO: check
+                            model_name = model_path.name if model_path.is_dir() else model_path.stem
+                            model_key = self.create_key(model_name, cur_base_model, cur_model_type)
 
-        if new_models_found:
+                            if model_key in self.models:
+                                raise Exception(f"Model with key {model_key} added twice")
+
+                            if model_path.is_relative_to(self.app_config.root_path):
+                                model_path = model_path.relative_to(self.app_config.root_path)
+                                try:
+                                    model_config: ModelConfigBase = model_class.probe_config(str(model_path))
+                                    self.models[model_key] = model_config
+                                    new_models_found = True
+                                except NotImplementedError as e:
+                                    self.logger.warning(e)
+
+        imported_models = self.autoimport()
+
+        if (new_models_found or imported_models) and self.config_path:
             self.commit()
+
+    def autoimport(self)->set[Path]:
+        '''
+        Scan the autoimport directory (if defined) and import new models, delete defunct models.
+        '''
+        # avoid circular import
+        from invokeai.backend.install.model_install_backend import ModelInstall
+        from invokeai.frontend.install.model_install import ask_user_for_prediction_type
+        
+        installer = ModelInstall(config = self.app_config,
+                                 model_manager = self,
+                                 prediction_type_helper = ask_user_for_prediction_type,
+                                 )
+        
+        installed = set()
+        scanned_dirs = set()
+        
+        config = self.app_config
+        known_paths = {(self.app_config.root_path / x['path']) for x in self.list_models()}
+
+        for autodir in [config.autoimport_dir,
+                        config.lora_dir,
+                        config.embedding_dir,
+                        config.controlnet_dir]:
+            if autodir is None:
+                continue
+
+            self.logger.info(f'Scanning {autodir} for models to import')
+        
+            autodir = self.app_config.root_path / autodir
+            if not autodir.exists():
+                continue
+
+            items_scanned = 0
+            new_models_found = set()
+            
+            for root, dirs, files in os.walk(autodir):
+                items_scanned += len(dirs) + len(files)
+                for d in dirs:
+                    path = Path(root) / d
+                    if path in known_paths or path.parent in scanned_dirs:
+                        scanned_dirs.add(path)
+                        continue
+                    if any([(path/x).exists() for x in {'config.json','model_index.json','learned_embeds.bin'}]):
+                        new_models_found.update(installer.heuristic_install(path))
+                        scanned_dirs.add(path)
+
+                for f in files:
+                    path = Path(root) / f
+                    if path in known_paths or path.parent in scanned_dirs:
+                        continue
+                    if path.suffix in {'.ckpt','.bin','.pth','.safetensors','.pt'}:
+                        new_models_found.update(installer.heuristic_install(path))
+
+            self.logger.info(f'Scanned {items_scanned} files and directories, imported {len(new_models_found)} models')
+            installed.update(new_models_found)
+
+        return installed
+
+    def heuristic_import(self,
+                         items_to_import: Set[str],
+                         prediction_type_helper: Callable[[Path],SchedulerPredictionType]=None,
+                         )->Set[str]:
+        '''Import a list of paths, repo_ids or URLs. Returns the set of
+        successfully imported items.
+        :param items_to_import: Set of strings corresponding to models to be imported.
+        :param prediction_type_helper: A callback that receives the Path of a Stable Diffusion 2 checkpoint model and returns a SchedulerPredictionType.
+
+        The prediction type helper is necessary to distinguish between
+        models based on Stable Diffusion 2 Base (requiring
+        SchedulerPredictionType.Epsilson) and Stable Diffusion 768
+        (requiring SchedulerPredictionType.VPrediction). It is
+        generally impossible to do this programmatically, so the
+        prediction_type_helper usually asks the user to choose.
+
+        '''
+        # avoid circular import here
+        from invokeai.backend.install.model_install_backend import ModelInstall
+        successfully_installed = set()
+        
+        installer = ModelInstall(config = self.app_config,
+                                 prediction_type_helper = prediction_type_helper,
+                                 model_manager = self)
+        for thing in items_to_import:
+            try:
+                installed = installer.heuristic_install(thing)
+                successfully_installed.update(installed)
+            except Exception as e:
+                self.logger.warning(f'{thing} could not be imported: {str(e)}')
+                
+        self.commit()                
+        return successfully_installed

invokeai/backend/model_management/model_probe.py

@@ -1,27 +1,28 @@
 import json
-import traceback
 import torch
 import safetensors.torch
 
 from dataclasses import dataclass
-from enum import Enum
 
-from diffusers import ModelMixin, ConfigMixin, StableDiffusionPipeline, AutoencoderKL, ControlNetModel
+from diffusers import ModelMixin, ConfigMixin
 from pathlib import Path
 from typing import Callable, Literal, Union, Dict
 from picklescan.scanner import scan_file_path
 
-import invokeai.backend.util.logging as logger
-from .models import BaseModelType, ModelType, ModelVariantType, SchedulerPredictionType, SilenceWarnings
+from .models import (
+    BaseModelType, ModelType, ModelVariantType,
+    SchedulerPredictionType, SilenceWarnings,
+)
+from .models.base import read_checkpoint_meta
 
 @dataclass
-class ModelVariantInfo(object):
+class ModelProbeInfo(object):
     model_type: ModelType
     base_type: BaseModelType
     variant_type: ModelVariantType
     prediction_type: SchedulerPredictionType
     upcast_attention: bool
-    format: Literal['folder','checkpoint']
+    format: Literal['diffusers','checkpoint', 'lycoris']
     image_size: int
 
 class ProbeBase(object):
@@ -31,19 +32,19 @@ class ProbeBase(object):
 class ModelProbe(object):
     
     PROBES = {
-        'folder': { },
+        'diffusers': { },
         'checkpoint': { },
     }
 
     CLASS2TYPE = {
-        'StableDiffusionPipeline' : ModelType.Pipeline,
+        'StableDiffusionPipeline' : ModelType.Main,
         'AutoencoderKL' : ModelType.Vae,
         'ControlNetModel' : ModelType.ControlNet,
     }
     
     @classmethod
     def register_probe(cls,
-                       format: Literal['folder','file'],
+                       format: Literal['diffusers','checkpoint'],
                        model_type: ModelType,
                        probe_class: ProbeBase):
         cls.PROBES[format][model_type] = probe_class
@@ -51,8 +52,8 @@ class ModelProbe(object):
     @classmethod
     def heuristic_probe(cls,
                         model: Union[Dict, ModelMixin, Path],
-                        prediction_type_helper: Callable[[Path],BaseModelType]=None,
-                        )->ModelVariantInfo:
+                        prediction_type_helper: Callable[[Path],SchedulerPredictionType]=None,
+                        )->ModelProbeInfo:
         if isinstance(model,Path):
             return cls.probe(model_path=model,prediction_type_helper=prediction_type_helper)
         elif isinstance(model,(dict,ModelMixin,ConfigMixin)):
@@ -64,7 +65,7 @@ class ModelProbe(object):
     def probe(cls,
               model_path: Path,
               model: Union[Dict, ModelMixin] = None,
-              prediction_type_helper: Callable[[Path],BaseModelType] = None)->ModelVariantInfo:
+              prediction_type_helper: Callable[[Path],SchedulerPredictionType] = None)->ModelProbeInfo:
         '''
         Probe the model at model_path and return sufficient information about it
         to place it somewhere in the models directory hierarchy. If the model is
@@ -74,23 +75,24 @@ class ModelProbe(object):
         between V2-Base and V2-768 SD models.
         '''
         if model_path:
-            format = 'folder' if model_path.is_dir() else 'checkpoint'
+            format_type = 'diffusers' if model_path.is_dir() else 'checkpoint'
         else:
-            format = 'folder' if isinstance(model,(ConfigMixin,ModelMixin)) else 'checkpoint'
+            format_type = 'diffusers' if isinstance(model,(ConfigMixin,ModelMixin)) else 'checkpoint'
 
         model_info = None
         try:
             model_type = cls.get_model_type_from_folder(model_path, model) \
-                if format == 'folder' \
+                if format_type == 'diffusers' \
                    else cls.get_model_type_from_checkpoint(model_path, model)
-            probe_class = cls.PROBES[format].get(model_type)
+            probe_class = cls.PROBES[format_type].get(model_type)
             if not probe_class:
                 return None
             probe = probe_class(model_path, model, prediction_type_helper)
             base_type = probe.get_base_type()
             variant_type = probe.get_variant_type()
             prediction_type = probe.get_scheduler_prediction_type()
-            model_info = ModelVariantInfo(
+            format = probe.get_format()
+            model_info = ModelProbeInfo(
                 model_type = model_type,
                 base_type = base_type,
                 variant_type = variant_type,
@@ -102,32 +104,40 @@ class ModelProbe(object):
                                      and prediction_type==SchedulerPredictionType.VPrediction \
                                      ) else 512,
             )
-        except Exception as e:
+        except Exception:
             return None
 
         return model_info
 
     @classmethod
-    def get_model_type_from_checkpoint(cls, model_path: Path, checkpoint: dict)->ModelType:
-        if model_path.suffix not in ('.bin','.pt','.ckpt','.safetensors'):
+    def get_model_type_from_checkpoint(cls, model_path: Path, checkpoint: dict) -> ModelType:
+        if model_path.suffix not in ('.bin','.pt','.ckpt','.safetensors','.pth'):
             return None
-        if model_path.name=='learned_embeds.bin':
+
+        if model_path.name == "learned_embeds.bin":
             return ModelType.TextualInversion
-        checkpoint = checkpoint or cls._scan_and_load_checkpoint(model_path)
-        state_dict = checkpoint.get("state_dict") or checkpoint
-        if any([x.startswith("model.diffusion_model") for x in state_dict.keys()]):
-            return ModelType.Pipeline
-        if any([x.startswith("encoder.conv_in") for x in state_dict.keys()]):
-            return ModelType.Vae
-        if "string_to_token" in state_dict or "emb_params" in state_dict:
-            return ModelType.TextualInversion
-        if any([x.startswith("lora") for x in state_dict.keys()]):
-            return ModelType.Lora
-        if any([x.startswith("control_model") for x in state_dict.keys()]):
-            return ModelType.ControlNet
-        if any([x.startswith("input_blocks") for x in state_dict.keys()]):
-            return ModelType.ControlNet
-        return None # give up
+
+        ckpt = checkpoint if checkpoint else read_checkpoint_meta(model_path, scan=True)
+        ckpt = ckpt.get("state_dict", ckpt)
+
+        for key in ckpt.keys():
+            if any(key.startswith(v) for v in {"cond_stage_model.", "first_stage_model.", "model.diffusion_model."}):
+                return ModelType.Main
+            elif any(key.startswith(v) for v in {"encoder.conv_in", "decoder.conv_in"}):
+                return ModelType.Vae
+            elif any(key.startswith(v) for v in {"lora_te_", "lora_unet_"}):
+                return ModelType.Lora
+            elif any(key.startswith(v) for v in {"control_model", "input_blocks"}):
+                return ModelType.ControlNet
+            elif key in {"emb_params", "string_to_param"}:
+                return ModelType.TextualInversion
+
+        else:
+            # diffusers-ti
+            if len(ckpt) < 10 and all(isinstance(v, torch.Tensor) for v in ckpt.values()):
+                return ModelType.TextualInversion
+        
+        raise ValueError("Unable to determine model type")
 
     @classmethod
     def get_model_type_from_folder(cls, folder_path: Path, model: ModelMixin)->ModelType:
@@ -192,11 +202,14 @@ class ProbeBase(object):
     def get_scheduler_prediction_type(self)->SchedulerPredictionType:
         pass
 
+    def get_format(self)->str:
+        pass
+
 class CheckpointProbeBase(ProbeBase):
     def __init__(self,
                  checkpoint_path: Path,
                  checkpoint: dict,
-                 helper: Callable[[Path],BaseModelType] = None
+                 helper: Callable[[Path],SchedulerPredictionType] = None
                  )->BaseModelType:
         self.checkpoint = checkpoint or ModelProbe._scan_and_load_checkpoint(checkpoint_path)
         self.checkpoint_path = checkpoint_path
@@ -205,9 +218,12 @@ class CheckpointProbeBase(ProbeBase):
     def get_base_type(self)->BaseModelType:
         pass
 
+    def get_format(self)->str:
+        return 'checkpoint'
+
     def get_variant_type(self)-> ModelVariantType:
         model_type = ModelProbe.get_model_type_from_checkpoint(self.checkpoint_path,self.checkpoint)
-        if model_type != ModelType.Pipeline:
+        if model_type != ModelType.Main:
             return ModelVariantType.Normal
         state_dict = self.checkpoint.get('state_dict') or self.checkpoint
         in_channels = state_dict[
@@ -246,7 +262,8 @@ class PipelineCheckpointProbe(CheckpointProbeBase):
                     return SchedulerPredictionType.Epsilon
                 elif checkpoint["global_step"] == 110000:
                     return SchedulerPredictionType.VPrediction
-            if self.checkpoint_path and self.helper:
+            if self.checkpoint_path and self.helper \
+               and not self.checkpoint_path.with_suffix('.yaml').exists():  # if a .yaml config file exists, then this step not needed
                 return self.helper(self.checkpoint_path)
             else:
                 return None
@@ -257,6 +274,9 @@ class VaeCheckpointProbe(CheckpointProbeBase):
         return BaseModelType.StableDiffusion1
 
 class LoRACheckpointProbe(CheckpointProbeBase):
+    def get_format(self)->str:
+        return 'lycoris'
+
     def get_base_type(self)->BaseModelType:
         checkpoint = self.checkpoint
         key1 = "lora_te_text_model_encoder_layers_0_mlp_fc1.lora_down.weight"
@@ -276,6 +296,9 @@ class LoRACheckpointProbe(CheckpointProbeBase):
             return None
 
 class TextualInversionCheckpointProbe(CheckpointProbeBase):
+    def get_format(self)->str:
+        return None
+
     def get_base_type(self)->BaseModelType:
         checkpoint = self.checkpoint
         if 'string_to_token' in checkpoint:
@@ -322,17 +345,16 @@ class FolderProbeBase(ProbeBase):
     def get_variant_type(self)->ModelVariantType:
         return ModelVariantType.Normal
 
+    def get_format(self)->str:
+        return 'diffusers'
+    
 class PipelineFolderProbe(FolderProbeBase):
     def get_base_type(self)->BaseModelType:
         if self.model:
             unet_conf = self.model.unet.config
-            scheduler_conf = self.model.scheduler.config
         else:
             with open(self.folder_path / 'unet' / 'config.json','r') as file:
                 unet_conf = json.load(file)
-            with open(self.folder_path / 'scheduler' / 'scheduler_config.json','r') as file:
-                scheduler_conf = json.load(file)
-            
         if unet_conf['cross_attention_dim'] == 768:
             return BaseModelType.StableDiffusion1  
         elif unet_conf['cross_attention_dim'] == 1024:
@@ -381,6 +403,9 @@ class VaeFolderProbe(FolderProbeBase):
         return BaseModelType.StableDiffusion1
 
 class TextualInversionFolderProbe(FolderProbeBase):
+    def get_format(self)->str:
+        return None
+    
     def get_base_type(self)->BaseModelType:
         path = self.folder_path / 'learned_embeds.bin'
         if not path.exists():
@@ -401,16 +426,24 @@ class ControlNetFolderProbe(FolderProbeBase):
                else BaseModelType.StableDiffusion2
 
 class LoRAFolderProbe(FolderProbeBase):
-    # I've never seen one of these in the wild, so this is a noop
-    pass
+    def get_base_type(self)->BaseModelType:
+        model_file = None
+        for suffix in ['safetensors','bin']:
+            base_file = self.folder_path / f'pytorch_lora_weights.{suffix}'
+            if base_file.exists():
+                model_file = base_file
+                break
+        if not model_file:
+            raise Exception('Unknown LoRA format encountered')
+        return LoRACheckpointProbe(model_file,None).get_base_type()
 
 ############## register probe classes ######
-ModelProbe.register_probe('folder', ModelType.Pipeline,  PipelineFolderProbe)
-ModelProbe.register_probe('folder', ModelType.Vae, VaeFolderProbe)
-ModelProbe.register_probe('folder', ModelType.Lora, LoRAFolderProbe)
-ModelProbe.register_probe('folder', ModelType.TextualInversion, TextualInversionFolderProbe)
-ModelProbe.register_probe('folder', ModelType.ControlNet, ControlNetFolderProbe)
-ModelProbe.register_probe('checkpoint', ModelType.Pipeline, PipelineCheckpointProbe)
+ModelProbe.register_probe('diffusers', ModelType.Main,  PipelineFolderProbe)
+ModelProbe.register_probe('diffusers', ModelType.Vae, VaeFolderProbe)
+ModelProbe.register_probe('diffusers', ModelType.Lora, LoRAFolderProbe)
+ModelProbe.register_probe('diffusers', ModelType.TextualInversion, TextualInversionFolderProbe)
+ModelProbe.register_probe('diffusers', ModelType.ControlNet, ControlNetFolderProbe)
+ModelProbe.register_probe('checkpoint', ModelType.Main, PipelineCheckpointProbe)
 ModelProbe.register_probe('checkpoint', ModelType.Vae, VaeCheckpointProbe)
 ModelProbe.register_probe('checkpoint', ModelType.Lora, LoRACheckpointProbe)
 ModelProbe.register_probe('checkpoint', ModelType.TextualInversion, TextualInversionCheckpointProbe)

invokeai/backend/model_management/models/__init__.py

@@ -11,21 +11,21 @@ from .textual_inversion import TextualInversionModel
 
 MODEL_CLASSES = {
     BaseModelType.StableDiffusion1: {
-        ModelType.Pipeline: StableDiffusion1Model,
+        ModelType.Main: StableDiffusion1Model,
         ModelType.Vae: VaeModel,
         ModelType.Lora: LoRAModel,
         ModelType.ControlNet: ControlNetModel,
         ModelType.TextualInversion: TextualInversionModel,
     },
     BaseModelType.StableDiffusion2: {
-        ModelType.Pipeline: StableDiffusion2Model,
+        ModelType.Main: StableDiffusion2Model,
         ModelType.Vae: VaeModel,
         ModelType.Lora: LoRAModel,
         ModelType.ControlNet: ControlNetModel,
         ModelType.TextualInversion: TextualInversionModel,
     },
     #BaseModelType.Kandinsky2_1: {
-    #    ModelType.Pipeline: Kandinsky2_1Model,
+    #    ModelType.Main: Kandinsky2_1Model,
     #    ModelType.MoVQ: MoVQModel,
     #    ModelType.Lora: LoRAModel,
     #    ModelType.ControlNet: ControlNetModel,

invokeai/backend/model_management/models/base.py

@@ -1,9 +1,12 @@
+import json
 import os
 import sys
 import typing
 import inspect
 from enum import Enum
 from abc import ABCMeta, abstractmethod
+from pathlib import Path
+from picklescan.scanner import scan_file_path
 import torch
 import safetensors.torch
 from diffusers import DiffusionPipeline, ConfigMixin
@@ -18,7 +21,7 @@ class BaseModelType(str, Enum):
     #Kandinsky2_1 = "kandinsky-2.1"
 
 class ModelType(str, Enum):
-    Pipeline = "pipeline"
+    Main = "main"
     Vae = "vae"
     Lora = "lora"
     ControlNet = "controlnet" # used by model_probe
@@ -56,7 +59,6 @@ class ModelConfigBase(BaseModel):
     class Config:
         use_enum_values = True
 
-
 class EmptyConfigLoader(ConfigMixin):
     @classmethod
     def load_config(cls, *args, **kwargs):
@@ -124,7 +126,10 @@ class ModelBase(metaclass=ABCMeta):
             if not isinstance(value, type) or not issubclass(value, ModelConfigBase):
                 continue
 
-            fields = inspect.get_annotations(value)
+            if hasattr(inspect,'get_annotations'):
+                fields = inspect.get_annotations(value)
+            else:
+                fields = value.__annotations__
             try:
                 field = fields["model_format"]
             except:
@@ -383,15 +388,18 @@ def _fast_safetensors_reader(path: str):
 
     return checkpoint
 
-
-def read_checkpoint_meta(path: str):
-    if path.endswith(".safetensors"):
+def read_checkpoint_meta(path: Union[str, Path], scan: bool = False):
+    if str(path).endswith(".safetensors"):
         try:
             checkpoint = _fast_safetensors_reader(path)
         except:
             # TODO: create issue for support "meta"?
             checkpoint = safetensors.torch.load_file(path, device="cpu")
     else:
+        if scan:
+            scan_result = scan_file_path(path)
+            if scan_result.infected_files != 0:
+                raise Exception(f"The model file \"{path}\" is potentially infected by malware. Aborting import.")
         checkpoint = torch.load(path, map_location=torch.device("meta"))
     return checkpoint
 

invokeai/backend/model_management/models/stable_diffusion.py

@@ -34,17 +34,17 @@ class StableDiffusion1Model(DiffusersModel):
     class CheckpointConfig(ModelConfigBase):
         model_format: Literal[StableDiffusion1ModelFormat.Checkpoint]
         vae: Optional[str] = Field(None)
-        config: Optional[str] = Field(None)
+        config: str
         variant: ModelVariantType
 
 
     def __init__(self, model_path: str, base_model: BaseModelType, model_type: ModelType):
         assert base_model == BaseModelType.StableDiffusion1
-        assert model_type == ModelType.Pipeline
+        assert model_type == ModelType.Main
         super().__init__(
             model_path=model_path,
             base_model=BaseModelType.StableDiffusion1,
-            model_type=ModelType.Pipeline,
+            model_type=ModelType.Main,
         )
 
     @classmethod
@@ -69,7 +69,7 @@ class StableDiffusion1Model(DiffusersModel):
                 in_channels = unet_config['in_channels']
 
             else:
-                raise Exception("Not supported stable diffusion diffusers format(possibly onnx?)")
+                raise NotImplementedError(f"{path} is not a supported stable diffusion diffusers format")
 
         else:
             raise NotImplementedError(f"Unknown stable diffusion 1.* format: {model_format}")
@@ -81,6 +81,8 @@ class StableDiffusion1Model(DiffusersModel):
         else:
             raise Exception("Unkown stable diffusion 1.* model format")
 
+        if ckpt_config_path is None:
+            ckpt_config_path = _select_ckpt_config(BaseModelType.StableDiffusion1, variant)
 
         return cls.create_config(
             path=path,
@@ -109,14 +111,12 @@ class StableDiffusion1Model(DiffusersModel):
         config: ModelConfigBase,
         base_model: BaseModelType,
     ) -> str:
-        assert model_path == config.path
-
         if isinstance(config, cls.CheckpointConfig):
             return _convert_ckpt_and_cache(
                 version=BaseModelType.StableDiffusion1,
                 model_config=config,
                 output_path=output_path,
-            ) # TODO: args
+            )
         else:
             return model_path
 
@@ -131,25 +131,20 @@ class StableDiffusion2Model(DiffusersModel):
         model_format: Literal[StableDiffusion2ModelFormat.Diffusers]
         vae: Optional[str] = Field(None)
         variant: ModelVariantType
-        prediction_type: SchedulerPredictionType
-        upcast_attention: bool
 
     class CheckpointConfig(ModelConfigBase):
         model_format: Literal[StableDiffusion2ModelFormat.Checkpoint]
         vae: Optional[str] = Field(None)
-        config: Optional[str] = Field(None)
+        config: str
         variant: ModelVariantType
-        prediction_type: SchedulerPredictionType
-        upcast_attention: bool
-
 
     def __init__(self, model_path: str, base_model: BaseModelType, model_type: ModelType):
         assert base_model == BaseModelType.StableDiffusion2
-        assert model_type == ModelType.Pipeline
+        assert model_type == ModelType.Main
         super().__init__(
             model_path=model_path,
             base_model=BaseModelType.StableDiffusion2,
-            model_type=ModelType.Pipeline,
+            model_type=ModelType.Main,
         )
 
     @classmethod
@@ -188,13 +183,8 @@ class StableDiffusion2Model(DiffusersModel):
         else:
             raise Exception("Unkown stable diffusion 2.* model format")
 
-        if variant == ModelVariantType.Normal:
-            prediction_type = SchedulerPredictionType.VPrediction
-            upcast_attention = True
-
-        else:
-            prediction_type = SchedulerPredictionType.Epsilon
-            upcast_attention = False
+        if ckpt_config_path is None:
+            ckpt_config_path = _select_ckpt_config(BaseModelType.StableDiffusion2, variant)
 
         return cls.create_config(
             path=path,
@@ -202,8 +192,6 @@ class StableDiffusion2Model(DiffusersModel):
 
             config=ckpt_config_path,
             variant=variant,
-            prediction_type=prediction_type,
-            upcast_attention=upcast_attention,
         )
 
     @classproperty
@@ -225,14 +213,12 @@ class StableDiffusion2Model(DiffusersModel):
         config: ModelConfigBase,
         base_model: BaseModelType,
     ) -> str:
-        assert model_path == config.path
-
         if isinstance(config, cls.CheckpointConfig):
             return _convert_ckpt_and_cache(
                 version=BaseModelType.StableDiffusion2,
                 model_config=config,
                 output_path=output_path,
-            ) # TODO: args
+            )
         else:
             return model_path
 
@@ -243,18 +229,18 @@ def _select_ckpt_config(version: BaseModelType, variant: ModelVariantType):
             ModelVariantType.Inpaint: "v1-inpainting-inference.yaml",
         },
         BaseModelType.StableDiffusion2: {
-            # code further will manually set upcast_attention and v_prediction
-            ModelVariantType.Normal: "v2-inference.yaml",
+            ModelVariantType.Normal: "v2-inference-v.yaml", # best guess, as we can't differentiate with base(512)
             ModelVariantType.Inpaint: "v2-inpainting-inference.yaml",
             ModelVariantType.Depth: "v2-midas-inference.yaml",
         }
     }
 
+    app_config = InvokeAIAppConfig.get_config()
     try:
-        # TODO: path
-        #model_config.config = app_config.config_dir / "stable-diffusion" / ckpt_configs[version][model_config.variant]
-        #return InvokeAIAppConfig.get_config().legacy_conf_dir / ckpt_configs[version][variant]
-        return InvokeAIAppConfig.get_config().root_dir / "configs" / "stable-diffusion" / ckpt_configs[version][variant]
+        config_path = app_config.legacy_conf_path / ckpt_configs[version][variant]
+        if config_path.is_relative_to(app_config.root_path):
+            config_path = config_path.relative_to(app_config.root_path)
+        return str(config_path)
             
     except:
         return None
@@ -273,36 +259,14 @@ def _convert_ckpt_and_cache(
     """
     app_config = InvokeAIAppConfig.get_config()
 
-    if model_config.config is None:
-        model_config.config = _select_ckpt_config(version, model_config.variant)
-        if model_config.config is None:
-            raise Exception(f"Model variant {model_config.variant} not supported for {version}")
-
-
-    weights = app_config.root_dir / model_config.path
-    config_file = app_config.root_dir / model_config.config
+    weights = app_config.root_path / model_config.path
+    config_file = app_config.root_path / model_config.config
     output_path = Path(output_path)
 
-    if version == BaseModelType.StableDiffusion1:
-        upcast_attention = False
-        prediction_type = SchedulerPredictionType.Epsilon
-
-    elif version == BaseModelType.StableDiffusion2:
-        upcast_attention = model_config.upcast_attention
-        prediction_type = model_config.prediction_type
-
-    else:
-        raise Exception(f"Unknown model provided: {version}")
-
-
     # return cached version if it exists
     if output_path.exists():
         return output_path
 
-    # TODO: I think that it more correctly to convert with embedded vae
-    #       as if user will delete custom vae he will got not embedded but also custom vae
-    #vae_ckpt_path, vae_model = self._get_vae_for_conversion(weights, mconfig)
-
     # to avoid circular import errors
     from ..convert_ckpt_to_diffusers import convert_ckpt_to_diffusers
     with SilenceWarnings():        
@@ -313,9 +277,6 @@ def _convert_ckpt_and_cache(
             model_variant=model_config.variant,
             original_config_file=config_file,
             extract_ema=True,
-            upcast_attention=upcast_attention,
-            prediction_type=prediction_type,
             scan_needed=True,
-            model_root=app_config.models_path,
         )
     return output_path

invokeai/backend/model_management/models/vae.py

@@ -137,7 +137,6 @@ def _convert_vae_ckpt_and_cache(
         from .stable_diffusion import _select_ckpt_config
         # all sd models use same vae settings
         config_file = _select_ckpt_config(base_model, ModelVariantType.Normal)
-
     else:
         raise Exception(f"Vae conversion not supported for model type: {base_model}")
 
@@ -152,13 +151,12 @@ def _convert_vae_ckpt_and_cache(
     if "state_dict" in checkpoint:
         checkpoint = checkpoint["state_dict"]
 
-    config = OmegaConf.load(config_file)
+    config = OmegaConf.load(app_config.root_path/config_file)
 
     vae_model = convert_ldm_vae_to_diffusers(
         checkpoint = checkpoint,
         vae_config = config,
         image_size = image_size,
-        model_root = app_config.models_path,
     )
     vae_model.save_pretrained(
         output_path,

invokeai/backend/stable_diffusion/diffusers_pipeline.py

@@ -215,10 +215,12 @@ class GeneratorToCallbackinator(Generic[ParamType, ReturnType, CallbackType]):
 @dataclass
 class ControlNetData:
     model: ControlNetModel = Field(default=None)
-    image_tensor: torch.Tensor= Field(default=None)
-    weight: Union[float, List[float]]= Field(default=1.0)
+    image_tensor: torch.Tensor = Field(default=None)
+    weight: Union[float, List[float]] = Field(default=1.0)
     begin_step_percent: float = Field(default=0.0)
     end_step_percent: float = Field(default=1.0)
+    control_mode: str = Field(default="balanced")
+
 
 @dataclass(frozen=True)
 class ConditioningData:
@@ -599,48 +601,68 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
 
         # TODO: should this scaling happen here or inside self._unet_forward?
         #     i.e. before or after passing it to InvokeAIDiffuserComponent
-        latent_model_input = self.scheduler.scale_model_input(latents, timestep)
+        unet_latent_input = self.scheduler.scale_model_input(latents, timestep)
 
         # default is no controlnet, so set controlnet processing output to None
         down_block_res_samples, mid_block_res_sample = None, None
 
         if control_data is not None:
-            # FIXME: make sure guidance_scale < 1.0 is handled correctly if doing per-step guidance setting
-            # if conditioning_data.guidance_scale > 1.0:
-            if conditioning_data.guidance_scale is not None:
-                # expand the latents input to control model if doing classifier free guidance
-                #    (which I think for now is always true, there is conditional elsewhere that stops execution if
-                #     classifier_free_guidance is <= 1.0 ?)
-                latent_control_input = torch.cat([latent_model_input] * 2)
-            else:
-                latent_control_input = latent_model_input
             # control_data should be type List[ControlNetData]
             # this loop covers both ControlNet (one ControlNetData in list)
             #      and MultiControlNet (multiple ControlNetData in list)
             for i, control_datum in enumerate(control_data):
-                # print("controlnet", i, "==>", type(control_datum))
+                control_mode = control_datum.control_mode
+                # soft_injection and cfg_injection are the two ControlNet control_mode booleans
+                #     that are combined at higher level to make control_mode enum
+                #  soft_injection determines whether to do per-layer re-weighting adjustment (if True)
+                #     or default weighting (if False)
+                soft_injection = (control_mode == "more_prompt" or control_mode == "more_control")
+                #  cfg_injection = determines whether to apply ControlNet to only the conditional (if True)
+                #      or the default both conditional and unconditional (if False)
+                cfg_injection = (control_mode == "more_control" or control_mode == "unbalanced")
+
                 first_control_step = math.floor(control_datum.begin_step_percent * total_step_count)
                 last_control_step = math.ceil(control_datum.end_step_percent * total_step_count)
                 # only apply controlnet if current step is within the controlnet's begin/end step range
                 if step_index >= first_control_step and step_index <= last_control_step:
-                    # print("running controlnet", i, "for step", step_index)
+
+                    if cfg_injection:
+                        control_latent_input = unet_latent_input
+                    else:
+                        # expand the latents input to control model if doing classifier free guidance
+                        #    (which I think for now is always true, there is conditional elsewhere that stops execution if
+                        #     classifier_free_guidance is <= 1.0 ?)
+                        control_latent_input = torch.cat([unet_latent_input] * 2)
+
+                    if cfg_injection:  # only applying ControlNet to conditional instead of in unconditioned
+                        encoder_hidden_states = torch.cat([conditioning_data.unconditioned_embeddings])
+                    else:
+                        encoder_hidden_states = torch.cat([conditioning_data.unconditioned_embeddings,
+                                                           conditioning_data.text_embeddings])
                     if isinstance(control_datum.weight, list):
                         # if controlnet has multiple weights, use the weight for the current step
                         controlnet_weight = control_datum.weight[step_index]
                     else:
                         # if controlnet has a single weight, use it for all steps
                         controlnet_weight = control_datum.weight
+
+                    # controlnet(s) inference
                     down_samples, mid_sample = control_datum.model(
-                        sample=latent_control_input,
+                        sample=control_latent_input,
                         timestep=timestep,
-                        encoder_hidden_states=torch.cat([conditioning_data.unconditioned_embeddings,
-                                                         conditioning_data.text_embeddings]),
+                        encoder_hidden_states=encoder_hidden_states,
                         controlnet_cond=control_datum.image_tensor,
-                        conditioning_scale=controlnet_weight,
-                        # cross_attention_kwargs,
-                        guess_mode=False,
+                        conditioning_scale=controlnet_weight, # controlnet specific, NOT the guidance scale
+                        guess_mode=soft_injection, # this is still called guess_mode in diffusers ControlNetModel
                         return_dict=False,
                     )
+                    if cfg_injection:
+                        # Inferred ControlNet only for the conditional batch.
+                        # To apply the output of ControlNet to both the unconditional and conditional batches,
+                        #   add 0 to the unconditional batch to keep it unchanged.
+                        down_samples = [torch.cat([torch.zeros_like(d), d]) for d in down_samples]
+                        mid_sample = torch.cat([torch.zeros_like(mid_sample), mid_sample])
+
                     if down_block_res_samples is None and mid_block_res_sample is None:
                         down_block_res_samples, mid_block_res_sample = down_samples, mid_sample
                     else:
@@ -653,11 +675,11 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
 
         # predict the noise residual
         noise_pred = self.invokeai_diffuser.do_diffusion_step(
-            latent_model_input,
-            t,
-            conditioning_data.unconditioned_embeddings,
-            conditioning_data.text_embeddings,
-            conditioning_data.guidance_scale,
+            x=unet_latent_input,
+            sigma=t,
+            unconditioning=conditioning_data.unconditioned_embeddings,
+            conditioning=conditioning_data.text_embeddings,
+            unconditional_guidance_scale=conditioning_data.guidance_scale,
             step_index=step_index,
             total_step_count=total_step_count,
             down_block_additional_residuals=down_block_res_samples,  # from controlnet(s)
@@ -962,6 +984,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         device="cuda",
         dtype=torch.float16,
         do_classifier_free_guidance=True,
+        control_mode="balanced"
     ):
 
         if not isinstance(image, torch.Tensor):
@@ -992,6 +1015,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
             repeat_by = num_images_per_prompt
         image = image.repeat_interleave(repeat_by, dim=0)
         image = image.to(device=device, dtype=dtype)
-        if do_classifier_free_guidance:
+        cfg_injection = (control_mode == "more_control" or control_mode == "unbalanced")
+        if do_classifier_free_guidance and not cfg_injection:
             image = torch.cat([image] * 2)
         return image

invokeai/backend/util/__init__.py

@@ -16,6 +16,7 @@ from .util import (
     download_with_resume,
     instantiate_from_config,
     url_attachment_name,
+    Chdir
 )
 
 

invokeai/backend/util/util.py

@@ -381,3 +381,18 @@ def image_to_dataURL(image: Image.Image, image_format: str = "PNG") -> str:
         buffered.getvalue()
     ).decode("UTF-8")
     return image_base64
+
+class Chdir(object):
+    '''Context manager to chdir to desired directory and change back after context exits:
+    Args:
+        path (Path): The path to the cwd
+    '''
+    def __init__(self, path: Path):
+        self.path = path
+        self.original = Path().absolute()
+
+    def __enter__(self):
+        os.chdir(self.path)
+
+    def __exit__(self,*args):
+        os.chdir(self.original)

invokeai/configs/INITIAL_MODELS.yaml

@@ -1,107 +1,92 @@
 # This file predefines a few models that the user may want to install.
-diffusers:
-   stable-diffusion-1.5:
-      description: Stable Diffusion version 1.5 diffusers model (4.27 GB)
-      repo_id: runwayml/stable-diffusion-v1-5
-      format: diffusers
-      vae:
-        repo_id: stabilityai/sd-vae-ft-mse
-      recommended: True
-      default: True
-   sd-inpainting-1.5:
-     description: RunwayML SD 1.5 model optimized for inpainting, diffusers version (4.27 GB)
-     repo_id: runwayml/stable-diffusion-inpainting
-     format: diffusers
-     vae:
-       repo_id: stabilityai/sd-vae-ft-mse
-     recommended: True
-   stable-diffusion-2.1:
-      description: Stable Diffusion version 2.1 diffusers model, trained on 768 pixel images (5.21 GB)
-      repo_id: stabilityai/stable-diffusion-2-1
-      format: diffusers
-      recommended: True
-   sd-inpainting-2.0:
-      description: Stable Diffusion version 2.0 inpainting model (5.21 GB)
-      repo_id: stabilityai/stable-diffusion-2-inpainting
-      format: diffusers
-      recommended: False
-   analog-diffusion-1.0:
-      description: An SD-1.5 model trained on diverse analog photographs (2.13 GB)
-      repo_id: wavymulder/Analog-Diffusion
-      format: diffusers
-      recommended: false
-   deliberate-1.0:
-      description: Versatile model that produces detailed images up to 768px (4.27 GB)
-      format: diffusers
-      repo_id: XpucT/Deliberate
-      recommended: False
-   d&d-diffusion-1.0:
-      description: Dungeons & Dragons characters (2.13 GB)
-      format: diffusers
-      repo_id: 0xJustin/Dungeons-and-Diffusion
-      recommended: False
-   dreamlike-photoreal-2.0:
-      description: A photorealistic model trained on 768 pixel images based on SD 1.5 (2.13 GB)
-      format: diffusers
-      repo_id: dreamlike-art/dreamlike-photoreal-2.0
-      recommended: False
-   inkpunk-1.0:
-      description: Stylized illustrations inspired by Gorillaz, FLCL and Shinkawa; prompt with "nvinkpunk" (4.27 GB)
-      format: diffusers
-      repo_id: Envvi/Inkpunk-Diffusion
-      recommended: False
-   openjourney-4.0:
-      description: An SD 1.5 model fine tuned on Midjourney; prompt with "mdjrny-v4 style" (2.13 GB)
-      format: diffusers
-      repo_id: prompthero/openjourney
-      vae:
-        repo_id: stabilityai/sd-vae-ft-mse
-      recommended: False
-   portrait-plus-1.0:
-      description: An SD-1.5 model trained on close range portraits of people; prompt with "portrait+" (2.13 GB)
-      format: diffusers
-      repo_id: wavymulder/portraitplus
-      recommended: False
-   seek-art-mega-1.0:
-      description: A general use SD-1.5 "anything" model that supports multiple styles (2.1 GB)
-      repo_id: coreco/seek.art_MEGA
-      format: diffusers
-      vae:
-        repo_id: stabilityai/sd-vae-ft-mse
-      recommended: False
-   trinart-2.0:
-      description: An SD-1.5 model finetuned with ~40K assorted high resolution manga/anime-style images (2.13 GB)
-      repo_id: naclbit/trinart_stable_diffusion_v2
-      format: diffusers
-      vae:
-        repo_id: stabilityai/sd-vae-ft-mse
-      recommended: False
-   waifu-diffusion-1.4:
-      description: An SD-1.5 model trained on 680k anime/manga-style images (2.13 GB)
-      repo_id: hakurei/waifu-diffusion
-      format: diffusers
-      vae:
-        repo_id: stabilityai/sd-vae-ft-mse
-      recommended: False
-controlnet:
-   canny: lllyasviel/control_v11p_sd15_canny
-   inpaint: lllyasviel/control_v11p_sd15_inpaint
-   mlsd: lllyasviel/control_v11p_sd15_mlsd
-   depth: lllyasviel/control_v11f1p_sd15_depth
-   normal_bae: lllyasviel/control_v11p_sd15_normalbae
-   seg: lllyasviel/control_v11p_sd15_seg
-   lineart: lllyasviel/control_v11p_sd15_lineart
-   lineart_anime: lllyasviel/control_v11p_sd15s2_lineart_anime
-   scribble: lllyasviel/control_v11p_sd15_scribble
-   softedge: lllyasviel/control_v11p_sd15_softedge
-   shuffle: lllyasviel/control_v11e_sd15_shuffle
-   tile: lllyasviel/control_v11f1e_sd15_tile
-   ip2p: lllyasviel/control_v11e_sd15_ip2p
-textual_inversion:
-   'EasyNegative': https://huggingface.co/embed/EasyNegative/resolve/main/EasyNegative.safetensors
-   'ahx-beta-453407d': sd-concepts-library/ahx-beta-453407d
-lora:
-   'LowRA': https://civitai.com/api/download/models/63006
-   'Ink scenery': https://civitai.com/api/download/models/83390
-   'sd-model-finetuned-lora-t4': sayakpaul/sd-model-finetuned-lora-t4
- 
+sd-1/main/stable-diffusion-v1-5:
+   description: Stable Diffusion version 1.5 diffusers model (4.27 GB)
+   repo_id: runwayml/stable-diffusion-v1-5
+   recommended: True
+   default: True
+sd-1/main/stable-diffusion-inpainting:
+   description: RunwayML SD 1.5 model optimized for inpainting, diffusers version (4.27 GB)
+   repo_id: runwayml/stable-diffusion-inpainting
+   recommended: True
+sd-2/main/stable-diffusion-2-1:
+   description: Stable Diffusion version 2.1 diffusers model, trained on 768 pixel images (5.21 GB)
+   repo_id: stabilityai/stable-diffusion-2-1
+   recommended: True
+sd-2/main/stable-diffusion-2-inpainting:
+   description: Stable Diffusion version 2.0 inpainting model (5.21 GB)
+   repo_id: stabilityai/stable-diffusion-2-inpainting
+   recommended: False
+sd-1/main/Analog-Diffusion:
+   description: An SD-1.5 model trained on diverse analog photographs (2.13 GB)
+   repo_id: wavymulder/Analog-Diffusion
+   recommended: false
+sd-1/main/Deliberate:
+   description: Versatile model that produces detailed images up to 768px (4.27 GB)
+   repo_id: XpucT/Deliberate
+   recommended: False
+sd-1/main/Dungeons-and-Diffusion:
+   description: Dungeons & Dragons characters (2.13 GB)
+   repo_id: 0xJustin/Dungeons-and-Diffusion
+   recommended: False
+sd-1/main/dreamlike-photoreal-2:
+   description: A photorealistic model trained on 768 pixel images based on SD 1.5 (2.13 GB)
+   repo_id: dreamlike-art/dreamlike-photoreal-2.0
+   recommended: False
+sd-1/main/Inkpunk-Diffusion:
+   description: Stylized illustrations inspired by Gorillaz, FLCL and Shinkawa; prompt with "nvinkpunk" (4.27 GB)
+   repo_id: Envvi/Inkpunk-Diffusion
+   recommended: False
+sd-1/main/openjourney:
+   description: An SD 1.5 model fine tuned on Midjourney; prompt with "mdjrny-v4 style" (2.13 GB)
+   repo_id: prompthero/openjourney
+   recommended: False
+sd-1/main/portraitplus:
+   description: An SD-1.5 model trained on close range portraits of people; prompt with "portrait+" (2.13 GB)
+   repo_id: wavymulder/portraitplus
+   recommended: False
+sd-1/main/seek.art_MEGA:
+   repo_id: coreco/seek.art_MEGA
+   description: A general use SD-1.5 "anything" model that supports multiple styles (2.1 GB)
+   recommended: False
+sd-1/main/trinart_stable_diffusion_v2:
+   description: An SD-1.5 model finetuned with ~40K assorted high resolution manga/anime-style images (2.13 GB)
+   repo_id: naclbit/trinart_stable_diffusion_v2
+   recommended: False
+sd-1/main/waifu-diffusion:
+   description: An SD-1.5 model trained on 680k anime/manga-style images (2.13 GB)
+   repo_id: hakurei/waifu-diffusion
+   recommended: False
+sd-1/controlnet/canny:
+   repo_id: lllyasviel/control_v11p_sd15_canny
+sd-1/controlnet/inpaint:
+   repo_id: lllyasviel/control_v11p_sd15_inpaint
+sd-1/controlnet/mlsd:
+   repo_id: lllyasviel/control_v11p_sd15_mlsd
+sd-1/controlnet/depth:
+   repo_id: lllyasviel/control_v11f1p_sd15_depth
+sd-1/controlnet/normal_bae:
+   repo_id: lllyasviel/control_v11p_sd15_normalbae
+sd-1/controlnet/seg:
+   repo_id: lllyasviel/control_v11p_sd15_seg
+sd-1/controlnet/lineart:
+   repo_id: lllyasviel/control_v11p_sd15_lineart
+sd-1/controlnet/lineart_anime:
+   repo_id: lllyasviel/control_v11p_sd15s2_lineart_anime
+sd-1/controlnet/scribble:
+   repo_id: lllyasviel/control_v11p_sd15_scribble
+sd-1/controlnet/softedge:
+   repo_id: lllyasviel/control_v11p_sd15_softedge
+sd-1/controlnet/shuffle:
+   repo_id: lllyasviel/control_v11e_sd15_shuffle
+sd-1/controlnet/tile:
+   repo_id: lllyasviel/control_v11f1e_sd15_tile
+sd-1/controlnet/ip2p:
+   repo_id: lllyasviel/control_v11e_sd15_ip2p
+sd-1/embedding/EasyNegative:
+   path: https://huggingface.co/embed/EasyNegative/resolve/main/EasyNegative.safetensors
+sd-1/embedding/ahx-beta-453407d:
+   repo_id: sd-concepts-library/ahx-beta-453407d
+sd-1/lora/LowRA:
+   path: https://civitai.com/api/download/models/63006
+sd-1/lora/Ink scenery:
+   path: https://civitai.com/api/download/models/83390

invokeai/configs/stable-diffusion/v2-inpainting-inference-v.yaml

@@ -0,0 +1,159 @@
+model:
+  base_learning_rate: 5.0e-05
+  target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    parameterization: "v"
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false
+    conditioning_key: hybrid
+    scale_factor: 0.18215
+    monitor: val/loss_simple_ema
+    finetune_keys: null
+    use_ema: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_checkpoint: True
+        image_size: 32 # unused
+        in_channels: 9
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_head_channels: 64 # need to fix for flash-attn
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: 1
+        context_dim: 1024
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          #attn_type: "vanilla-xformers"
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+            - 1
+            - 2
+            - 4
+            - 4
+          num_res_blocks: 2
+          attn_resolutions: [ ]
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
+      params:
+        freeze: True
+        layer: "penultimate"
+
+
+data:
+  target: ldm.data.laion.WebDataModuleFromConfig
+  params:
+    tar_base: null  # for concat as in LAION-A
+    p_unsafe_threshold: 0.1
+    filter_word_list: "data/filters.yaml"
+    max_pwatermark: 0.45
+    batch_size: 8
+    num_workers: 6
+    multinode: True
+    min_size: 512
+    train:
+      shards:
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-0/{00000..18699}.tar -"
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-1/{00000..18699}.tar -"
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-2/{00000..18699}.tar -"
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-3/{00000..18699}.tar -"
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-4/{00000..18699}.tar -"  #{00000-94333}.tar"
+      shuffle: 10000
+      image_key: jpg
+      image_transforms:
+      - target: torchvision.transforms.Resize
+        params:
+          size: 512
+          interpolation: 3
+      - target: torchvision.transforms.RandomCrop
+        params:
+          size: 512
+      postprocess:
+        target: ldm.data.laion.AddMask
+        params:
+          mode: "512train-large"
+          p_drop: 0.25
+    # NOTE use enough shards to avoid empty validation loops in workers
+    validation:
+      shards:
+        - "pipe:aws s3 cp s3://deep-floyd-s3/datasets/laion_cleaned-part5/{93001..94333}.tar - "
+      shuffle: 0
+      image_key: jpg
+      image_transforms:
+      - target: torchvision.transforms.Resize
+        params:
+          size: 512
+          interpolation: 3
+      - target: torchvision.transforms.CenterCrop
+        params:
+          size: 512
+      postprocess:
+        target: ldm.data.laion.AddMask
+        params:
+          mode: "512train-large"
+          p_drop: 0.25
+
+lightning:
+  find_unused_parameters: True
+  modelcheckpoint:
+    params:
+      every_n_train_steps: 5000
+
+  callbacks:
+    metrics_over_trainsteps_checkpoint:
+      params:
+        every_n_train_steps: 10000
+
+    image_logger:
+      target: main.ImageLogger
+      params:
+        enable_autocast: False
+        disabled: False
+        batch_frequency: 1000
+        max_images: 4
+        increase_log_steps: False
+        log_first_step: False
+        log_images_kwargs:
+          use_ema_scope: False
+          inpaint: False
+          plot_progressive_rows: False
+          plot_diffusion_rows: False
+          N: 4
+          unconditional_guidance_scale: 5.0
+          unconditional_guidance_label: [""]
+          ddim_steps: 50  # todo check these out for depth2img,
+          ddim_eta: 0.0   # todo check these out for depth2img,
+
+  trainer:
+    benchmark: True
+    val_check_interval: 5000000
+    num_sanity_val_steps: 0
+    accumulate_grad_batches: 1

invokeai/configs/stable-diffusion/v2-inpainting-inference.yaml

@@ -0,0 +1,158 @@
+model:
+  base_learning_rate: 5.0e-05
+  target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false
+    conditioning_key: hybrid
+    scale_factor: 0.18215
+    monitor: val/loss_simple_ema
+    finetune_keys: null
+    use_ema: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_checkpoint: True
+        image_size: 32 # unused
+        in_channels: 9
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_head_channels: 64 # need to fix for flash-attn
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: 1
+        context_dim: 1024
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          #attn_type: "vanilla-xformers"
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+            - 1
+            - 2
+            - 4
+            - 4
+          num_res_blocks: 2
+          attn_resolutions: [ ]
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
+      params:
+        freeze: True
+        layer: "penultimate"
+
+
+data:
+  target: ldm.data.laion.WebDataModuleFromConfig
+  params:
+    tar_base: null  # for concat as in LAION-A
+    p_unsafe_threshold: 0.1
+    filter_word_list: "data/filters.yaml"
+    max_pwatermark: 0.45
+    batch_size: 8
+    num_workers: 6
+    multinode: True
+    min_size: 512
+    train:
+      shards:
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-0/{00000..18699}.tar -"
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-1/{00000..18699}.tar -"
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-2/{00000..18699}.tar -"
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-3/{00000..18699}.tar -"
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-4/{00000..18699}.tar -"  #{00000-94333}.tar"
+      shuffle: 10000
+      image_key: jpg
+      image_transforms:
+      - target: torchvision.transforms.Resize
+        params:
+          size: 512
+          interpolation: 3
+      - target: torchvision.transforms.RandomCrop
+        params:
+          size: 512
+      postprocess:
+        target: ldm.data.laion.AddMask
+        params:
+          mode: "512train-large"
+          p_drop: 0.25
+    # NOTE use enough shards to avoid empty validation loops in workers
+    validation:
+      shards:
+        - "pipe:aws s3 cp s3://deep-floyd-s3/datasets/laion_cleaned-part5/{93001..94333}.tar - "
+      shuffle: 0
+      image_key: jpg
+      image_transforms:
+      - target: torchvision.transforms.Resize
+        params:
+          size: 512
+          interpolation: 3
+      - target: torchvision.transforms.CenterCrop
+        params:
+          size: 512
+      postprocess:
+        target: ldm.data.laion.AddMask
+        params:
+          mode: "512train-large"
+          p_drop: 0.25
+
+lightning:
+  find_unused_parameters: True
+  modelcheckpoint:
+    params:
+      every_n_train_steps: 5000
+
+  callbacks:
+    metrics_over_trainsteps_checkpoint:
+      params:
+        every_n_train_steps: 10000
+
+    image_logger:
+      target: main.ImageLogger
+      params:
+        enable_autocast: False
+        disabled: False
+        batch_frequency: 1000
+        max_images: 4
+        increase_log_steps: False
+        log_first_step: False
+        log_images_kwargs:
+          use_ema_scope: False
+          inpaint: False
+          plot_progressive_rows: False
+          plot_diffusion_rows: False
+          N: 4
+          unconditional_guidance_scale: 5.0
+          unconditional_guidance_label: [""]
+          ddim_steps: 50  # todo check these out for depth2img,
+          ddim_eta: 0.0   # todo check these out for depth2img,
+
+  trainer:
+    benchmark: True
+    val_check_interval: 5000000
+    num_sanity_val_steps: 0
+    accumulate_grad_batches: 1

invokeai/frontend/install/invokeai_update.py

@@ -108,11 +108,11 @@ def main():
 
     print(f':crossed_fingers: Upgrading to [yellow]{tag if tag else release}[/yellow]')
     if release:
-        cmd = f"pip install 'invokeai{extras} @ {INVOKE_AI_SRC}/{release}.zip' --use-pep517 --upgrade"
+        cmd = f'pip install "invokeai{extras} @ {INVOKE_AI_SRC}/{release}.zip" --use-pep517 --upgrade'
     elif tag:
-        cmd = f"pip install 'invokeai{extras} @ {INVOKE_AI_TAG}/{tag}.zip' --use-pep517 --upgrade"
+        cmd = f'pip install "invokeai{extras} @ {INVOKE_AI_TAG}/{tag}.zip" --use-pep517 --upgrade'
     else:
-        cmd = f"pip install 'invokeai{extras} @ {INVOKE_AI_BRANCH}/{branch}.zip' --use-pep517 --upgrade"
+        cmd = f'pip install "invokeai{extras} @ {INVOKE_AI_BRANCH}/{branch}.zip" --use-pep517 --upgrade'
     print('')
     print('')
     if os.system(cmd)==0:

invokeai/frontend/install/model_install.py

@@ -11,7 +11,6 @@ The work is actually done in backend code in model_install_backend.py.
 
 import argparse
 import curses
-import os
 import sys
 import textwrap
 import traceback
@@ -20,28 +19,22 @@ from multiprocessing import Process
 from multiprocessing.connection import Connection, Pipe
 from pathlib import Path
 from shutil import get_terminal_size
-from typing import List
 
 import logging
 import npyscreen
 import torch
 from npyscreen import widget
-from omegaconf import OmegaConf
 
 from invokeai.backend.util.logging import InvokeAILogger
 
 from invokeai.backend.install.model_install_backend import (
-    Dataset_path,
-    default_config_file,
-    default_dataset,
-    install_requested_models,
-    recommended_datasets,
     ModelInstallList,
-    UserSelections,
+    InstallSelections,
+    ModelInstall,
+    SchedulerPredictionType,
 )
-from invokeai.backend import ModelManager
+from invokeai.backend.model_management import ModelManager, ModelType
 from invokeai.backend.util import choose_precision, choose_torch_device
-from invokeai.backend.util.logging import InvokeAILogger
 from invokeai.frontend.install.widgets import (
     CenteredTitleText,
     MultiSelectColumns,
@@ -58,6 +51,7 @@ from invokeai.frontend.install.widgets import (
 from invokeai.app.services.config import InvokeAIAppConfig
 
 config = InvokeAIAppConfig.get_config()
+logger = InvokeAILogger.getLogger()
 
 # build a table mapping all non-printable characters to None
 # for stripping control characters
@@ -71,8 +65,8 @@ def make_printable(s:str)->str:
     return s.translate(NOPRINT_TRANS_TABLE)
 
 class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
-    # for responsive resizing - disabled
-    # FIX_MINIMUM_SIZE_WHEN_CREATED = False
+    # for responsive resizing set to False, but this seems to cause a crash!
+    FIX_MINIMUM_SIZE_WHEN_CREATED = True
     
     # for persistence
     current_tab = 0
@@ -90,25 +84,10 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
         if not config.model_conf_path.exists():
             with open(config.model_conf_path,'w') as file:
                 print('# InvokeAI model configuration file',file=file)
-        model_manager = ModelManager(config.model_conf_path)
-        
-        self.starter_models = OmegaConf.load(Dataset_path)['diffusers']
-        self.installed_diffusers_models = self.list_additional_diffusers_models(
-             model_manager,
-             self.starter_models,
-        )
-        self.installed_cn_models = model_manager.list_controlnet_models()
-        self.installed_lora_models = model_manager.list_lora_models()
-        self.installed_ti_models = model_manager.list_ti_models()
-
-        try:
-            self.existing_models = OmegaConf.load(default_config_file())
-        except:
-            self.existing_models = dict()
-            
-        self.starter_model_list = list(self.starter_models.keys())
-        self.installed_models = dict()
-
+        self.installer = ModelInstall(config)
+        self.all_models = self.installer.all_models()
+        self.starter_models = self.installer.starter_models()
+        self.model_labels = self._get_model_labels()        
         window_width, window_height = get_terminal_size()
 
         self.nextrely -= 1
@@ -141,39 +120,37 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
             scroll_exit = True,
         )
         self.tabs.on_changed = self._toggle_tables
-        
+
         top_of_table = self.nextrely
-        self.starter_diffusers_models = self.add_starter_diffusers()
+        self.starter_pipelines = self.add_starter_pipelines()
         bottom_of_table = self.nextrely
 
         self.nextrely = top_of_table
-        self.diffusers_models = self.add_diffusers_widgets(
-            predefined_models=self.installed_diffusers_models,
-            model_type='Diffusers',
+        self.pipeline_models = self.add_pipeline_widgets(
+            model_type=ModelType.Main,
             window_width=window_width,
+            exclude = self.starter_models
         )
+        # self.pipeline_models['autoload_pending'] = True
         bottom_of_table = max(bottom_of_table,self.nextrely)
 
         self.nextrely = top_of_table
         self.controlnet_models = self.add_model_widgets(
-            predefined_models=self.installed_cn_models,
-            model_type='ControlNet',
+            model_type=ModelType.ControlNet,
             window_width=window_width,
         )
         bottom_of_table = max(bottom_of_table,self.nextrely)
 
         self.nextrely = top_of_table
         self.lora_models = self.add_model_widgets(
-            predefined_models=self.installed_lora_models,
-            model_type="LoRA/LyCORIS",
+            model_type=ModelType.Lora,
             window_width=window_width,
         )
         bottom_of_table = max(bottom_of_table,self.nextrely)
 
         self.nextrely = top_of_table
         self.ti_models = self.add_model_widgets(
-            predefined_models=self.installed_ti_models,
-            model_type="Textual Inversion Embeddings",
+            model_type=ModelType.TextualInversion,
             window_width=window_width,
         )
         bottom_of_table = max(bottom_of_table,self.nextrely)
@@ -184,7 +161,7 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
             BufferBox,
             name='Log Messages',
             editable=False,
-            max_height = 16,
+            max_height = 10,
         )
         
         self.nextrely += 1
@@ -197,13 +174,14 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
                 rely=-3,
                 when_pressed_function=self.on_back,
             )
-        self.ok_button = self.add_widget_intelligent(
-            npyscreen.ButtonPress,
-            name=done_label,
-            relx=(window_width - len(done_label)) // 2,
-            rely=-3,
-            when_pressed_function=self.on_execute
-        )
+        else:
+            self.ok_button = self.add_widget_intelligent(
+                npyscreen.ButtonPress,
+                name=done_label,
+                relx=(window_width - len(done_label)) // 2,
+                rely=-3,
+                when_pressed_function=self.on_execute
+            )
 
         label = "APPLY CHANGES & EXIT"
         self.done = self.add_widget_intelligent(
@@ -220,18 +198,15 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
         self._toggle_tables([self.current_tab])
 
     ############# diffusers tab ##########        
-    def add_starter_diffusers(self)->dict[str, npyscreen.widget]:
+    def add_starter_pipelines(self)->dict[str, npyscreen.widget]:
         '''Add widgets responsible for selecting diffusers models'''
         widgets = dict()
-
-        starter_model_labels = self._get_starter_model_labels()
-        recommended_models = [
-            x
-            for x in self.starter_model_list
-            if self.starter_models[x].get("recommended", False)
-        ]
+        models = self.all_models
+        starters = self.starter_models
+        starter_model_labels = self.model_labels
+        
         self.installed_models = sorted(
-            [x for x in list(self.starter_models.keys()) if x in self.existing_models]
+            [x for x in starters if models[x].installed]
         )
 
         widgets.update(
@@ -246,55 +221,46 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
         self.nextrely -= 1
         # if user has already installed some initial models, then don't patronize them
         # by showing more recommendations
-        show_recommended = not self.existing_models
+        show_recommended = len(self.installed_models)==0
+        keys = [x for x in models.keys() if x in starters]
         widgets.update(
             models_selected = self.add_widget_intelligent(
                 MultiSelectColumns,
                 columns=1,
                 name="Install Starter Models",
-                values=starter_model_labels,
+                values=[starter_model_labels[x] for x in keys],
                 value=[
-                    self.starter_model_list.index(x)
-                    for x in self.starter_model_list
-                    if (show_recommended and x in recommended_models)\
-                    or (x in self.existing_models)
+                    keys.index(x)
+                    for x in keys
+                    if (show_recommended and models[x].recommended) \
+                    or (x in self.installed_models)
                 ],
-                max_height=len(starter_model_labels) + 1,
+                max_height=len(starters) + 1,
                 relx=4,
                 scroll_exit=True,
-            )
+            ),
+            models = keys,
         )
 
-        widgets.update(
-            purge_deleted = self.add_widget_intelligent(
-                npyscreen.Checkbox,
-                name="Purge unchecked diffusers models from disk",
-                value=False,
-                scroll_exit=True,
-                relx=4,
-            )
-        )
-        widgets['purge_deleted'].when_value_edited = lambda: self.sync_purge_buttons(widgets['purge_deleted'])
-        
         self.nextrely += 1
         return widgets
 
     ############# Add a set of model install widgets ########
     def add_model_widgets(self,
-                          predefined_models: dict[str,bool],
-                          model_type: str,
+                          model_type: ModelType,
                           window_width: int=120,
                           install_prompt: str=None,
-                          add_purge_deleted: bool=False,
+                          exclude: set=set(),
                           )->dict[str,npyscreen.widget]:
         '''Generic code to create model selection widgets'''
         widgets = dict()
-        model_list = sorted(predefined_models.keys())
+        model_list = [x for x in self.all_models if self.all_models[x].model_type==model_type and not x in exclude]
+        model_labels = [self.model_labels[x] for x in model_list]
         if len(model_list) > 0:
-            max_width = max([len(x) for x in model_list])
+            max_width = max([len(x) for x in model_labels])
             columns = window_width // (max_width+8)  # 8 characters for "[x] " and padding
             columns = min(len(model_list),columns) or 1
-            prompt = install_prompt or f"Select the desired {model_type} models to install. Unchecked models will be purged from disk."
+            prompt = install_prompt or f"Select the desired {model_type.value.title()} models to install. Unchecked models will be purged from disk."
 
             widgets.update(
                 label1 = self.add_widget_intelligent(
@@ -310,31 +276,19 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
                     MultiSelectColumns,
                     columns=columns,
                     name=f"Install {model_type} Models",
-                    values=model_list,
+                    values=model_labels,
                     value=[
                         model_list.index(x)
                         for x in model_list
-                        if predefined_models[x]
+                        if self.all_models[x].installed
                     ],
                     max_height=len(model_list)//columns + 1,
                     relx=4,
                     scroll_exit=True,
-                )
+                ),
+                models = model_list,
             )
 
-            if add_purge_deleted:
-                self.nextrely += 1
-                widgets.update(
-                    purge_deleted = self.add_widget_intelligent(
-                        npyscreen.Checkbox,
-                        name="Purge unchecked diffusers models from disk",
-                        value=False,
-                        scroll_exit=True,
-                        relx=4,
-                    )
-                )
-                widgets['purge_deleted'].when_value_edited = lambda: self.sync_purge_buttons(widgets['purge_deleted'])
-
         self.nextrely += 1
         widgets.update(
             download_ids = self.add_widget_intelligent(
@@ -348,63 +302,33 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
         return widgets
 
     ### Tab for arbitrary diffusers widgets ###
-    def add_diffusers_widgets(self,
-                              predefined_models: dict[str,bool],
-                              model_type: str='Diffusers',
-                              window_width: int=120,
-                              )->dict[str,npyscreen.widget]:
+    def add_pipeline_widgets(self,
+                             model_type: ModelType=ModelType.Main,
+                             window_width: int=120,
+                             **kwargs,
+                             )->dict[str,npyscreen.widget]:
         '''Similar to add_model_widgets() but adds some additional widgets at the bottom
         to support the autoload directory'''
         widgets = self.add_model_widgets(
-            predefined_models,
-            'Diffusers',
-            window_width,
-            install_prompt="Additional diffusers models already installed.",
-            add_purge_deleted=True
+            model_type = model_type,
+            window_width = window_width,
+            install_prompt=f"Additional {model_type.value.title()} models already installed.",
+            **kwargs,
         )
 
-        label = "Directory to scan for models to automatically import (<tab> autocompletes):"
-        self.nextrely += 1
-        widgets.update(
-            autoload_directory = self.add_widget_intelligent(
-                FileBox,
-                max_height=3,
-                name=label,
-                value=str(config.autoconvert_dir) if config.autoconvert_dir else None,
-                select_dir=True,
-                must_exist=True,
-                use_two_lines=False,
-                labelColor="DANGER",
-                begin_entry_at=len(label)+1,
-                scroll_exit=True,
-            )
-        )
-        widgets.update(
-            autoscan_on_startup = self.add_widget_intelligent(
-                npyscreen.Checkbox,
-                name="Scan and import from this directory each time InvokeAI starts",
-                value=config.autoconvert_dir is not None,
-                relx=4,
-                scroll_exit=True,
-            )
-        )
         return widgets
 
-    def sync_purge_buttons(self,checkbox):
-        value = checkbox.value
-        self.starter_diffusers_models['purge_deleted'].value = value
-        self.diffusers_models['purge_deleted'].value = value
-        
     def resize(self):
         super().resize()
-        if (s := self.starter_diffusers_models.get("models_selected")):
-            s.values = self._get_starter_model_labels()
+        if (s := self.starter_pipelines.get("models_selected")):
+            keys = [x for x in self.all_models.keys() if x in self.starter_models]
+            s.values = [self.model_labels[x] for x in keys]
 
     def _toggle_tables(self, value=None):
         selected_tab = value[0]
         widgets = [
-            self.starter_diffusers_models,
-            self.diffusers_models,
+            self.starter_pipelines,
+            self.pipeline_models,
             self.controlnet_models,
             self.lora_models,
             self.ti_models,
@@ -412,34 +336,38 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
 
         for group in widgets:
             for k,v in group.items():
-                v.hidden = True
-                v.editable = False
+                try:
+                    v.hidden = True
+                    v.editable = False
+                except:
+                    pass
         for k,v in widgets[selected_tab].items():
-            v.hidden = False
-            if not isinstance(v,(npyscreen.FixedText, npyscreen.TitleFixedText, CenteredTitleText)):
-                v.editable = True
+            try:
+                v.hidden = False
+                if not isinstance(v,(npyscreen.FixedText, npyscreen.TitleFixedText, CenteredTitleText)):
+                    v.editable = True
+            except:
+                pass
         self.__class__.current_tab = selected_tab  # for persistence
         self.display()
 
-    def _get_starter_model_labels(self) -> List[str]:
+    def _get_model_labels(self) -> dict[str,str]:
         window_width, window_height = get_terminal_size()
-        label_width = 25
         checkbox_width = 4
         spacing_width = 2
+        
+        models = self.all_models
+        label_width = max([len(models[x].name) for x in models])
         description_width = window_width - label_width - checkbox_width - spacing_width
-        im = self.starter_models
-        names = self.starter_model_list
-        descriptions = [
-            im[x].description[0 : description_width - 3] + "..."
-            if len(im[x].description) > description_width
-            else im[x].description
-            for x in names
-        ]
-        return [
-            f"%-{label_width}s %s" % (names[x], descriptions[x])
-            for x in range(0, len(names))
-        ]
 
+        result = dict()
+        for x in models.keys():
+            description = models[x].description
+            description = description[0 : description_width - 3] + "..." \
+                if description and len(description) > description_width \
+                   else description if description else ''
+            result[x] =  f"%-{label_width}s %s" % (models[x].name, description)
+        return result
             
     def _get_columns(self) -> int:
         window_width, window_height = get_terminal_size()
@@ -467,7 +395,7 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
             target = process_and_execute,
             kwargs=dict(
                 opt = app.program_opts,
-                selections = app.user_selections,
+                selections = app.install_selections,
                 conn_out = child_conn,
             )
         )
@@ -475,8 +403,8 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
         child_conn.close()
         self.subprocess_connection = parent_conn
         self.subprocess = p
-        app.user_selections = UserSelections()
-        # process_and_execute(app.opt, app.user_selections)
+        app.install_selections = InstallSelections()
+        # process_and_execute(app.opt, app.install_selections)
 
     def on_back(self):
         self.parentApp.switchFormPrevious()
@@ -492,7 +420,7 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
         self.parentApp.setNextForm(None)
         self.parentApp.user_cancelled = False
         self.editing = False
-
+        
     ########## This routine monitors the child process that is performing model installation and removal #####
     def while_waiting(self):
         '''Called during idle periods. Main task is to update the Log Messages box with messages
@@ -548,8 +476,8 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
         
         # rebuild the form, saving and restoring some of the fields that need to be preserved.
         saved_messages = self.monitor.entry_widget.values
-        autoload_dir = self.diffusers_models['autoload_directory'].value
-        autoscan = self.diffusers_models['autoscan_on_startup'].value
+        # autoload_dir = str(config.root_path / self.pipeline_models['autoload_directory'].value)
+        # autoscan = self.pipeline_models['autoscan_on_startup'].value
         
         app.main_form = app.addForm(
             "MAIN", addModelsForm, name="Install Stable Diffusion Models", multipage=self.multipage,
@@ -558,23 +486,8 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
         
         app.main_form.monitor.entry_widget.values = saved_messages
         app.main_form.monitor.entry_widget.buffer([''],scroll_end=True)
-        app.main_form.diffusers_models['autoload_directory'].value = autoload_dir
-        app.main_form.diffusers_models['autoscan_on_startup'].value = autoscan
-        
-    ###############################################################
-    
-    def list_additional_diffusers_models(self,
-                                         manager: ModelManager,
-                                         starters:dict
-                                         )->dict[str,bool]:
-        '''Return a dict of all the currently installed models that are not on the starter list'''
-        model_info = manager.list_models()
-        additional_models = {
-            x:True for x in model_info \
-            if model_info[x]['format']=='diffusers' \
-            and x not in starters
-        }
-        return additional_models
+        # app.main_form.pipeline_models['autoload_directory'].value = autoload_dir
+        # app.main_form.pipeline_models['autoscan_on_startup'].value = autoscan
         
     def marshall_arguments(self):
         """
@@ -586,89 +499,40 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
         .autoscan_on_startup:  True if invokeai should scan and import at startup time
         .import_model_paths:   list of URLs, repo_ids and file paths to import
         """
-        # we're using a global here rather than storing the result in the parentapp
-        # due to some bug in npyscreen that is causing attributes to be lost
-        selections = self.parentApp.user_selections
+        selections = self.parentApp.install_selections
+        all_models = self.all_models
 
-        # Starter models to install/remove
-        starter_models = dict(
-            map(
-                lambda x: (self.starter_model_list[x], True),
-                self.starter_diffusers_models['models_selected'].value,
-            )
-        )
-        selections.purge_deleted_models = self.starter_diffusers_models['purge_deleted'].value or \
-            self.diffusers_models['purge_deleted'].value
-        
-        selections.install_models = [x for x in starter_models if x not in self.existing_models]
-        selections.remove_models = [x for x in self.starter_model_list if x in self.existing_models and x not in starter_models]
+        # Defined models (in INITIAL_CONFIG.yaml or models.yaml) to add/remove
+        ui_sections = [self.starter_pipelines, self.pipeline_models,
+                       self.controlnet_models, self.lora_models, self.ti_models]
+        for section in ui_sections:
+            if not 'models_selected' in section:
+                continue
+            selected = set([section['models'][x] for x in section['models_selected'].value])
+            models_to_install = [x for x in selected if not self.all_models[x].installed]
+            models_to_remove = [x for x in section['models'] if x not in selected and self.all_models[x].installed]
+            selections.remove_models.extend(models_to_remove)
+            selections.install_models.extend(all_models[x].path or all_models[x].repo_id \
+                                             for x in models_to_install if all_models[x].path or all_models[x].repo_id)
 
-        # "More" models
-        selections.import_model_paths = self.diffusers_models['download_ids'].value.split()
-        if diffusers_selected := self.diffusers_models.get('models_selected'):
-            selections.remove_models.extend([x
-                                             for x in diffusers_selected.values
-                                             if self.installed_diffusers_models[x]
-                                             and diffusers_selected.values.index(x) not in diffusers_selected.value
-                                             ]
-                                            )
-                                        
-        # TODO: REFACTOR THIS REPETITIVE CODE
-        if cn_models_selected := self.controlnet_models.get('models_selected'):
-            selections.install_cn_models = [cn_models_selected.values[x]
-                                            for x in cn_models_selected.value
-                                            if not self.installed_cn_models[cn_models_selected.values[x]]
-                                            ]
-            selections.remove_cn_models = [x
-                                           for x in cn_models_selected.values
-                                           if self.installed_cn_models[x]
-                                           and cn_models_selected.values.index(x) not in cn_models_selected.value
-                                           ]
-        if (additional_cns := self.controlnet_models['download_ids'].value.split()):
-            valid_cns = [x for x in additional_cns if '/' in x]
-            selections.install_cn_models.extend(valid_cns)
+        # models located in the 'download_ids" section
+        for section in ui_sections:
+            if downloads := section.get('download_ids'):
+                selections.install_models.extend(downloads.value.split())
 
-        # same thing, for LoRAs
-        if loras_selected := self.lora_models.get('models_selected'):
-            selections.install_lora_models = [loras_selected.values[x]
-                                              for x in loras_selected.value
-                                              if not self.installed_lora_models[loras_selected.values[x]]
-                                              ]
-            selections.remove_lora_models = [x
-                                             for x in loras_selected.values
-                                             if self.installed_lora_models[x]
-                                             and loras_selected.values.index(x) not in loras_selected.value
-                                             ]
-        if (additional_loras := self.lora_models['download_ids'].value.split()):
-            selections.install_lora_models.extend(additional_loras)
-
-        # same thing, for TIs
-        # TODO: refactor
-        if tis_selected := self.ti_models.get('models_selected'):
-            selections.install_ti_models = [tis_selected.values[x]
-                                            for x in tis_selected.value
-                                            if not self.installed_ti_models[tis_selected.values[x]]
-                                            ]
-            selections.remove_ti_models = [x
-                                           for x in tis_selected.values
-                                           if self.installed_ti_models[x]
-                                           and tis_selected.values.index(x) not in tis_selected.value
-                                           ]
-                
-        if (additional_tis := self.ti_models['download_ids'].value.split()):
-            selections.install_ti_models.extend(additional_tis)
-            
         # load directory and whether to scan on startup
-        selections.scan_directory = self.diffusers_models['autoload_directory'].value
-        selections.autoscan_on_startup = self.diffusers_models['autoscan_on_startup'].value
-
+        # if self.parentApp.autoload_pending:
+        #     selections.scan_directory = str(config.root_path / self.pipeline_models['autoload_directory'].value)
+        #     self.parentApp.autoload_pending = False
+        # selections.autoscan_on_startup = self.pipeline_models['autoscan_on_startup'].value
 
 class AddModelApplication(npyscreen.NPSAppManaged):
     def __init__(self,opt):
         super().__init__()
         self.program_opts = opt
         self.user_cancelled = False
-        self.user_selections = UserSelections()
+        # self.autoload_pending = True
+        self.install_selections = InstallSelections()
 
     def onStart(self):
         npyscreen.setTheme(npyscreen.Themes.DefaultTheme)
@@ -687,26 +551,22 @@ class StderrToMessage():
         pass
 
 # --------------------------------------------------------
-def ask_user_for_config_file(model_path: Path,
-                             tui_conn: Connection=None
-                             )->Path:
+def ask_user_for_prediction_type(model_path: Path,
+                                 tui_conn: Connection=None
+                                 )->SchedulerPredictionType:
     if tui_conn:
         logger.debug('Waiting for user response...')
-        return _ask_user_for_cf_tui(model_path, tui_conn)        
+        return _ask_user_for_pt_tui(model_path, tui_conn)        
     else:
-        return _ask_user_for_cf_cmdline(model_path)
+        return _ask_user_for_pt_cmdline(model_path)
 
-def _ask_user_for_cf_cmdline(model_path):
-    choices = [
-        config.legacy_conf_path / x
-        for x in ['v2-inference.yaml','v2-inference-v.yaml']
-    ]
-    choices.extend([None])
+def _ask_user_for_pt_cmdline(model_path: Path)->SchedulerPredictionType:
+    choices = [SchedulerPredictionType.Epsilon, SchedulerPredictionType.VPrediction, None]
     print(
 f"""
 Please select the type of the V2 checkpoint named {model_path.name}:
-[1] A Stable Diffusion v2.x base model (512 pixels; there should be no 'parameterization:' line in its yaml file)
-[2] A Stable Diffusion v2.x v-predictive model (768 pixels; look for a 'parameterization: "v"' line in its yaml file)
+[1] A model based on Stable Diffusion v2 trained on 512 pixel images (SD-2-base)
+[2] A model based on Stable Diffusion v2 trained on 768 pixel images (SD-2-768)
 [3] Skip this model and come back later.
 """
         )
@@ -723,7 +583,7 @@ Please select the type of the V2 checkpoint named {model_path.name}:
             return
     return choice
         
-def _ask_user_for_cf_tui(model_path: Path, tui_conn: Connection)->Path:
+def _ask_user_for_pt_tui(model_path: Path, tui_conn: Connection)->SchedulerPredictionType:
     try:
         tui_conn.send_bytes(f'*need v2 config for:{model_path}'.encode('utf-8'))
         # note that we don't do any status checking here
@@ -731,20 +591,20 @@ def _ask_user_for_cf_tui(model_path: Path, tui_conn: Connection)->Path:
         if response is None:
             return None
         elif response == 'epsilon':
-            return config.legacy_conf_path / 'v2-inference.yaml'
+            return SchedulerPredictionType.epsilon
         elif response == 'v':
-            return config.legacy_conf_path  / 'v2-inference-v.yaml'
+            return SchedulerPredictionType.VPrediction
         elif response == 'abort':
             logger.info('Conversion aborted')
             return None
         else:
-            return Path(response)
+            return response
     except:
         return None
         
 # --------------------------------------------------------
 def process_and_execute(opt: Namespace,
-                        selections: UserSelections,
+                        selections: InstallSelections,
                         conn_out: Connection=None,
                         ):
     # set up so that stderr is sent to conn_out
@@ -755,34 +615,14 @@ def process_and_execute(opt: Namespace,
         logger = InvokeAILogger.getLogger()
         logger.handlers.clear()
         logger.addHandler(logging.StreamHandler(translator))
-    
-    models_to_install = selections.install_models
-    models_to_remove = selections.remove_models
-    directory_to_scan = selections.scan_directory
-    scan_at_startup = selections.autoscan_on_startup
-    potential_models_to_install = selections.import_model_paths
 
-    install_requested_models(
-        diffusers = ModelInstallList(models_to_install, models_to_remove),
-        controlnet = ModelInstallList(selections.install_cn_models, selections.remove_cn_models),
-        lora = ModelInstallList(selections.install_lora_models, selections.remove_lora_models),
-        ti = ModelInstallList(selections.install_ti_models, selections.remove_ti_models),
-        scan_directory=Path(directory_to_scan) if directory_to_scan else None,
-        external_models=potential_models_to_install,
-        scan_at_startup=scan_at_startup,
-        precision="float32"
-        if opt.full_precision
-        else choose_precision(torch.device(choose_torch_device())),
-        purge_deleted=selections.purge_deleted_models,
-        config_file_path=Path(opt.config_file) if opt.config_file else config.model_conf_path,
-        model_config_file_callback = lambda x: ask_user_for_config_file(x,conn_out)
-    )
+    installer = ModelInstall(config, prediction_type_helper=lambda x: ask_user_for_prediction_type(x,conn_out))
+    installer.install(selections)
 
     if conn_out:
         conn_out.send_bytes('*done*'.encode('utf-8'))
         conn_out.close()
 
-
 def do_listings(opt)->bool:
     """List installed models of various sorts, and return
     True if any were requested."""
@@ -813,39 +653,34 @@ def select_and_download_models(opt: Namespace):
         if opt.full_precision
         else choose_precision(torch.device(choose_torch_device()))
     )
-
-    if do_listings(opt):
-        pass
-    # this processes command line additions/removals
-    elif opt.diffusers or opt.controlnets or opt.textual_inversions or opt.loras:
-        action = 'remove_models' if opt.delete else 'install_models'
-        diffusers_args = {'diffusers':ModelInstallList(remove_models=opt.diffusers or [])} \
-                          if opt.delete \
-                          else {'external_models':opt.diffusers or []} 
-        install_requested_models(
-            **diffusers_args,
-            controlnet=ModelInstallList(**{action:opt.controlnets or []}),
-            ti=ModelInstallList(**{action:opt.textual_inversions or []}),
-            lora=ModelInstallList(**{action:opt.loras or []}),
-            precision=precision,
-            purge_deleted=True,
-            model_config_file_callback=lambda x: ask_user_for_config_file(x),
+    config.precision = precision
+    helper = lambda x: ask_user_for_prediction_type(x)
+    # if do_listings(opt):
+    # pass
+    
+    installer = ModelInstall(config, prediction_type_helper=helper)
+    if opt.add or opt.delete:
+        selections = InstallSelections(
+            install_models = opt.add or [],
+            remove_models = opt.delete or []
         )
+        installer.install(selections)
     elif opt.default_only:
-        install_requested_models(
-            diffusers=ModelInstallList(install_models=default_dataset()),
-            precision=precision,
+        selections = InstallSelections(
+            install_models = installer.default_model()
         )
+        installer.install(selections)
     elif opt.yes_to_all:
-        install_requested_models(
-            diffusers=ModelInstallList(install_models=recommended_datasets()),
-            precision=precision,
+        selections = InstallSelections(
+            install_models = installer.recommended_models()
         )
+        installer.install(selections)
 
     # this is where the TUI is called
     else:
         # needed because the torch library is loaded, even though we don't use it
-        torch.multiprocessing.set_start_method("spawn")
+        # currently commented out because it has started generating errors (?)
+        # torch.multiprocessing.set_start_method("spawn")
 
         # the third argument is needed in the Windows 11 environment in
         # order to launch and resize a console window running this program
@@ -861,35 +696,20 @@ def select_and_download_models(opt: Namespace):
                     installApp.main_form.subprocess.terminate()
                     installApp.main_form.subprocess = None
             raise e
-        process_and_execute(opt, installApp.user_selections)
+        process_and_execute(opt, installApp.install_selections)
 
 # -------------------------------------
 def main():
     parser = argparse.ArgumentParser(description="InvokeAI model downloader")
     parser.add_argument(
-        "--diffusers",
+        "--add",
         nargs="*",
-        help="List of URLs or repo_ids of diffusers to install/delete",
-    )
-    parser.add_argument(
-        "--loras",
-        nargs="*",
-        help="List of URLs or repo_ids of LoRA/LyCORIS models to install/delete",
-    )
-    parser.add_argument(
-        "--controlnets",
-        nargs="*",
-        help="List of URLs or repo_ids of controlnet models to install/delete",
-    )
-    parser.add_argument(
-        "--textual-inversions",
-        nargs="*",
-        help="List of URLs or repo_ids of textual inversion embeddings to install/delete",
+        help="List of URLs, local paths or repo_ids of models to install",
     )
     parser.add_argument(
         "--delete",
-        action="store_true",
-        help="Delete models listed on command line rather than installing them",
+        nargs="*",
+        help="List of names of models to idelete",
     )
     parser.add_argument(
         "--full-precision",
@@ -909,7 +729,7 @@ def main():
     parser.add_argument(
         "--default_only",
         action="store_true",
-        help="only install the default model",
+        help="Only install the default model",
     )
     parser.add_argument(
         "--list-models",
@@ -965,13 +785,15 @@ def main():
             logger.error(
                 "Insufficient vertical space for the interface. Please make your window taller and try again"
             )
-        elif str(e).startswith("addwstr"):
+        input('Press any key to continue...')
+    except Exception as e:
+        if str(e).startswith("addwstr"):
             logger.error(
                 "Insufficient horizontal space for the interface. Please make your window wider and try again."
             )
-    except Exception as e:
-        print(f'An exception has occurred: {str(e)} Details:')
-        print(traceback.format_exc(), file=sys.stderr)
+        else:
+            print(f'An exception has occurred: {str(e)} Details:')
+            print(traceback.format_exc(), file=sys.stderr)
         input('Press any key to continue...')
     
 

invokeai/frontend/install/widgets.py

@@ -17,8 +17,8 @@ from shutil import get_terminal_size
 from curses import BUTTON2_CLICKED,BUTTON3_CLICKED
 
 # minimum size for UIs
-MIN_COLS = 120
-MIN_LINES = 50
+MIN_COLS = 130
+MIN_LINES = 45
 
 # -------------------------------------
 def set_terminal_size(columns: int, lines: int, launch_command: str=None):
@@ -42,6 +42,18 @@ def set_terminal_size(columns: int, lines: int, launch_command: str=None):
     elif OS in ["Darwin", "Linux"]:
         _set_terminal_size_unix(width,height)
 
+    # check whether it worked....
+    ts = get_terminal_size()
+    pause = False
+    if ts.columns < columns:
+        print('\033[1mThis window is too narrow for the user interface. Please make it wider.\033[0m')
+        pause = True
+    if ts.lines < lines:
+        print('\033[1mThis window is too short for the user interface. Please make it taller.\033[0m')
+        pause = True
+    if pause:
+        input('Press any key to continue..')
+
 def _set_terminal_size_powershell(width: int, height: int):
     script=f'''
 $pshost = get-host
@@ -61,6 +73,12 @@ def _set_terminal_size_unix(width: int, height: int):
     import fcntl
     import termios
 
+    # These terminals accept the size command and report that the
+    # size changed, but they lie!!!
+    for bad_terminal in ['TERMINATOR_UUID', 'ALACRITTY_WINDOW_ID']:
+        if os.environ.get(bad_terminal):
+            return
+    
     winsize = struct.pack("HHHH", height, width, 0, 0)
     fcntl.ioctl(sys.stdout.fileno(), termios.TIOCSWINSZ, winsize)
     sys.stdout.write("\x1b[8;{height};{width}t".format(height=height, width=width))
@@ -75,6 +93,12 @@ def set_min_terminal_size(min_cols: int, min_lines: int, launch_command: str=Non
     lines = max(term_lines, min_lines)
     set_terminal_size(cols, lines, launch_command)
 
+    # did it work?
+    term_cols, term_lines = get_terminal_size()
+    if term_cols < cols or term_lines < lines:
+        print(f'This window is too small for optimal display. For best results please enlarge it.')
+        input('After resizing, press any key to continue...')
+
 class IntSlider(npyscreen.Slider):
     def translate_value(self):
         stri = "%2d / %2d" % (self.value, self.out_of)
@@ -378,13 +402,12 @@ def select_stable_diffusion_config_file(
         wrap:bool =True,
         model_name:str='Unknown',
 ):
-    message = "Please select the correct base model for the V2 checkpoint named {model_name}. Press <CANCEL> to skip installation."
+    message = f"Please select the correct base model for the V2 checkpoint named '{model_name}'. Press <CANCEL> to skip installation."
     title = "CONFIG FILE SELECTION"
     options=[
         "An SD v2.x base model (512 pixels; no 'parameterization:' line in its yaml file)",
         "An SD v2.x v-predictive model (768 pixels; 'parameterization: \"v\"' line in its yaml file)",
         "Skip installation for now and come back later",
-        "Enter config file path manually",
     ]
 
     F = ConfirmCancelPopup(
@@ -406,35 +429,17 @@ def select_stable_diffusion_config_file(
     mlw.values = message
 
     choice = F.add(
-        SingleSelectWithChanged,
+        npyscreen.SelectOne,
         values = options,
         value = [0],
         max_height = len(options)+1,
         scroll_exit=True,
     )
-    file = F.add(
-        FileBox,
-        name='Path to config file',
-        max_height=3,
-        hidden=True,
-        must_exist=True,
-        scroll_exit=True
-    )
-
-    def toggle_visible(value):
-        value = value[0]
-        if value==3:
-            file.hidden=False
-        else:
-            file.hidden=True
-        F.display()
-        
-    choice.on_changed = toggle_visible
 
     F.editw = 1
     F.edit()
     if not F.value:
         return None
-    assert choice.value[0] in range(0,4),'invalid choice'
-    choices = ['epsilon','v','abort',file.value]
+    assert choice.value[0] in range(0,3),'invalid choice'
+    choices = ['epsilon','v','abort']
     return choices[choice.value[0]]

invokeai/frontend/web/config/common.ts

@@ -0,0 +1,12 @@
+import react from '@vitejs/plugin-react-swc';
+import { visualizer } from 'rollup-plugin-visualizer';
+import { PluginOption, UserConfig } from 'vite';
+import eslint from 'vite-plugin-eslint';
+import tsconfigPaths from 'vite-tsconfig-paths';
+
+export const commonPlugins: UserConfig['plugins'] = [
+  react(),
+  eslint(),
+  tsconfigPaths(),
+  visualizer() as unknown as PluginOption,
+];

invokeai/frontend/web/config/vite.app.config.ts

@@ -1,17 +1,9 @@
-import react from '@vitejs/plugin-react-swc';
-import { visualizer } from 'rollup-plugin-visualizer';
-import { PluginOption, UserConfig } from 'vite';
-import eslint from 'vite-plugin-eslint';
-import tsconfigPaths from 'vite-tsconfig-paths';
+import { UserConfig } from 'vite';
+import { commonPlugins } from './common';
 
 export const appConfig: UserConfig = {
   base: './',
-  plugins: [
-    react(),
-    eslint(),
-    tsconfigPaths(),
-    visualizer() as unknown as PluginOption,
-  ],
+  plugins: [...commonPlugins],
   build: {
     chunkSizeWarningLimit: 1500,
   },

invokeai/frontend/web/config/vite.package.config.ts

@@ -1,19 +1,13 @@
-import react from '@vitejs/plugin-react-swc';
 import path from 'path';
-import { visualizer } from 'rollup-plugin-visualizer';
-import { PluginOption, UserConfig } from 'vite';
+import { UserConfig } from 'vite';
 import dts from 'vite-plugin-dts';
-import eslint from 'vite-plugin-eslint';
-import tsconfigPaths from 'vite-tsconfig-paths';
 import cssInjectedByJsPlugin from 'vite-plugin-css-injected-by-js';
+import { commonPlugins } from './common';
 
 export const packageConfig: UserConfig = {
   base: './',
   plugins: [
-    react(),
-    eslint(),
-    tsconfigPaths(),
-    visualizer() as unknown as PluginOption,
+    ...commonPlugins,
     dts({
       insertTypesEntry: true,
     }),

invokeai/frontend/web/dist/index.html

@@ -12,7 +12,7 @@
         margin: 0;
       }
     </style>
-    <script type="module" crossorigin src="./assets/index-8a3e9251.js"></script>
+    <script type="module" crossorigin src="./assets/index-4dfaefdd.js"></script>
   </head>
 
   <body dir="ltr">

invokeai/frontend/web/dist/locales/en.json

@@ -24,16 +24,13 @@
     },
     "common": {
         "hotkeysLabel": "Hotkeys",
-        "themeLabel": "Theme",
+        "darkMode": "Dark Mode",
+        "lightMode": "Light Mode",
         "languagePickerLabel": "Language",
         "reportBugLabel": "Report Bug",
         "githubLabel": "Github",
         "discordLabel": "Discord",
         "settingsLabel": "Settings",
-        "darkTheme": "Dark",
-        "lightTheme": "Light",
-        "greenTheme": "Green",
-        "oceanTheme": "Ocean",
         "langArabic": "العربية",
         "langEnglish": "English",
         "langDutch": "Nederlands",
@@ -524,7 +521,8 @@
         "initialImage": "Initial Image",
         "showOptionsPanel": "Show Options Panel",
         "hidePreview": "Hide Preview",
-        "showPreview": "Show Preview"
+        "showPreview": "Show Preview",
+        "controlNetControlMode": "Control Mode"
     },
     "settings": {
         "models": "Models",
@@ -547,7 +545,8 @@
         "general": "General",
         "generation": "Generation",
         "ui": "User Interface",
-        "availableSchedulers": "Available Schedulers"
+        "favoriteSchedulers": "Favorite Schedulers",
+        "favoriteSchedulersPlaceholder": "No schedulers favorited"
     },
     "toast": {
         "serverError": "Server Error",

invokeai/frontend/web/dist/locales/fi.json

@@ -0,0 +1,122 @@
+{
+    "accessibility": {
+        "reset": "Resetoi",
+        "useThisParameter": "Käytä tätä parametria",
+        "modelSelect": "Mallin Valinta",
+        "exitViewer": "Poistu katselimesta",
+        "uploadImage": "Lataa kuva",
+        "copyMetadataJson": "Kopioi metadata JSON:iin",
+        "invokeProgressBar": "Invoken edistymispalkki",
+        "nextImage": "Seuraava kuva",
+        "previousImage": "Edellinen kuva",
+        "zoomIn": "Lähennä",
+        "flipHorizontally": "Käännä vaakasuoraan",
+        "zoomOut": "Loitonna",
+        "rotateCounterClockwise": "Kierrä vastapäivään",
+        "rotateClockwise": "Kierrä myötäpäivään",
+        "flipVertically": "Käännä pystysuoraan",
+        "showGallery": "Näytä galleria",
+        "modifyConfig": "Muokkaa konfiguraatiota",
+        "toggleAutoscroll": "Kytke automaattinen vieritys",
+        "toggleLogViewer": "Kytke lokin katselutila",
+        "showOptionsPanel": "Näytä asetukset"
+    },
+    "common": {
+        "postProcessDesc2": "Erillinen käyttöliittymä tullaan julkaisemaan helpottaaksemme työnkulkua jälkikäsittelyssä.",
+        "training": "Kouluta",
+        "statusLoadingModel": "Ladataan mallia",
+        "statusModelChanged": "Malli vaihdettu",
+        "statusConvertingModel": "Muunnetaan mallia",
+        "statusModelConverted": "Malli muunnettu",
+        "langFrench": "Ranska",
+        "langItalian": "Italia",
+        "languagePickerLabel": "Kielen valinta",
+        "hotkeysLabel": "Pikanäppäimet",
+        "reportBugLabel": "Raportoi Bugista",
+        "langPolish": "Puola",
+        "themeLabel": "Teema",
+        "langDutch": "Hollanti",
+        "settingsLabel": "Asetukset",
+        "githubLabel": "Github",
+        "darkTheme": "Tumma",
+        "lightTheme": "Vaalea",
+        "greenTheme": "Vihreä",
+        "langGerman": "Saksa",
+        "langPortuguese": "Portugali",
+        "discordLabel": "Discord",
+        "langEnglish": "Englanti",
+        "oceanTheme": "Meren sininen",
+        "langRussian": "Venäjä",
+        "langUkranian": "Ukraina",
+        "langSpanish": "Espanja",
+        "upload": "Lataa",
+        "statusMergedModels": "Mallit yhdistelty",
+        "img2img": "Kuva kuvaksi",
+        "nodes": "Solmut",
+        "nodesDesc": "Solmupohjainen järjestelmä kuvien generoimiseen on parhaillaan kehitteillä. Pysy kuulolla päivityksistä tähän uskomattomaan ominaisuuteen liittyen.",
+        "postProcessDesc1": "Invoke AI tarjoaa monenlaisia jälkikäsittelyominaisuukisa. Kuvan laadun skaalaus sekä kasvojen korjaus ovat jo saatavilla WebUI:ssä. Voit ottaa ne käyttöön lisäasetusten valikosta teksti kuvaksi sekä kuva kuvaksi -välilehdiltä. Voit myös suoraan prosessoida kuvia käyttämällä kuvan toimintapainikkeita nykyisen kuvan yläpuolella tai tarkastelussa.",
+        "postprocessing": "Jälkikäsitellään",
+        "postProcessing": "Jälkikäsitellään",
+        "cancel": "Peruuta",
+        "close": "Sulje",
+        "accept": "Hyväksy",
+        "statusConnected": "Yhdistetty",
+        "statusError": "Virhe",
+        "statusProcessingComplete": "Prosessointi valmis",
+        "load": "Lataa",
+        "back": "Takaisin",
+        "statusGeneratingTextToImage": "Generoidaan tekstiä kuvaksi",
+        "trainingDesc2": "InvokeAI tukee jo mukautettujen upotusten kouluttamista tekstin inversiolla käyttäen pääskriptiä.",
+        "statusDisconnected": "Yhteys katkaistu",
+        "statusPreparing": "Valmistellaan",
+        "statusIterationComplete": "Iteraatio valmis",
+        "statusMergingModels": "Yhdistellään malleja",
+        "statusProcessingCanceled": "Valmistelu peruutettu",
+        "statusSavingImage": "Tallennetaan kuvaa",
+        "statusGeneratingImageToImage": "Generoidaan kuvaa kuvaksi",
+        "statusRestoringFacesGFPGAN": "Korjataan kasvoja (GFPGAN)",
+        "statusRestoringFacesCodeFormer": "Korjataan kasvoja (CodeFormer)",
+        "statusGeneratingInpainting": "Generoidaan sisällemaalausta",
+        "statusGeneratingOutpainting": "Generoidaan ulosmaalausta",
+        "statusRestoringFaces": "Korjataan kasvoja",
+        "pinOptionsPanel": "Kiinnitä asetukset -paneeli",
+        "loadingInvokeAI": "Ladataan Invoke AI:ta",
+        "loading": "Ladataan",
+        "statusGenerating": "Generoidaan",
+        "txt2img": "Teksti kuvaksi",
+        "trainingDesc1": "Erillinen työnkulku omien upotusten ja tarkastuspisteiden kouluttamiseksi käyttäen tekstin inversiota ja dreamboothia selaimen käyttöliittymässä.",
+        "postProcessDesc3": "Invoke AI:n komentorivi tarjoaa paljon muita ominaisuuksia, kuten esimerkiksi Embiggenin.",
+        "unifiedCanvas": "Yhdistetty kanvas",
+        "statusGenerationComplete": "Generointi valmis"
+    },
+    "gallery": {
+        "uploads": "Lataukset",
+        "showUploads": "Näytä lataukset",
+        "galleryImageResetSize": "Resetoi koko",
+        "maintainAspectRatio": "Säilytä kuvasuhde",
+        "galleryImageSize": "Kuvan koko",
+        "pinGallery": "Kiinnitä galleria",
+        "showGenerations": "Näytä generaatiot",
+        "singleColumnLayout": "Yhden sarakkeen asettelu",
+        "generations": "Generoinnit",
+        "gallerySettings": "Gallerian asetukset",
+        "autoSwitchNewImages": "Vaihda uusiin kuviin automaattisesti",
+        "allImagesLoaded": "Kaikki kuvat ladattu",
+        "noImagesInGallery": "Ei kuvia galleriassa",
+        "loadMore": "Lataa lisää"
+    },
+    "hotkeys": {
+        "keyboardShortcuts": "näppäimistön pikavalinnat",
+        "appHotkeys": "Sovelluksen pikanäppäimet",
+        "generalHotkeys": "Yleiset pikanäppäimet",
+        "galleryHotkeys": "Gallerian pikanäppäimet",
+        "unifiedCanvasHotkeys": "Yhdistetyn kanvaan pikanäppäimet",
+        "cancel": {
+            "desc": "Peruuta kuvan luominen",
+            "title": "Peruuta"
+        },
+        "invoke": {
+            "desc": "Luo kuva"
+        }
+    }
+}

invokeai/frontend/web/dist/locales/mn.json

@@ -0,0 +1 @@
+{}

invokeai/frontend/web/dist/locales/sv.json

@@ -0,0 +1,254 @@
+{
+    "accessibility": {
+        "copyMetadataJson": "Kopiera metadata JSON",
+        "zoomIn": "Zooma in",
+        "exitViewer": "Avslutningsvisare",
+        "modelSelect": "Välj modell",
+        "uploadImage": "Ladda upp bild",
+        "invokeProgressBar": "Invoke förloppsmätare",
+        "nextImage": "Nästa bild",
+        "toggleAutoscroll": "Växla automatisk rullning",
+        "flipHorizontally": "Vänd vågrätt",
+        "flipVertically": "Vänd lodrätt",
+        "zoomOut": "Zooma ut",
+        "toggleLogViewer": "Växla logvisare",
+        "reset": "Starta om",
+        "previousImage": "Föregående bild",
+        "useThisParameter": "Använd denna parametern",
+        "showGallery": "Visa galleri",
+        "rotateCounterClockwise": "Rotera moturs",
+        "rotateClockwise": "Rotera medurs",
+        "modifyConfig": "Ändra konfiguration",
+        "showOptionsPanel": "Visa inställningspanelen"
+    },
+    "common": {
+        "hotkeysLabel": "Snabbtangenter",
+        "reportBugLabel": "Rapportera bugg",
+        "githubLabel": "Github",
+        "discordLabel": "Discord",
+        "settingsLabel": "Inställningar",
+        "darkTheme": "Mörk",
+        "lightTheme": "Ljus",
+        "greenTheme": "Grön",
+        "oceanTheme": "Hav",
+        "langEnglish": "Engelska",
+        "langDutch": "Nederländska",
+        "langFrench": "Franska",
+        "langGerman": "Tyska",
+        "langItalian": "Italienska",
+        "langArabic": "العربية",
+        "langHebrew": "עברית",
+        "langPolish": "Polski",
+        "langPortuguese": "Português",
+        "langBrPortuguese": "Português do Brasil",
+        "langSimplifiedChinese": "简体中文",
+        "langJapanese": "日本語",
+        "langKorean": "한국어",
+        "langRussian": "Русский",
+        "unifiedCanvas": "Förenad kanvas",
+        "nodesDesc": "Ett nodbaserat system för bildgenerering är under utveckling. Håll utkik för uppdateringar om denna fantastiska funktion.",
+        "langUkranian": "Украї́нська",
+        "langSpanish": "Español",
+        "postProcessDesc2": "Ett dedikerat användargränssnitt kommer snart att släppas för att underlätta mer avancerade arbetsflöden av efterbehandling.",
+        "trainingDesc1": "Ett dedikerat arbetsflöde för träning av dina egna inbäddningar och kontrollpunkter genom Textual Inversion eller Dreambooth från webbgränssnittet.",
+        "trainingDesc2": "InvokeAI stöder redan träning av anpassade inbäddningar med hjälp av Textual Inversion genom huvudscriptet.",
+        "upload": "Ladda upp",
+        "close": "Stäng",
+        "cancel": "Avbryt",
+        "accept": "Acceptera",
+        "statusDisconnected": "Frånkopplad",
+        "statusGeneratingTextToImage": "Genererar text till bild",
+        "statusGeneratingImageToImage": "Genererar Bild till bild",
+        "statusGeneratingInpainting": "Genererar Måla i",
+        "statusGenerationComplete": "Generering klar",
+        "statusModelConverted": "Modell konverterad",
+        "statusMergingModels": "Sammanfogar modeller",
+        "pinOptionsPanel": "Nåla fast inställningspanelen",
+        "loading": "Laddar",
+        "loadingInvokeAI": "Laddar Invoke AI",
+        "statusRestoringFaces": "Återskapar ansikten",
+        "languagePickerLabel": "Språkväljare",
+        "themeLabel": "Tema",
+        "txt2img": "Text till bild",
+        "nodes": "Noder",
+        "img2img": "Bild till bild",
+        "postprocessing": "Efterbehandling",
+        "postProcessing": "Efterbehandling",
+        "load": "Ladda",
+        "training": "Träning",
+        "postProcessDesc1": "Invoke AI erbjuder ett brett utbud av efterbehandlingsfunktioner. Uppskalning och ansiktsåterställning finns redan tillgängligt i webbgränssnittet. Du kommer åt dem ifrån Avancerade inställningar-menyn under Bild till bild-fliken. Du kan också behandla bilder direkt genom att använda knappen bildåtgärder ovanför nuvarande bild eller i bildvisaren.",
+        "postProcessDesc3": "Invoke AI's kommandotolk erbjuder många olika funktioner, bland annat \"Förstora\".",
+        "statusGenerating": "Genererar",
+        "statusError": "Fel",
+        "back": "Bakåt",
+        "statusConnected": "Ansluten",
+        "statusPreparing": "Förbereder",
+        "statusProcessingCanceled": "Bearbetning avbruten",
+        "statusProcessingComplete": "Bearbetning färdig",
+        "statusGeneratingOutpainting": "Genererar Fyll ut",
+        "statusIterationComplete": "Itterering klar",
+        "statusSavingImage": "Sparar bild",
+        "statusRestoringFacesGFPGAN": "Återskapar ansikten (GFPGAN)",
+        "statusRestoringFacesCodeFormer": "Återskapar ansikten (CodeFormer)",
+        "statusUpscaling": "Skala upp",
+        "statusUpscalingESRGAN": "Uppskalning (ESRGAN)",
+        "statusModelChanged": "Modell ändrad",
+        "statusLoadingModel": "Laddar modell",
+        "statusConvertingModel": "Konverterar modell",
+        "statusMergedModels": "Modeller sammanfogade"
+    },
+    "gallery": {
+        "generations": "Generationer",
+        "showGenerations": "Visa generationer",
+        "uploads": "Uppladdningar",
+        "showUploads": "Visa uppladdningar",
+        "galleryImageSize": "Bildstorlek",
+        "allImagesLoaded": "Alla bilder laddade",
+        "loadMore": "Ladda mer",
+        "galleryImageResetSize": "Återställ storlek",
+        "gallerySettings": "Galleriinställningar",
+        "maintainAspectRatio": "Behåll bildförhållande",
+        "pinGallery": "Nåla fast galleri",
+        "noImagesInGallery": "Inga bilder i galleriet",
+        "autoSwitchNewImages": "Ändra automatiskt till nya bilder",
+        "singleColumnLayout": "Enkolumnslayout"
+    },
+    "hotkeys": {
+        "generalHotkeys": "Allmänna snabbtangenter",
+        "galleryHotkeys": "Gallerisnabbtangenter",
+        "unifiedCanvasHotkeys": "Snabbtangenter för sammanslagskanvas",
+        "invoke": {
+            "title": "Anropa",
+            "desc": "Genererar en bild"
+        },
+        "cancel": {
+            "title": "Avbryt",
+            "desc": "Avbryt bildgenerering"
+        },
+        "focusPrompt": {
+            "desc": "Fokusera området för promptinmatning",
+            "title": "Fokusprompt"
+        },
+        "pinOptions": {
+            "desc": "Nåla fast alternativpanelen",
+            "title": "Nåla fast alternativ"
+        },
+        "toggleOptions": {
+            "title": "Växla inställningar",
+            "desc": "Öppna och stäng alternativpanelen"
+        },
+        "toggleViewer": {
+            "title": "Växla visaren",
+            "desc": "Öppna och stäng bildvisaren"
+        },
+        "toggleGallery": {
+            "title": "Växla galleri",
+            "desc": "Öppna eller stäng galleribyrån"
+        },
+        "maximizeWorkSpace": {
+            "title": "Maximera arbetsyta",
+            "desc": "Stäng paneler och maximera arbetsyta"
+        },
+        "changeTabs": {
+            "title": "Växla flik",
+            "desc": "Byt till en annan arbetsyta"
+        },
+        "consoleToggle": {
+            "title": "Växla konsol",
+            "desc": "Öppna och stäng konsol"
+        },
+        "setSeed": {
+            "desc": "Använd seed för nuvarande bild",
+            "title": "välj seed"
+        },
+        "setParameters": {
+            "title": "Välj parametrar",
+            "desc": "Använd alla parametrar från nuvarande bild"
+        },
+        "setPrompt": {
+            "desc": "Använd prompt för nuvarande bild",
+            "title": "Välj prompt"
+        },
+        "restoreFaces": {
+            "title": "Återskapa ansikten",
+            "desc": "Återskapa nuvarande bild"
+        },
+        "upscale": {
+            "title": "Skala upp",
+            "desc": "Skala upp nuvarande bild"
+        },
+        "showInfo": {
+            "title": "Visa info",
+            "desc": "Visa metadata för nuvarande bild"
+        },
+        "sendToImageToImage": {
+            "title": "Skicka till Bild till bild",
+            "desc": "Skicka nuvarande bild till Bild till bild"
+        },
+        "deleteImage": {
+            "title": "Radera bild",
+            "desc": "Radera nuvarande bild"
+        },
+        "closePanels": {
+            "title": "Stäng paneler",
+            "desc": "Stäng öppna paneler"
+        },
+        "previousImage": {
+            "title": "Föregående bild",
+            "desc": "Visa föregående bild"
+        },
+        "nextImage": {
+            "title": "Nästa bild",
+            "desc": "Visa nästa bild"
+        },
+        "toggleGalleryPin": {
+            "title": "Växla gallerinål",
+            "desc": "Nålar fast eller nålar av galleriet i gränssnittet"
+        },
+        "increaseGalleryThumbSize": {
+            "title": "Förstora galleriets bildstorlek",
+            "desc": "Förstora miniatyrbildernas storlek"
+        },
+        "decreaseGalleryThumbSize": {
+            "title": "Minska gelleriets bildstorlek",
+            "desc": "Minska miniatyrbildernas storlek i galleriet"
+        },
+        "decreaseBrushSize": {
+            "desc": "Förminska storleken på kanvas- pensel eller suddgummi",
+            "title": "Minska penselstorlek"
+        },
+        "increaseBrushSize": {
+            "title": "Öka penselstorlek",
+            "desc": "Öka stoleken på kanvas- pensel eller suddgummi"
+        },
+        "increaseBrushOpacity": {
+            "title": "Öka penselns opacitet",
+            "desc": "Öka opaciteten för kanvaspensel"
+        },
+        "decreaseBrushOpacity": {
+            "desc": "Minska kanvaspenselns opacitet",
+            "title": "Minska penselns opacitet"
+        },
+        "moveTool": {
+            "title": "Flytta",
+            "desc": "Tillåt kanvasnavigation"
+        },
+        "fillBoundingBox": {
+            "title": "Fyll ram",
+            "desc": "Fyller ramen med pensels färg"
+        },
+        "keyboardShortcuts": "Snabbtangenter",
+        "appHotkeys": "Appsnabbtangenter",
+        "selectBrush": {
+            "desc": "Välj kanvaspensel",
+            "title": "Välj pensel"
+        },
+        "selectEraser": {
+            "desc": "Välj kanvassuddgummi",
+            "title": "Välj suddgummi"
+        },
+        "eraseBoundingBox": {
+            "title": "Ta bort ram"
+        }
+    }
+}

invokeai/frontend/web/dist/locales/tr.json

@@ -0,0 +1,64 @@
+{
+    "accessibility": {
+        "invokeProgressBar": "Invoke ilerleme durumu",
+        "nextImage": "Sonraki Resim",
+        "useThisParameter": "Kullanıcı parametreleri",
+        "copyMetadataJson": "Metadata verilerini kopyala (JSON)",
+        "exitViewer": "Görüntüleme Modundan Çık",
+        "zoomIn": "Yakınlaştır",
+        "zoomOut": "Uzaklaştır",
+        "rotateCounterClockwise": "Döndür (Saat yönünün tersine)",
+        "rotateClockwise": "Döndür (Saat yönünde)",
+        "flipHorizontally": "Yatay Çevir",
+        "flipVertically": "Dikey Çevir",
+        "modifyConfig": "Ayarları Değiştir",
+        "toggleAutoscroll": "Otomatik kaydırmayı aç/kapat",
+        "toggleLogViewer": "Günlük Görüntüleyici Aç/Kapa",
+        "showOptionsPanel": "Ayarlar Panelini Göster",
+        "modelSelect": "Model Seçin",
+        "reset": "Sıfırla",
+        "uploadImage": "Resim Yükle",
+        "previousImage": "Önceki Resim",
+        "menu": "Menü",
+        "showGallery": "Galeriyi Göster"
+    },
+    "common": {
+        "hotkeysLabel": "Kısayol Tuşları",
+        "themeLabel": "Tema",
+        "languagePickerLabel": "Dil Seçimi",
+        "reportBugLabel": "Hata Bildir",
+        "githubLabel": "Github",
+        "discordLabel": "Discord",
+        "settingsLabel": "Ayarlar",
+        "darkTheme": "Karanlık Tema",
+        "lightTheme": "Aydınlık Tema",
+        "greenTheme": "Yeşil Tema",
+        "oceanTheme": "Okyanus Tema",
+        "langArabic": "Arapça",
+        "langEnglish": "İngilizce",
+        "langDutch": "Hollandaca",
+        "langFrench": "Fransızca",
+        "langGerman": "Almanca",
+        "langItalian": "İtalyanca",
+        "langJapanese": "Japonca",
+        "langPolish": "Lehçe",
+        "langPortuguese": "Portekizce",
+        "langBrPortuguese": "Portekizcr (Brezilya)",
+        "langRussian": "Rusça",
+        "langSimplifiedChinese": "Çince (Basit)",
+        "langUkranian": "Ukraynaca",
+        "langSpanish": "İspanyolca",
+        "txt2img": "Metinden Resime",
+        "img2img": "Resimden Metine",
+        "linear": "Çizgisel",
+        "nodes": "Düğümler",
+        "postprocessing": "İşlem Sonrası",
+        "postProcessing": "İşlem Sonrası",
+        "postProcessDesc2": "Daha gelişmiş özellikler için ve iş akışını kolaylaştırmak için özel bir kullanıcı arayüzü çok yakında yayınlanacaktır.",
+        "postProcessDesc3": "Invoke AI komut satırı arayüzü, bir çok yeni özellik sunmaktadır.",
+        "langKorean": "Korece",
+        "unifiedCanvas": "Akıllı Tuval",
+        "nodesDesc": "Görüntülerin oluşturulmasında hazırladığımız yeni bir sistem geliştirme aşamasındadır. Bu harika özellikler ve çok daha fazlası için bizi takip etmeye devam edin.",
+        "postProcessDesc1": "Invoke AI son kullanıcıya yönelik bir çok özellik sunar. Görüntü kalitesi yükseltme, yüz restorasyonu WebUI üzerinden kullanılabilir. Metinden resime ve resimden metne araçlarına gelişmiş seçenekler menüsünden ulaşabilirsiniz. İsterseniz mevcut görüntü ekranının üzerindeki veya görüntüleyicideki görüntüyü doğrudan düzenleyebilirsiniz."
+    }
+}

invokeai/frontend/web/dist/locales/vi.json

@@ -0,0 +1 @@
+{}

invokeai/frontend/web/package.json

@@ -23,8 +23,7 @@
     "dev": "concurrently \"vite dev\" \"yarn run theme:watch\"",
     "dev:host": "concurrently \"vite dev --host\" \"yarn run theme:watch\"",
     "build": "yarn run lint && vite build",
-    "api:web": "openapi -i http://localhost:9090/openapi.json -o src/services/api --client axios --useOptions --useUnionTypes --indent 2 --request src/services/fixtures/request.ts",
-    "api:file": "openapi -i src/services/fixtures/openapi.json -o src/services/api --client axios --useOptions --useUnionTypes --indent 2 --request src/services/fixtures/request.ts",
+    "typegen": "npx openapi-typescript http://localhost:9090/openapi.json --output src/services/api/schema.d.ts -t",
     "preview": "vite preview",
     "lint:madge": "madge --circular src/main.tsx",
     "lint:eslint": "eslint --max-warnings=0 .",
@@ -54,57 +53,62 @@
     ]
   },
   "dependencies": {
+    "@apidevtools/swagger-parser": "^10.1.0",
     "@chakra-ui/anatomy": "^2.1.1",
     "@chakra-ui/icons": "^2.0.19",
-    "@chakra-ui/react": "^2.6.0",
-    "@chakra-ui/styled-system": "^2.9.0",
-    "@chakra-ui/theme-tools": "^2.0.16",
-    "@dagrejs/graphlib": "^2.1.12",
+    "@chakra-ui/react": "^2.7.1",
+    "@chakra-ui/styled-system": "^2.9.1",
+    "@chakra-ui/theme-tools": "^2.0.18",
+    "@dagrejs/graphlib": "^2.1.13",
     "@dnd-kit/core": "^6.0.8",
     "@dnd-kit/modifiers": "^6.0.1",
     "@emotion/react": "^11.11.1",
-    "@emotion/styled": "^11.10.6",
-    "@floating-ui/react-dom": "^2.0.0",
-    "@fontsource/inter": "^4.5.15",
-    "@mantine/core": "^6.0.13",
-    "@mantine/hooks": "^6.0.13",
+    "@emotion/styled": "^11.11.0",
+    "@floating-ui/react-dom": "^2.0.1",
+    "@fontsource-variable/inter": "^5.0.3",
+    "@fontsource/inter": "^5.0.3",
+    "@mantine/core": "^6.0.14",
+    "@mantine/hooks": "^6.0.14",
     "@reduxjs/toolkit": "^1.9.5",
     "@roarr/browser-log-writer": "^1.1.5",
     "chakra-ui-contextmenu": "^1.0.5",
     "dateformat": "^5.0.3",
     "downshift": "^7.6.0",
-    "formik": "^2.2.9",
-    "framer-motion": "^10.12.4",
+    "formik": "^2.4.2",
+    "framer-motion": "^10.12.17",
     "fuse.js": "^6.6.2",
-    "i18next": "^22.4.15",
-    "i18next-browser-languagedetector": "^7.0.1",
-    "i18next-http-backend": "^2.2.0",
-    "konva": "^9.0.1",
+    "i18next": "^23.2.3",
+    "i18next-browser-languagedetector": "^7.0.2",
+    "i18next-http-backend": "^2.2.1",
+    "konva": "^9.2.0",
     "lodash-es": "^4.17.21",
-    "overlayscrollbars": "^2.1.1",
+    "nanostores": "^0.9.2",
+    "openapi-fetch": "^0.4.0",
+    "overlayscrollbars": "^2.2.0",
     "overlayscrollbars-react": "^0.5.0",
     "patch-package": "^7.0.0",
+    "query-string": "^8.1.0",
     "re-resizable": "^6.9.9",
     "react": "^18.2.0",
     "react-colorful": "^5.6.1",
     "react-dom": "^18.2.0",
     "react-dropzone": "^14.2.3",
     "react-hotkeys-hook": "4.4.0",
-    "react-i18next": "^12.2.2",
-    "react-icons": "^4.9.0",
-    "react-konva": "^18.2.7",
-    "react-redux": "^8.0.5",
-    "react-resizable-panels": "^0.0.42",
+    "react-i18next": "^13.0.1",
+    "react-icons": "^4.10.1",
+    "react-konva": "^18.2.10",
+    "react-redux": "^8.1.1",
+    "react-resizable-panels": "^0.0.52",
     "react-use": "^17.4.0",
-    "react-virtuoso": "^4.3.5",
-    "react-zoom-pan-pinch": "^3.0.7",
-    "reactflow": "^11.7.0",
+    "react-virtuoso": "^4.3.11",
+    "react-zoom-pan-pinch": "^3.0.8",
+    "reactflow": "^11.7.4",
     "redux-dynamic-middlewares": "^2.2.0",
     "redux-remember": "^3.3.1",
     "roarr": "^7.15.0",
     "serialize-error": "^11.0.0",
-    "socket.io-client": "^4.6.0",
-    "use-image": "^1.1.0",
+    "socket.io-client": "^4.7.0",
+    "use-image": "^1.1.1",
     "uuid": "^9.0.0",
     "zod": "^3.21.4"
   },
@@ -115,22 +119,22 @@
     "ts-toolbelt": "^9.6.0"
   },
   "devDependencies": {
-    "@chakra-ui/cli": "^2.4.0",
+    "@chakra-ui/cli": "^2.4.1",
     "@types/dateformat": "^5.0.0",
     "@types/lodash-es": "^4.14.194",
-    "@types/node": "^18.16.2",
-    "@types/react": "^18.2.0",
-    "@types/react-dom": "^18.2.1",
+    "@types/node": "^20.3.1",
+    "@types/react": "^18.2.14",
+    "@types/react-dom": "^18.2.6",
     "@types/react-redux": "^7.1.25",
-    "@types/react-transition-group": "^4.4.5",
-    "@types/uuid": "^9.0.0",
-    "@typescript-eslint/eslint-plugin": "^5.59.1",
-    "@typescript-eslint/parser": "^5.59.1",
-    "@vitejs/plugin-react-swc": "^3.3.0",
+    "@types/react-transition-group": "^4.4.6",
+    "@types/uuid": "^9.0.2",
+    "@typescript-eslint/eslint-plugin": "^5.60.0",
+    "@typescript-eslint/parser": "^5.60.0",
+    "@vitejs/plugin-react-swc": "^3.3.2",
     "axios": "^1.4.0",
     "babel-plugin-transform-imports": "^2.0.0",
-    "concurrently": "^8.0.1",
-    "eslint": "^8.39.0",
+    "concurrently": "^8.2.0",
+    "eslint": "^8.43.0",
     "eslint-config-prettier": "^8.8.0",
     "eslint-plugin-prettier": "^4.2.1",
     "eslint-plugin-react": "^7.32.2",
@@ -138,18 +142,20 @@
     "form-data": "^4.0.0",
     "husky": "^8.0.3",
     "lint-staged": "^13.2.2",
-    "madge": "^6.0.0",
-    "openapi-types": "^12.1.0",
+    "madge": "^6.1.0",
+    "openapi-types": "^12.1.3",
+    "openapi-typescript": "^6.2.8",
     "openapi-typescript-codegen": "^0.24.0",
     "postinstall-postinstall": "^2.1.0",
     "prettier": "^2.8.8",
-    "rollup-plugin-visualizer": "^5.9.0",
-    "terser": "^5.17.1",
+    "rollup-plugin-visualizer": "^5.9.2",
+    "terser": "^5.18.1",
     "ts-toolbelt": "^9.6.0",
-    "vite": "^4.3.3",
+    "vite": "^4.3.9",
     "vite-plugin-css-injected-by-js": "^3.1.1",
     "vite-plugin-dts": "^2.3.0",
     "vite-plugin-eslint": "^1.8.1",
+    "vite-plugin-node-polyfills": "^0.9.0",
     "vite-tsconfig-paths": "^4.2.0",
     "yarn": "^1.22.19"
   }

invokeai/frontend/web/patches/@chakra-ui+cli+2.4.0.patch

@@ -1,14 +0,0 @@
-diff --git a/node_modules/@chakra-ui/cli/dist/scripts/read-theme-file.worker.js b/node_modules/@chakra-ui/cli/dist/scripts/read-theme-file.worker.js
-index 937cf0d..7dcc0c0 100644
---- a/node_modules/@chakra-ui/cli/dist/scripts/read-theme-file.worker.js
-+++ b/node_modules/@chakra-ui/cli/dist/scripts/read-theme-file.worker.js
-@@ -50,7 +50,8 @@ async function readTheme(themeFilePath) {
-       project: tsConfig.configFileAbsolutePath,
-       compilerOptions: {
-         module: "CommonJS",
--        esModuleInterop: true
-+        esModuleInterop: true,
-+        jsx: 'react'
-       },
-       transpileOnly: true,
-       swc: true

invokeai/frontend/web/patches/openapi-fetch+0.4.0.patch

@@ -0,0 +1,55 @@
+diff --git a/node_modules/openapi-fetch/dist/index.js b/node_modules/openapi-fetch/dist/index.js
+index cd4528a..8976b51 100644
+--- a/node_modules/openapi-fetch/dist/index.js
++++ b/node_modules/openapi-fetch/dist/index.js
+@@ -1,5 +1,5 @@
+ // settings & const
+-const DEFAULT_HEADERS = {
++const CONTENT_TYPE_APPLICATION_JSON = {
+     "Content-Type": "application/json",
+ };
+ const TRAILING_SLASH_RE = /\/*$/;
+@@ -29,18 +29,29 @@ export function createFinalURL(url, options) {
+     }
+     return finalURL;
+ }
++function stringifyBody(body) {
++    if (body instanceof ArrayBuffer || body instanceof File || body instanceof DataView || body instanceof Blob || ArrayBuffer.isView(body) || body instanceof URLSearchParams || body instanceof FormData) {
++      return;
++    }
++  
++    if (typeof body === "string") {
++      return body;
++    }
++  
++    return JSON.stringify(body);
++  }
++  
+ export default function createClient(clientOptions = {}) {
+     const { fetch = globalThis.fetch, ...options } = clientOptions;
+-    const defaultHeaders = new Headers({
+-        ...DEFAULT_HEADERS,
+-        ...(options.headers ?? {}),
+-    });
++    const defaultHeaders = new Headers(options.headers ?? {});
+     async function coreFetch(url, fetchOptions) {
+         const { headers, body: requestBody, params = {}, parseAs = "json", querySerializer = defaultSerializer, ...init } = fetchOptions || {};
+         // URL
+         const finalURL = createFinalURL(url, { baseUrl: options.baseUrl, params, querySerializer });
++        // Stringify body if needed
++        const stringifiedBody = stringifyBody(requestBody);
+         // headers
+-        const baseHeaders = new Headers(defaultHeaders); // clone defaults (don’t overwrite!)
++        const baseHeaders = new Headers(stringifiedBody ? { ...CONTENT_TYPE_APPLICATION_JSON, ...defaultHeaders } : defaultHeaders); // clone defaults (don’t overwrite!)
+         const headerOverrides = new Headers(headers);
+         for (const [k, v] of headerOverrides.entries()) {
+             if (v === undefined || v === null)
+@@ -54,7 +65,7 @@ export default function createClient(clientOptions = {}) {
+             ...options,
+             ...init,
+             headers: baseHeaders,
+-            body: typeof requestBody === "string" ? requestBody : JSON.stringify(requestBody),
++            body: stringifiedBody ?? requestBody,
+         });
+         // handle empty content
+         // note: we return `{}` because we want user truthy checks for `.data` or `.error` to succeed

invokeai/frontend/web/public/locales/en.json

@@ -24,16 +24,13 @@
     },
     "common": {
         "hotkeysLabel": "Hotkeys",
-        "themeLabel": "Theme",
+        "darkMode": "Dark Mode",
+        "lightMode": "Light Mode",
         "languagePickerLabel": "Language",
         "reportBugLabel": "Report Bug",
         "githubLabel": "Github",
         "discordLabel": "Discord",
         "settingsLabel": "Settings",
-        "darkTheme": "Dark",
-        "lightTheme": "Light",
-        "greenTheme": "Green",
-        "oceanTheme": "Ocean",
         "langArabic": "العربية",
         "langEnglish": "English",
         "langDutch": "Nederlands",
@@ -524,7 +521,8 @@
         "initialImage": "Initial Image",
         "showOptionsPanel": "Show Options Panel",
         "hidePreview": "Hide Preview",
-        "showPreview": "Show Preview"
+        "showPreview": "Show Preview",
+        "controlNetControlMode": "Control Mode"
     },
     "settings": {
         "models": "Models",

invokeai/frontend/web/src/app/components/App.tsx

@@ -24,7 +24,8 @@ import Toaster from './Toaster';
 import DeleteImageModal from 'features/gallery/components/DeleteImageModal';
 import { requestCanvasRescale } from 'features/canvas/store/thunks/requestCanvasScale';
 import UpdateImageBoardModal from '../../features/gallery/components/Boards/UpdateImageBoardModal';
-import { useListModelsQuery } from 'services/apiSlice';
+import { useListModelsQuery } from 'services/api/endpoints/models';
+import DeleteBoardImagesModal from '../../features/gallery/components/Boards/DeleteBoardImagesModal';
 
 const DEFAULT_CONFIG = {};
 
@@ -48,7 +49,7 @@ const App = ({
   const isApplicationReady = useIsApplicationReady();
 
   const { data: pipelineModels } = useListModelsQuery({
-    model_type: 'pipeline',
+    model_type: 'main',
   });
   const { data: controlnetModels } = useListModelsQuery({
     model_type: 'controlnet',
@@ -158,6 +159,7 @@ const App = ({
       </Grid>
       <DeleteImageModal />
       <UpdateImageBoardModal />
+      <DeleteBoardImagesModal />
       <Toaster />
       <GlobalHotkeys />
     </>