Updated version to 3.3.0post3

Fix for breaking change in `python-socketio` 5.10.0 in which `enter_room` and `leave_room` were made coroutines.

.github/workflows/pypi-release.yml

@@ -28,7 +28,7 @@ jobs:
         run: twine check dist/*
 
       - name: check PyPI versions
-        if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/v2.3'
+        if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/heads/release/')
         run: |
           pip install --upgrade requests
           python -c "\

docs/contributing/LOCAL_DEVELOPMENT.md

@@ -47,34 +47,9 @@ pip install ".[dev,test]"
 These are optional groups of packages which are defined within the `pyproject.toml`
 and will be required for testing the changes you make to the code.
 
-### Running Tests
-
-We use [pytest](https://docs.pytest.org/en/7.2.x/) for our test suite. Tests can
-be found under the `./tests` folder and can be run with a single `pytest`
-command. Optionally, to review test coverage you can append `--cov`.
-
-```zsh
-pytest --cov
-```
-
-Test outcomes and coverage will be reported in the terminal. In addition a more
-detailed report is created in both XML and HTML format in the `./coverage`
-folder. The HTML one in particular can help identify missing statements
-requiring tests to ensure coverage. This can be run by opening
-`./coverage/html/index.html`.
-
-For example.
-
-```zsh
-pytest --cov; open ./coverage/html/index.html
-```
-
-??? info "HTML coverage report output"
-
-    ![html-overview](../assets/contributing/html-overview.png)
-
-    ![html-detail](../assets/contributing/html-detail.png)
+### Tests
 
+See the [tests documentation](./TESTS.md) for information about running and writing tests.
 ### Reloading Changes
 
 Experimenting with changes to the Python source code is a drag if you have to re-start the server —
@@ -167,6 +142,23 @@ and so you'll have access to the same python environment as the InvokeAI app.
 
 This is _super_ handy.
 
+#### Enabling Type-Checking with Pylance
+
+We use python's typing system in InvokeAI. PR reviews will include checking that types are present and correct. We don't enforce types with `mypy` at this time, but that is on the horizon.
+
+Using a code analysis tool to automatically type check your code (and types) is very important when writing with types. These tools provide immediate feedback in your editor when types are incorrect, and following their suggestions lead to fewer runtime bugs.
+
+Pylance, installed at the beginning of this guide, is the de-facto python LSP (language server protocol). It provides type checking in the editor (among many other features). Once installed, you do need to enable type checking manually:
+
+- Open a python file
+- Look along the status bar in VSCode for `{ } Python`
+- Click the `{ }`
+- Turn type checking on - basic is fine
+
+You'll now see red squiggly lines where type issues are detected. Hover your cursor over the indicated symbols to see what's wrong.
+
+In 99% of cases when the type checker says there is a problem, there really is a problem, and you should take some time to understand and resolve what it is pointing out.
+
 #### Debugging configs with `launch.json`
 
 Debugging configs are managed in a `launch.json` file. Like most VSCode configs,

docs/contributing/TESTS.md

@@ -0,0 +1,89 @@
+# InvokeAI Backend Tests
+
+We use `pytest` to run the backend python tests. (See [pyproject.toml](/pyproject.toml) for the default `pytest` options.)
+
+## Fast vs. Slow
+All tests are categorized as either 'fast' (no test annotation) or 'slow' (annotated with the `@pytest.mark.slow` decorator).
+
+'Fast' tests are run to validate every PR, and are fast enough that they can be run routinely during development.
+
+'Slow' tests are currently only run manually on an ad-hoc basis. In the future, they may be automated to run nightly. Most developers are only expected to run the 'slow' tests that directly relate to the feature(s) that they are working on.
+
+As a rule of thumb, tests should be marked as 'slow' if there is a chance that they take >1s (e.g. on a CPU-only machine with slow internet connection). Common examples of slow tests are tests that depend on downloading a model, or running model inference.
+
+## Running Tests
+
+Below are some common test commands:
+```bash
+# Run the fast tests. (This implicitly uses the configured default option: `-m "not slow"`.)
+pytest tests/
+
+# Equivalent command to run the fast tests.
+pytest tests/ -m "not slow"
+
+# Run the slow tests.
+pytest tests/ -m "slow"
+
+# Run the slow tests from a specific file.
+pytest tests/path/to/slow_test.py -m "slow"
+
+# Run all tests (fast and slow).
+pytest tests -m ""
+```
+
+## Test Organization
+
+All backend tests are in the [`tests/`](/tests/) directory. This directory mirrors the organization of the `invokeai/` directory. For example, tests for `invokeai/model_management/model_manager.py` would be found in `tests/model_management/test_model_manager.py`.
+
+TODO: The above statement is aspirational. A re-organization of legacy tests is required to make it true.
+
+## Tests that depend on models
+
+There are a few things to keep in mind when adding tests that depend on models.
+
+1. If a required model is not already present, it should automatically be downloaded as part of the test setup.
+2. If a model is already downloaded, it should not be re-downloaded unnecessarily.
+3. Take reasonable care to keep the total number of models required for the tests low. Whenever possible, re-use models that are already required for other tests. If you are adding a new model, consider including a comment to explain why it is required/unique.
+
+There are several utilities to help with model setup for tests. Here is a sample test that depends on a model:
+```python
+import pytest
+import torch
+
+from invokeai.backend.model_management.models.base import BaseModelType, ModelType
+from invokeai.backend.util.test_utils import install_and_load_model
+
+@pytest.mark.slow
+def test_model(model_installer, torch_device):
+    model_info = install_and_load_model(
+        model_installer=model_installer,
+        model_path_id_or_url="HF/dummy_model_id",
+        model_name="dummy_model",
+        base_model=BaseModelType.StableDiffusion1,
+        model_type=ModelType.Dummy,
+    )
+
+    dummy_input = build_dummy_input(torch_device)
+
+    with torch.no_grad(), model_info as model:
+        model.to(torch_device, dtype=torch.float32)
+        output = model(dummy_input)
+
+    # Validate output...
+
+```
+
+## Test Coverage
+
+To review test coverage, append `--cov` to your pytest command:
+```bash
+pytest tests/ --cov
+```
+
+Test outcomes and coverage will be reported in the terminal. In addition, a more detailed report is created in both XML and HTML format in the `./coverage` folder. The HTML output is particularly helpful in identifying untested statements where coverage should be improved. The HTML report can be viewed by opening `./coverage/html/index.html`.
+
+??? info "HTML coverage report output"
+
+    ![html-overview](../assets/contributing/html-overview.png)
+
+    ![html-detail](../assets/contributing/html-detail.png)

docs/contributing/contribution_guides/development.md

@@ -12,7 +12,7 @@ To get started, take a look at our [new contributors checklist](newContributorCh
 Once you're setup, for more information, you can review the documentation specific to your area of interest:
 
 * #### [InvokeAI Architecure](../ARCHITECTURE.md)
-* #### [Frontend Documentation](development_guides/contributingToFrontend.md)
+* #### [Frontend Documentation](./contributingToFrontend.md)
 * #### [Node Documentation](../INVOCATIONS.md)
 * #### [Local Development](../LOCAL_DEVELOPMENT.md)
 
@@ -38,9 +38,9 @@ There are two paths to making a development contribution:
 
 If you need help, you can ask questions in the [#dev-chat](https://discord.com/channels/1020123559063990373/1049495067846524939) channel of the Discord.
 
-For frontend related work, **@pyschedelicious** is the best person to reach out to. 
+For frontend related work, **@psychedelicious** is the best person to reach out to. 
 
-For backend related work, please reach out to **@blessedcoolant**, **@lstein**, **@StAlKeR7779** or **@pyschedelicious**.
+For backend related work, please reach out to **@blessedcoolant**, **@lstein**, **@StAlKeR7779** or **@psychedelicious**.
 
 
 ## **What does the Code of Conduct mean for me?**

docs/contributing/contribution_guides/documentation.md

@@ -10,4 +10,4 @@ When updating or creating documentation, please keep in mind InvokeAI is a tool
 
 ## Help & Questions
 
-Please ping @imic1 or @hipsterusername in the [Discord](https://discord.com/channels/1020123559063990373/1049495067846524939) if you have any questions.
+Please ping @imic or @hipsterusername in the [Discord](https://discord.com/channels/1020123559063990373/1049495067846524939) if you have any questions.

docs/features/CONFIGURATION.md

@@ -159,7 +159,7 @@ groups in `invokeia.yaml`:
 | `host`     | `localhost`      | Name or IP address of the network interface that the web server will listen on  |
 | `port`     | `9090`           | Network port number that the web server will listen on  |
 | `allow_origins`  | `[]`       | A list of host names or IP addresses that are allowed to connect to the InvokeAI API in the format `['host1','host2',...]` |
-| `allow_credentials | `true`   | Require credentials for a foreign host to access the InvokeAI API (don't change this) |
+| `allow_credentials` | `true`   | Require credentials for a foreign host to access the InvokeAI API (don't change this) |
 | `allow_methods` | `*`         | List of HTTP methods ("GET", "POST") that the web server is allowed to use when accessing the API  |
 | `allow_headers` | `*`         | List of HTTP headers that the web server will accept when accessing the API  |
 

docs/features/CONTROLNET.md

@@ -1,13 +1,11 @@
 ---
-title: ControlNet
+title: Control Adapters
 ---
 
-# :material-loupe: ControlNet
+# :material-loupe: Control Adapters
 
 ## 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
@@ -20,7 +18,7 @@ towards generating images that better fit your desired style or
 outcome.
 
 
-### How it works
+#### How it works
 
 ControlNet works by analyzing an input image, pre-processing that
 image to identify relevant information that can be interpreted by each
@@ -30,7 +28,7 @@ composition, or other aspects of the image to better achieve a
 specific result.
 
 
-### Models
+#### Models
 
 InvokeAI provides access to a series of ControlNet models that provide
 different effects or styles in your generated images.  Currently
@@ -96,6 +94,8 @@ A model that generates normal maps from input images, allowing for more realisti
 **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)
 
+**QR Code Monster**:
+A model that helps generate creative QR codes that still scan. Can also be used to create images with text, logos or shapes within them. 
 
 **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. 
@@ -120,7 +120,7 @@ With Pix2Pix, you can input an image into the controlnet, and then "instruct" th
 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
+### 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.
 
@@ -132,3 +132,31 @@ Weight - Strength of the Controlnet model applied to the generation for the sect
 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.
+
+
+## IP-Adapter
+
+[IP-Adapter](https://ip-adapter.github.io) is a tooling that allows for image prompt capabilities with text-to-image diffusion models. IP-Adapter works by analyzing the given image prompt to extract features, then passing those features to the UNet along with any other conditioning provided. 
+
+![IP-Adapter + T2I](https://github.com/tencent-ailab/IP-Adapter/raw/main/assets/demo/ip_adpter_plus_multi.jpg)
+
+![IP-Adapter + IMG2IMG](https://github.com/tencent-ailab/IP-Adapter/blob/main/assets/demo/image-to-image.jpg)
+
+#### Installation
+There are several ways to install IP-Adapter models with an existing InvokeAI installation:
+
+1. Through the command line interface launched from the invoke.sh / invoke.bat scripts, option [5] to download models.
+2. Through the Model Manager UI with models from the *Tools* section of [www.models.invoke.ai](www.models.invoke.ai). To do this, copy the repo ID from the desired model page, and paste it in the Add Model field of the model manager. **Note** Both the IP-Adapter and the Image Encoder must be installed for IP-Adapter to work. For example, the [SD 1.5 IP-Adapter](https://models.invoke.ai/InvokeAI/ip_adapter_plus_sd15) and [SD1.5 Image Encoder](https://models.invoke.ai/InvokeAI/ip_adapter_sd_image_encoder) must be installed to use IP-Adapter with SD1.5 based models.  
+3. **Advanced -- Not recommended ** Manually downloading the IP-Adapter and Image Encoder files - Image Encoder folders shouid be placed in the `models\any\clip_vision` folders. IP Adapter Model folders should be placed in the relevant `ip-adapter` folder of relevant base model folder of Invoke root directory. For example, for the SDXL IP-Adapter, files should be added to the `model/sdxl/ip_adapter/` folder. 
+
+#### Using IP-Adapter
+
+IP-Adapter can be used by navigating to the *Control Adapters* options and enabling IP-Adapter. 
+
+IP-Adapter requires an image to be used as the Image Prompt. It can also be used in conjunction with text prompts, Image-to-Image, Inpainting, Outpainting, ControlNets and LoRAs.
+
+
+Each IP-Adapter has two settings that are applied to the IP-Adapter:
+
+* Weight - Strength of the IP-Adapter 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 IP-Adapter applied.

docs/features/UTILITIES.md

@@ -0,0 +1,336 @@
+---
+title: Command-line Utilities
+---
+
+# :material-file-document: Utilities
+
+# Command-line Utilities
+
+InvokeAI comes with several scripts that are accessible via the
+command line. To access these commands, start the "developer's
+console" from the launcher (`invoke.bat` menu item [8]). Users who are
+familiar with Python can alternatively activate InvokeAI's virtual
+environment (typically, but not necessarily `invokeai/.venv`).
+
+In the developer's console, type the script's name to run it. To get a
+synopsis of what a utility does and the command-line arguments it
+accepts, pass it the `-h` argument, e.g.
+
+```bash
+invokeai-merge -h
+```
+## **invokeai-web**
+
+This script launches the web server and is effectively identical to
+selecting option [1] in the launcher. An advantage of launching the
+server from the command line is that you can override any setting
+configuration option in `invokeai.yaml` using like-named command-line
+arguments. For example, to temporarily change the size of the RAM
+cache to 7 GB, you can launch as follows:
+
+```bash
+invokeai-web --ram 7
+```
+
+## **invokeai-merge**
+
+This is the model merge script, the same as launcher option [4]. Call
+it with the `--gui` command-line argument to start the interactive
+console-based GUI. Alternatively, you can run it non-interactively
+using command-line arguments as illustrated in the example below which
+merges models named `stable-diffusion-1.5` and `inkdiffusion` into a new model named
+`my_new_model`:
+
+```bash
+invokeai-merge --force --base-model sd-1 --models stable-diffusion-1.5 inkdiffusion --merged_model_name my_new_model
+```
+
+## **invokeai-ti**
+
+This is the textual inversion training script that is run by launcher
+option [3]. Call it with `--gui` to run the interactive console-based
+front end. It can also be run non-interactively. It has about a
+zillion arguments, but a typical training session can be launched
+with:
+
+```bash
+invokeai-ti --model stable-diffusion-1.5 \
+            --placeholder_token 'jello' \
+            --learnable_property object \
+			--num_train_epochs 50 \
+			--train_data_dir /path/to/training/images \
+			--output_dir /path/to/trained/model
+```
+
+(Note that \\ is the Linux/Mac long-line continuation character. Use ^
+in Windows).
+
+## **invokeai-install**
+
+This is the console-based model install script that is run by launcher
+option [5]. If called without arguments, it will launch the
+interactive console-based interface. It can also be used
+non-interactively to list, add and remove models as shown by these
+examples:
+
+* This will download and install three models from CivitAI, HuggingFace,
+and local disk:
+
+```bash
+invokeai-install --add https://civitai.com/api/download/models/161302 ^
+                  gsdf/Counterfeit-V3.0  ^
+				  D:\Models\merge_model_two.safetensors
+```
+(Note that ^ is the Windows long-line continuation character. Use \\ on
+Linux/Mac).
+
+* This will list installed models of type `main`:
+
+```bash
+invokeai-model-install --list-models main
+```
+
+* This will delete the models named `voxel-ish` and `realisticVision`:
+
+```bash
+invokeai-model-install --delete voxel-ish realisticVision
+```
+
+## **invokeai-configure**
+
+This is the console-based configure script that ran when InvokeAI was
+first installed. You can run it again at any time to change the
+configuration, repair a broken install.
+
+Called without any arguments, `invokeai-configure` enters interactive
+mode with two screens. The first screen is a form that provides access
+to most of InvokeAI's configuration options. The second screen lets
+you download, add, and delete models interactively. When you exit the
+second screen, the script will add any missing "support models"
+needed for core functionality, and any selected "sd weights" which are
+the model checkpoint/diffusers files.
+
+This behavior can be changed via a series of command-line
+arguments. Here are some of the useful ones:
+
+* `invokeai-configure --skip-sd-weights --skip-support-models`
+This will run just the configuration part of the utility, skipping
+downloading of support models and stable diffusion weights.
+
+* `invokeai-configure --yes`
+This will run the configure script non-interactively. It will set the
+configuration options to their default values, install/repair support
+models, and download the "recommended" set of SD models.
+
+* `invokeai-configure --yes --default_only` 
+This will run the configure script non-interactively. In contrast to
+the previous command, it will only download the default SD model,
+Stable Diffusion v1.5
+
+* `invokeai-configure --yes --default_only --skip-sd-weights` 
+This is similar to the previous command, but will not download any
+SD models at all. It is usually used to repair a broken install.
+
+By default, `invokeai-configure` runs on the currently active InvokeAI
+root folder. To run it against a different root, pass it the `--root
+</path/to/root>` argument.
+
+Lastly, you can use `invokeai-configure` to create a working root
+directory entirely from scratch. Assuming you wish to make a root directory
+named `InvokeAI-New`, run this command:
+
+```bash
+invokeai-configure --root InvokeAI-New --yes --default_only
+```
+This will create a minimally functional root directory. You can now
+launch the web server against it with `invokeai-web --root InvokeAI-New`.
+
+## **invokeai-update**
+
+This is the interactive console-based script that is run by launcher
+menu item [9] to update to a new version of InvokeAI. It takes no
+command-line arguments.
+
+## **invokeai-metadata**
+
+This is a script which takes a list of InvokeAI-generated images and
+outputs their metadata in the same JSON format that you get from the
+`</>` button in the Web GUI. For example:
+
+```bash
+$ invokeai-metadata ffe2a115-b492-493c-afff-7679aa034b50.png
+ffe2a115-b492-493c-afff-7679aa034b50.png:
+{
+    "app_version": "3.1.0",
+    "cfg_scale": 8.0,
+    "clip_skip": 0,
+    "controlnets": [],
+    "generation_mode": "sdxl_txt2img",
+    "height": 1024,
+    "loras": [],
+    "model": {
+        "base_model": "sdxl",
+        "model_name": "stable-diffusion-xl-base-1.0",
+        "model_type": "main"
+    },
+    "negative_prompt": "",
+    "negative_style_prompt": "",
+    "positive_prompt": "military grade sushi dinner for shock troopers",
+    "positive_style_prompt": "",
+    "rand_device": "cpu",
+    "refiner_cfg_scale": 7.5,
+    "refiner_model": {
+        "base_model": "sdxl-refiner",
+        "model_name": "sd_xl_refiner_1.0",
+        "model_type": "main"
+    },
+    "refiner_negative_aesthetic_score": 2.5,
+    "refiner_positive_aesthetic_score": 6.0,
+    "refiner_scheduler": "euler",
+    "refiner_start": 0.8,
+    "refiner_steps": 20,
+    "scheduler": "euler",
+    "seed": 387129902,
+    "steps": 25,
+    "width": 1024
+}
+```
+
+You may list multiple files on the command line.
+
+## **invokeai-import-images**
+
+InvokeAI uses a database to store information about images it
+generated, and just copying the image files from one InvokeAI root
+directory to another does not automatically import those images into
+the destination's gallery. This script allows you to bulk import
+images generated by one instance of InvokeAI into a gallery maintained
+by another. It also works on images generated by older versions of
+InvokeAI, going way back to version 1.
+
+This script has an interactive mode only. The following example shows
+it in action:
+
+```bash
+$ invokeai-import-images
+===============================================================================
+This script will import images generated by earlier versions of
+InvokeAI into the currently installed root directory:
+   /home/XXXX/invokeai-main
+If this is not what you want to do, type ctrl-C now to cancel.
+===============================================================================
+= Configuration & Settings
+Found invokeai.yaml file at /home/XXXX/invokeai-main/invokeai.yaml:
+  Database : /home/XXXX/invokeai-main/databases/invokeai.db
+  Outputs  : /home/XXXX/invokeai-main/outputs/images
+ 
+Use these paths for import (yes) or choose different ones (no) [Yn]:
+Inputs: Specify absolute path containing InvokeAI .png images to import: /home/XXXX/invokeai-2.3/outputs/images/
+Include files from subfolders recursively [yN]?
+
+Options for board selection for imported images:
+1) Select an existing board name. (found 4)
+2) Specify a board name to create/add to.
+3) Create/add to board named 'IMPORT'.
+4) Create/add to board named 'IMPORT' with the current datetime string appended (.e.g IMPORT_20230919T203519Z).
+5) Create/add to board named 'IMPORT' with a the original file app_version appended (.e.g IMPORT_2.2.5).
+Specify desired board option: 3
+
+===============================================================================
+= Import Settings Confirmation
+
+Database File Path               : /home/XXXX/invokeai-main/databases/invokeai.db
+Outputs/Images Directory         : /home/XXXX/invokeai-main/outputs/images
+Import Image Source Directory    : /home/XXXX/invokeai-2.3/outputs/images/
+  Recurse Source SubDirectories  : No
+Count of .png file(s) found      : 5785
+Board name option specified      : IMPORT
+Database backup will be taken at : /home/XXXX/invokeai-main/databases/backup
+
+Notes about the import process:
+- Source image files will not be modified, only copied to the outputs directory.
+- If the same file name already exists in the destination, the file will be skipped.
+- If the same file name already has a record in the database, the file will be skipped.
+- Invoke AI metadata tags will be updated/written into the imported copy only.
+- On the imported copy, only Invoke AI known tags (latest and legacy) will be retained (dream, sd-metadata, invokeai, invokeai_metadata)
+- A property 'imported_app_version' will be added to metadata that can be viewed in the UI's metadata viewer.
+- The new 3.x InvokeAI outputs folder structure is flat so recursively found source imges will all be placed into the single outputs/images folder.
+ 
+Do you wish to continue with the import [Yn] ?
+
+Making DB Backup at /home/lstein/invokeai-main/databases/backup/backup-20230919T203519Z-invokeai.db...Done!
+
+===============================================================================
+Importing /home/XXXX/invokeai-2.3/outputs/images/17d09907-297d-4db3-a18a-60b337feac66.png
+... (5785 more lines) ...
+===============================================================================
+= Import Complete - Elpased Time: 0.28 second(s)
+
+Source File(s)                          : 5785
+Total Imported                          : 5783
+Skipped b/c file already exists on disk : 1
+Skipped b/c file already exists in db   : 0
+Errors during import                    : 1
+```
+## **invokeai-db-maintenance**
+
+This script helps maintain the integrity of your InvokeAI database by
+finding and fixing three problems that can arise over time:
+
+1. An image was manually deleted from the outputs directory, leaving a
+   dangling image record in the InvokeAI database. This will cause a
+   black image to appear in the gallery. This is an "orphaned database
+   image record." The script can fix this by running a "clean"
+   operation on the database, removing the orphaned entries.
+   
+2. An image is present in the outputs directory but there is no
+   corresponding entry in the database. This can happen when the image
+   is added manually to the outputs directory, or if a crash occurred
+   after the image was generated but before the database was
+   completely updated. The symptom is that the image is present in the
+   outputs folder but doesn't appear in the InvokeAI gallery. This is
+   called an "orphaned image file." The script can fix this problem by
+   running an "archive" operation in which orphaned files are moved
+   into a directory named `outputs/images-archive`. If you wish, you
+   can then run `invokeai-image-import` to reimport these images back
+   into the database.
+   
+3. The thumbnail for an image is missing, again causing a black
+   gallery thumbnail. This is fixed by running the "thumbnaiils"
+   operation, which simply regenerates and re-registers the missing
+   thumbnail.
+   
+You can find and fix all three of these problems in a single go by
+executing this command:
+
+```bash
+invokeai-db-maintenance --operation all
+```
+
+Or you can run just the clean and thumbnail operations like this:
+
+```bash
+invokeai-db-maintenance -operation clean, thumbnail
+```
+
+If called without any arguments, the script will ask you which
+operations you wish to perform.
+
+## **invokeai-migrate3**
+
+This script will migrate settings and models (but not images!) from an
+InvokeAI v2.3 root folder to an InvokeAI 3.X folder. Call it with the
+source and destination root folders like this:
+
+```bash
+invokeai-migrate3 --from ~/invokeai-2.3 --to invokeai-3.1.1
+```
+
+Both directories must previously have been properly created and
+initialized by `invokeai-configure`. If you wish to migrate the images
+contained in the older root as well, you can use the
+`invokeai-image-migrate` script described earlier.
+
+---
+
+Copyright (c) 2023, Lincoln Stein and the InvokeAI Development Team

docs/features/index.md

@@ -51,6 +51,9 @@ Prevent InvokeAI from displaying unwanted racy images.
 ### * [Controlling Logging](LOGGING.md)
 Control how InvokeAI logs status messages.
 
+### * [Command-line Utilities](UTILITIES.md)
+A list of the command-line utilities available with InvokeAI.
+
 <!-- OUT OF DATE
 ### * [Miscellaneous](OTHER.md)
 Run InvokeAI on Google Colab, generate images with repeating patterns,

docs/index.md

@@ -147,6 +147,7 @@ Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.
 
 ### InvokeAI Configuration
 - [Guide to InvokeAI Runtime Settings](features/CONFIGURATION.md)
+- [Database Maintenance and other Command Line Utilities](features/UTILITIES.md)
 
 ## :octicons-log-16: Important Changes Since Version 2.3
 

docs/installation/020_INSTALL_MANUAL.md

@@ -256,6 +256,10 @@ manager, please follow these steps:
         *highly recommended** if your virtual environment is located outside of
         your runtime directory.
 
+    !!! tip
+
+        On linux, it is recommended to run invokeai with the following env var: `MALLOC_MMAP_THRESHOLD_=1048576`. For example: `MALLOC_MMAP_THRESHOLD_=1048576 invokeai --web`. This helps to prevent memory fragmentation that can lead to memory accumulation over time. This env var is set automatically when running via `invoke.sh`.
+
 10.  Render away!
 
     Browse the [features](../features/index.md) section to learn about all the
@@ -296,8 +300,18 @@ code for InvokeAI. For this to work, you will need to install the
 on your system, please see the [Git Installation
 Guide](https://github.com/git-guides/install-git)
 
+You will also need to install the [frontend development toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/docs/contributing/contribution_guides/contributingToFrontend.md).
+
+If you have a "normal" installation, you should create a totally separate virtual environment for the git-based installation, else the two may interfere.
+
+> **Why do I need the frontend toolchain**?
+>
+> The InvokeAI project uses trunk-based development. That means our `main` branch is the development branch, and releases are tags on that branch. Because development is very active, we don't keep an updated build of the UI in `main` - we only build it for production releases.
+>
+> That means that between releases, to have a functioning application when running directly from the repo, you will need to run the UI in dev mode or build it regularly (any time the UI code changes).
+
 1. Create a fork of the InvokeAI repository through the GitHub UI or [this link](https://github.com/invoke-ai/InvokeAI/fork) 
-1. From the command line, run this command:
+2. From the command line, run this command:
    ```bash
    git clone https://github.com/<your_github_username>/InvokeAI.git
    ```
@@ -305,10 +319,10 @@ Guide](https://github.com/git-guides/install-git)
     This will create a directory named `InvokeAI` and populate it with the
     full source code from your fork of the InvokeAI repository.
 
-2. Activate the InvokeAI virtual environment as per step (4) of the manual
+3. Activate the InvokeAI virtual environment as per step (4) of the manual
 installation protocol (important!)
 
-3. Enter the InvokeAI repository directory and run one of these
+4. Enter the InvokeAI repository directory and run one of these
    commands, based on your GPU:
 
     === "CUDA (NVidia)"
@@ -334,11 +348,15 @@ installation protocol (important!)
     Be sure to pass `-e` (for an editable install) and don't forget the
     dot ("."). It is part of the command.
 
-    You can now run `invokeai` and its related commands. The code will be
+5.  Install the [frontend toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/docs/contributing/contribution_guides/contributingToFrontend.md) and do a production build of the UI as described.
+
+6.  You can now run `invokeai` and its related commands. The code will be
     read from the repository, so that you can edit the .py source files
     and watch the code's behavior change.
 
-4.  If you wish to contribute to the InvokeAI project, you are
+    When you pull in new changes to the repo, be sure to re-build the UI.
+
+7.  If you wish to contribute to the InvokeAI project, you are
     encouraged to establish a GitHub account and "fork"
     https://github.com/invoke-ai/InvokeAI into your own copy of the
     repository. You can then use GitHub functions to create and submit

docs/installation/050_INSTALLING_MODELS.md

@@ -171,3 +171,16 @@ subfolders and organize them as you wish.
 
 The location of the autoimport directories are controlled by settings
 in `invokeai.yaml`. See [Configuration](../features/CONFIGURATION.md).
+
+### Installing models that live in HuggingFace subfolders
+
+On rare occasions you may need to install a diffusers-style model that
+lives in a subfolder of a HuggingFace repo id. In this event, simply
+add ":_subfolder-name_" to the end of the repo id. For example, if the
+repo id is "monster-labs/control_v1p_sd15_qrcode_monster" and the model
+you wish to fetch lives in a subfolder named "v2", then the repo id to
+pass to the various model installers should be 
+
+```
+monster-labs/control_v1p_sd15_qrcode_monster:v2
+```

docs/nodes/NODES.md

@@ -4,12 +4,12 @@ The workflow editor is a blank canvas allowing for the use of individual functio
 
 If you're not familiar with Diffusion, take a look at our [Diffusion Overview.](../help/diffusion.md) Understanding how diffusion works will enable you to more easily use the Workflow Editor and build workflows to suit your needs.
 
-## UI Features
+## Features
 
 ### Linear View
 The Workflow Editor allows you to create a UI for your workflow, to make it easier to iterate on your generations. 
 
-To add an input to the Linear UI, right click on the input and select "Add to Linear View".
+To add an input to the Linear UI, right click on the input label and select "Add to Linear View".
 
 The Linear UI View will also be part of the saved workflow, allowing you share workflows and enable other to use them, regardless of complexity. 
 
@@ -25,6 +25,10 @@ Any node or input field can be renamed in the workflow editor. If the input fiel
 * Backspace/Delete to delete a node
 * Shift+Click to drag and select multiple nodes 
 
+### Node Caching 
+
+Nodes have a "Use Cache" option in their footer. This allows for performance improvements by using the previously cached values during the workflow processing. 
+
 
 ## Important Concepts 
 

docs/nodes/communityNodes.md

@@ -8,26 +8,42 @@ To download a node, simply download the `.py` node file from the link and add it
 
 To use a community workflow, download the the `.json` node graph file and load it into Invoke AI via the **Load Workflow** button in the Workflow Editor. 
 
-## Community Nodes
+- Community Nodes
+    + [Depth Map from Wavefront OBJ](#depth-map-from-wavefront-obj)
+    + [Film Grain](#film-grain)
+    + [Generative Grammar-Based Prompt Nodes](#generative-grammar-based-prompt-nodes)
+    + [GPT2RandomPromptMaker](#gpt2randompromptmaker)
+    + [Grid to Gif](#grid-to-gif)
+    + [Halftone](#halftone)
+    + [Ideal Size](#ideal-size)
+    + [Image and Mask Composition Pack](#image-and-mask-composition-pack)
+    + [Image to Character Art Image Nodes](#image-to-character-art-image-nodes)
+    + [Image Picker](#image-picker)
+    + [Load Video Frame](#load-video-frame)
+    + [Make 3D](#make-3d)
+    + [Oobabooga](#oobabooga)
+    + [Prompt Tools](#prompt-tools)
+    + [Retroize](#retroize)
+    + [Size Stepper Nodes](#size-stepper-nodes)
+    + [Text font to Image](#text-font-to-image)
+    + [Thresholding](#thresholding)
+    + [XY Image to Grid and Images to Grids nodes](#xy-image-to-grid-and-images-to-grids-nodes)
+- [Example Node Template](#example-node-template)
+- [Disclaimer](#disclaimer)
+- [Help](#help)
 
-### FaceTools
-
-**Description:** FaceTools is a collection of nodes created to manipulate faces as you would in Unified Canvas. It includes FaceMask, FaceOff, and FacePlace. FaceMask autodetects a face in the image using MediaPipe and creates a mask from it. FaceOff similarly detects a face, then takes the face off of the image by adding a square bounding box around it and cropping/scaling it. FacePlace puts the bounded face image from FaceOff back onto the original image. Using these nodes with other inpainting node(s), you can put new faces on existing things, put new things around existing faces, and work closer with a face as a bounded image. Additionally, you can supply X and Y offset values to scale/change the shape of the mask for finer control on FaceMask and FaceOff. See GitHub repository below for usage examples.
-
-**Node Link:** https://github.com/ymgenesis/FaceTools/
-
-**FaceMask Output Examples** 
-
-![5cc8abce-53b0-487a-b891-3bf94dcc8960](https://github.com/invoke-ai/InvokeAI/assets/25252829/43f36d24-1429-4ab1-bd06-a4bedfe0955e)
-![b920b710-1882-49a0-8d02-82dff2cca907](https://github.com/invoke-ai/InvokeAI/assets/25252829/7660c1ed-bf7d-4d0a-947f-1fc1679557ba)
-![71a91805-fda5-481c-b380-264665703133](https://github.com/invoke-ai/InvokeAI/assets/25252829/f8f6a2ee-2b68-4482-87da-b90221d5c3e2)
 
 --------------------------------
-### Ideal Size
+### Depth Map from Wavefront OBJ
 
-**Description:** This node calculates an ideal image size for a first pass of a multi-pass upscaling. The aim is to avoid duplication that results from choosing a size larger than the model is capable of.
+**Description:** Render depth maps from Wavefront .obj files (triangulated) using this simple 3D renderer utilizing numpy and matplotlib to compute and color the scene. There are simple parameters to change the FOV, camera position, and model orientation.
 
-**Node Link:** https://github.com/JPPhoto/ideal-size-node
+To be imported, an .obj must use triangulated meshes, so make sure to enable that option if exporting from a 3D modeling program. This renderer makes each triangle a solid color based on its average depth, so it will cause anomalies if your .obj has large triangles. In Blender, the Remesh modifier can be helpful to subdivide a mesh into small pieces that work well given these limitations.
+
+**Node Link:** https://github.com/dwringer/depth-from-obj-node
+
+**Example Usage:**
+</br><img src="https://raw.githubusercontent.com/dwringer/depth-from-obj-node/main/depth_from_obj_usage.jpg" width="500" />
 
 --------------------------------
 ### Film Grain
@@ -37,22 +53,19 @@ To use a community workflow, download the the `.json` node graph file and load i
 **Node Link:** https://github.com/JPPhoto/film-grain-node
 
 --------------------------------
-### Image Picker
+### Generative Grammar-Based Prompt Nodes
 
-**Description:** This InvokeAI node takes in a collection of images and randomly chooses one. This can be useful when you have a number of poses to choose from for a ControlNet node, or a number of input images for another purpose.
+**Description:** This set of 3 nodes generates prompts from simple user-defined grammar rules (loaded from custom files - examples provided below). The prompts are made by recursively expanding a special template string, replacing nonterminal "parts-of-speech" until no nonterminal terms remain in the string.
 
-**Node Link:** https://github.com/JPPhoto/image-picker-node
+This includes 3 Nodes:
+- *Lookup Table from File* - loads a YAML file "prompt" section (or of a whole folder of YAML's) into a JSON-ified dictionary (Lookups output)
+- *Lookups Entry from Prompt* - places a single entry in a new Lookups output under the specified heading
+- *Prompt from Lookup Table* - uses a Collection of Lookups as grammar rules from which to randomly generate prompts.
 
---------------------------------
-### Retroize
+**Node Link:** https://github.com/dwringer/generative-grammar-prompt-nodes
 
-**Description:** Retroize is a collection of nodes for InvokeAI to "Retroize" images. Any image can be given a fresh coat of retro paint with these nodes, either from your gallery or from within the graph itself. It includes nodes to pixelize, quantize, palettize, and ditherize images; as well as to retrieve palettes from existing images.
-
-**Node Link:** https://github.com/Ar7ific1al/invokeai-retroizeinode/
-
-**Retroize Output Examples**
-
-![image](https://github.com/Ar7ific1al/InvokeAI_nodes_retroize/assets/2306586/de8b4fa6-324c-4c2d-b36c-297600c73974)
+**Example Usage:**
+</br><img src="https://raw.githubusercontent.com/dwringer/generative-grammar-prompt-nodes/main/lookuptables_usage.jpg" width="500" />
 
 --------------------------------
 ### GPT2RandomPromptMaker
@@ -65,31 +78,133 @@ To use a community workflow, download the the `.json` node graph file and load i
 
 Generated Prompt: An enchanted weapon will be usable by any character regardless of their alignment.
 
-![9acf5aef-7254-40dd-95b3-8eac431dfab0 (1)](https://github.com/mickr777/InvokeAI/assets/115216705/8496ba09-bcdd-4ff7-8076-ff213b6a1e4c)
+<img src="https://github.com/mickr777/InvokeAI/assets/115216705/8496ba09-bcdd-4ff7-8076-ff213b6a1e4c" width="200" />
+
+--------------------------------
+### Grid to Gif
+
+**Description:** One node that turns a grid image into an image collection, one node that turns an image collection into a gif.
+
+**Node Link:** https://github.com/mildmisery/invokeai-GridToGifNode/blob/main/GridToGif.py
+
+**Example Node Graph:**  https://github.com/mildmisery/invokeai-GridToGifNode/blob/main/Grid%20to%20Gif%20Example%20Workflow.json
+
+**Output Examples** 
+
+<img src="https://raw.githubusercontent.com/mildmisery/invokeai-GridToGifNode/main/input.png" width="300" />
+<img src="https://raw.githubusercontent.com/mildmisery/invokeai-GridToGifNode/main/output.gif" width="300" />
+
+--------------------------------
+### Halftone
+
+**Description**: Halftone converts the source image to grayscale and then performs halftoning. CMYK Halftone converts the image to CMYK and applies a per-channel halftoning to make the source image look like a magazine or newspaper. For both nodes, you can specify angles and halftone dot spacing.
+
+**Node Link:** https://github.com/JPPhoto/halftone-node
+
+**Example**
+
+Input:
+
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/fd5efb9f-4355-4409-a1c2-c1ca99e0cab4" width="300" />
+
+Halftone Output:
+
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/7e606f29-e68f-4d46-b3d5-97f799a4ec2f" width="300" />
+
+CMYK Halftone Output:
+
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/c59c578f-db8e-4d66-8c66-2851752d75ea" width="300" />
+
+--------------------------------
+### Ideal Size
+
+**Description:** This node calculates an ideal image size for a first pass of a multi-pass upscaling. The aim is to avoid duplication that results from choosing a size larger than the model is capable of.
+
+**Node Link:** https://github.com/JPPhoto/ideal-size-node
+
+--------------------------------
+### Image and Mask Composition Pack
+
+**Description:** This is a pack of nodes for composing masks and images, including a simple text mask creator and both image and latent offset nodes. The offsets wrap around, so these can be used in conjunction with the Seamless node to progressively generate centered on different parts of the seamless tiling.
+
+This includes 15 Nodes:
+
+- *Adjust Image Hue Plus* - Rotate the hue of an image in one of several different color spaces.
+- *Blend Latents/Noise (Masked)* - Use a mask to blend part of one latents tensor [including Noise outputs] into another. Can be used to "renoise" sections during a multi-stage [masked] denoising process.
+- *Enhance Image* - Boost or reduce color saturation, contrast, brightness, sharpness, or invert colors of any image at any stage with this simple wrapper for pillow [PIL]'s ImageEnhance module.
+- *Equivalent Achromatic Lightness* - Calculates image lightness accounting for Helmholtz-Kohlrausch effect based on a method described by High, Green, and Nussbaum (2023).
+- *Text to Mask (Clipseg)* - Input a prompt and an image to generate a mask representing areas of the image matched by the prompt.
+- *Text to Mask Advanced (Clipseg)* - Output up to four prompt masks combined with logical "and", logical "or", or as separate channels of an RGBA image.
+- *Image Layer Blend* - Perform a layered blend of two images using alpha compositing. Opacity of top layer is selectable, with optional mask and several different blend modes/color spaces.
+- *Image Compositor* - Take a subject from an image with a flat backdrop and layer it on another image using a chroma key or flood select background removal.
+- *Image Dilate or Erode* - Dilate or expand a mask (or any image!). This is equivalent to an expand/contract operation.
+- *Image Value Thresholds* - Clip an image to pure black/white beyond specified thresholds.
+- *Offset Latents* - Offset a latents tensor in the vertical and/or horizontal dimensions, wrapping it around.
+- *Offset Image* - Offset an image in the vertical and/or horizontal dimensions, wrapping it around.
+- *Rotate/Flip Image* - Rotate an image in degrees clockwise/counterclockwise about its center, optionally resizing the image boundaries to fit, or flipping it about the vertical and/or horizontal axes.
+- *Shadows/Highlights/Midtones* - Extract three masks (with adjustable hard or soft thresholds) representing shadows, midtones, and highlights regions of an image.
+- *Text Mask (simple 2D)* - create and position a white on black (or black on white) line of text using any font locally available to Invoke.
+
+**Node Link:** https://github.com/dwringer/composition-nodes
+  
+</br><img src="https://raw.githubusercontent.com/dwringer/composition-nodes/main/composition_pack_overview.jpg" width="500" />
+
+--------------------------------
+### Image to Character Art Image Nodes
+
+**Description:** Group of nodes to convert an input image into ascii/unicode art Image
+
+**Node Link:** https://github.com/mickr777/imagetoasciiimage
+
+**Output Examples**
+
+<img src="https://user-images.githubusercontent.com/115216705/271817646-8e061fcc-9a2c-4fa9-bcc7-c0f7b01e9056.png" width="300" /><img src="https://github.com/mickr777/imagetoasciiimage/assets/115216705/3c4990eb-2f42-46b9-90f9-0088b939dc6a" width="300" /></br>
+<img src="https://github.com/mickr777/imagetoasciiimage/assets/115216705/fee7f800-a4a8-41e2-a66b-c66e4343307e" width="300" />
+<img src="https://github.com/mickr777/imagetoasciiimage/assets/115216705/1d9c1003-a45f-45c2-aac7-46470bb89330" width="300" />
+
+--------------------------------
+
+### Image Picker
+
+**Description:** This InvokeAI node takes in a collection of images and randomly chooses one. This can be useful when you have a number of poses to choose from for a ControlNet node, or a number of input images for another purpose.
+
+**Node Link:** https://github.com/JPPhoto/image-picker-node
 
 --------------------------------
 ### Load Video Frame
 
-**Description:** This is a video frame image provider + indexer/video creation nodes for hooking up to iterators and ranges and ControlNets and such for invokeAI node experimentation. Think animation + ControlNet outputs.
+**Description:** This is a video frame image provider + indexer/video creation nodes for hooking up to iterators and ranges and ControlNets and such for invokeAI node experimentation. Think animation + ControlNet outputs.
 
 **Node Link:** https://github.com/helix4u/load_video_frame
 
 **Example Node Graph:**  https://github.com/helix4u/load_video_frame/blob/main/Example_Workflow.json
 
 **Output Example:** 
-=======
-![Example animation](https://github.com/helix4u/load_video_frame/blob/main/testmp4_embed_converted.gif)
+
+<img src="https://github.com/helix4u/load_video_frame/blob/main/testmp4_embed_converted.gif" width="500" />
 [Full mp4 of Example Output test.mp4](https://github.com/helix4u/load_video_frame/blob/main/test.mp4)
 
 --------------------------------
+### Make 3D
 
+**Description:** Create compelling 3D stereo images from 2D originals.
+
+**Node Link:** [https://gitlab.com/srcrr/shift3d/-/raw/main/make3d.py](https://gitlab.com/srcrr/shift3d)
+
+**Example Node Graph:**  https://gitlab.com/srcrr/shift3d/-/raw/main/example-workflow.json?ref_type=heads&inline=false
+
+**Output Examples** 
+
+<img src="https://gitlab.com/srcrr/shift3d/-/raw/main/example-1.png" width="300" />
+<img src="https://gitlab.com/srcrr/shift3d/-/raw/main/example-2.png" width="300" />
+
+--------------------------------
 ### Oobabooga
 
 **Description:** asks a local LLM running in Oobabooga's Text-Generation-Webui to write a prompt based on the user input.
 
 **Link:** https://github.com/sammyf/oobabooga-node
 
-
 **Example:**
 
 "describe a new mystical  creature in its natural environment"
@@ -99,7 +214,7 @@ Generated Prompt: An enchanted weapon will be usable by any character regardless
 "The mystical creature I am describing to you is called the "Glimmerwing". It is a majestic, iridescent being that inhabits the depths of the most enchanted forests and glimmering lakes. Its body is covered in shimmering scales that reflect every color of the rainbow, and it has delicate, translucent wings that sparkle like diamonds in the sunlight. The Glimmerwing's home is a crystal-clear lake, surrounded by towering trees with leaves that shimmer like jewels. In this serene environment, the Glimmerwing spends its days swimming gracefully through the water, chasing schools of glittering fish and playing with the gentle ripples of the lake's surface.
 As the sun sets, the Glimmerwing perches on a branch of one of the trees, spreading its wings to catch the last rays of light. The creature's scales glow softly, casting a rainbow of colors across the forest floor. The Glimmerwing sings a haunting melody, its voice echoing through the stillness of the night air. Its song is said to have the power to heal the sick and bring peace to troubled souls. Those who are lucky enough to hear the Glimmerwing's song are forever changed by its beauty and grace."
 
-![glimmerwing_small](https://github.com/sammyf/oobabooga-node/assets/42468608/cecdd820-93dd-4c35-abbf-607e001fb2ed)
+<img src="https://github.com/sammyf/oobabooga-node/assets/42468608/cecdd820-93dd-4c35-abbf-607e001fb2ed" width="300" />
 
 **Requirement**
 
@@ -107,62 +222,37 @@ a Text-Generation-Webui instance (might work remotely too, but I never tried it)
 
 **Note**
 
-This node works best with SDXL models, especially as the style can be described independantly of the LLM's output.
+This node works best with SDXL models, especially as the style can be described independently of the LLM's output.
 
 --------------------------------
-### Depth Map from Wavefront OBJ
+### Prompt Tools 
 
-**Description:** Render depth maps from Wavefront .obj files (triangulated) using this simple 3D renderer utilizing numpy and matplotlib to compute and color the scene. There are simple parameters to change the FOV, camera position, and model orientation.
+**Description:** A set of InvokeAI nodes that add general prompt manipulation tools.  These were written to accompany the PromptsFromFile node and other prompt generation nodes.
 
-To be imported, an .obj must use triangulated meshes, so make sure to enable that option if exporting from a 3D modeling program. This renderer makes each triangle a solid color based on its average depth, so it will cause anomalies if your .obj has large triangles. In Blender, the Remesh modifier can be helpful to subdivide a mesh into small pieces that work well given these limitations.
+1. PromptJoin - Joins to prompts into one.
+2. PromptReplace - performs a search and replace on a prompt. With the option of using regex.
+3. PromptSplitNeg - splits a prompt into positive and negative using the old V2 method of [] for negative.
+4. PromptToFile - saves a prompt or collection of prompts to a file. one per line. There is an append/overwrite option.
+5. PTFieldsCollect - Converts image generation fields into a Json format string that can be passed to Prompt to file. 
+6. PTFieldsExpand - Takes Json string and converts it to individual generation parameters This can be fed from the Prompts to file node.
+7. PromptJoinThree -  Joins 3 prompt together.
+8. PromptStrength - This take a string and float and outputs another string in the format of (string)strength like the weighted format of compel. 
+9. PromptStrengthCombine - This takes a collection of prompt strength strings and outputs a string in the .and() or .blend() format that can be fed into a proper prompt node.
 
-**Node Link:** https://github.com/dwringer/depth-from-obj-node
+See full docs here: https://github.com/skunkworxdark/Prompt-tools-nodes/edit/main/README.md
 
-**Example Usage:**
-![depth from obj usage graph](https://raw.githubusercontent.com/dwringer/depth-from-obj-node/main/depth_from_obj_usage.jpg)
+**Node Link:** https://github.com/skunkworxdark/Prompt-tools-nodes
 
 --------------------------------
-### Enhance Image (simple adjustments)
+### Retroize
 
-**Description:** Boost or reduce color saturation, contrast, brightness, sharpness, or invert colors of any image at any stage with this simple wrapper for pillow [PIL]'s ImageEnhance module.
+**Description:** Retroize is a collection of nodes for InvokeAI to "Retroize" images. Any image can be given a fresh coat of retro paint with these nodes, either from your gallery or from within the graph itself. It includes nodes to pixelize, quantize, palettize, and ditherize images; as well as to retrieve palettes from existing images.
 
-Color inversion is toggled with a simple switch, while each of the four enhancer modes are activated by entering a value other than 1 in each corresponding input field. Values less than 1 will reduce the corresponding property, while values greater than 1 will enhance it.
+**Node Link:** https://github.com/Ar7ific1al/invokeai-retroizeinode/
 
-**Node Link:** https://github.com/dwringer/image-enhance-node
+**Retroize Output Examples**
 
-**Example Usage:**
-![enhance image usage graph](https://raw.githubusercontent.com/dwringer/image-enhance-node/main/image_enhance_usage.jpg)
-
---------------------------------
-### Generative Grammar-Based Prompt Nodes
-
-**Description:** This set of 3 nodes generates prompts from simple user-defined grammar rules (loaded from custom files - examples provided below). The prompts are made by recursively expanding a special template string, replacing nonterminal "parts-of-speech" until no more nonterminal terms remain in the string.
-
-This includes 3 Nodes:
-- *Lookup Table from File* - loads a YAML file "prompt" section (or of a whole folder of YAML's) into a JSON-ified dictionary (Lookups output)
-- *Lookups Entry from Prompt* - places a single entry in a new Lookups output under the specified heading
-- *Prompt from Lookup Table* - uses a Collection of Lookups as grammar rules from which to randomly generate prompts.
-
-**Node Link:** https://github.com/dwringer/generative-grammar-prompt-nodes
-
-**Example Usage:**
-![lookups usage example graph](https://raw.githubusercontent.com/dwringer/generative-grammar-prompt-nodes/main/lookuptables_usage.jpg)
-
---------------------------------
-### Image and Mask Composition Pack
-
-**Description:** This is a pack of nodes for composing masks and images, including a simple text mask creator and both image and latent offset nodes. The offsets wrap around, so these can be used in conjunction with the Seamless node to progressively generate centered on different parts of the seamless tiling.
-
-This includes 4 Nodes:
-- *Text Mask (simple 2D)* - create and position a white on black (or black on white) line of text using any font locally available to Invoke.
-- *Image Compositor* - Take a subject from an image with a flat backdrop and layer it on another image using a chroma key or flood select background removal.
-- *Offset Latents* - Offset a latents tensor in the vertical and/or horizontal dimensions, wrapping it around.
-- *Offset Image* - Offset an image in the vertical and/or horizontal dimensions, wrapping it around.
-
-**Node Link:** https://github.com/dwringer/composition-nodes
-
-**Example Usage:**
-![composition nodes usage graph](https://raw.githubusercontent.com/dwringer/composition-nodes/main/composition_nodes_usage.jpg)
+<img src="https://github.com/Ar7ific1al/InvokeAI_nodes_retroize/assets/2306586/de8b4fa6-324c-4c2d-b36c-297600c73974" width="500" />
 
 --------------------------------
 ### Size Stepper Nodes
@@ -174,10 +264,9 @@ A third node is included, *Random Switch (Integers)*, which is just a generic ve
 **Node Link:** https://github.com/dwringer/size-stepper-nodes
 
 **Example Usage:**
-![size stepper usage graph](https://raw.githubusercontent.com/dwringer/size-stepper-nodes/main/size_nodes_usage.jpg)
+</br><img src="https://raw.githubusercontent.com/dwringer/size-stepper-nodes/main/size_nodes_usage.jpg" width="500" />
 
 --------------------------------
-
 ### Text font to Image
 
 **Description:** text font to text image node for InvokeAI, download a font to use (or if in font cache uses it from there), the text is always resized to the image size, but can control that with padding, optional 2nd line
@@ -186,16 +275,52 @@ A third node is included, *Random Switch (Integers)*, which is just a generic ve
 
 **Output Examples**
 
-![a3609d48-d9b7-41f0-b280-063d857986fb](https://github.com/mickr777/InvokeAI/assets/115216705/c21b0af3-d9c6-4c16-9152-846a23effd36)
+<img src="https://github.com/mickr777/InvokeAI/assets/115216705/c21b0af3-d9c6-4c16-9152-846a23effd36" width="300" />
 
 Results after using the depth controlnet
 
-![9133eabb-bcda-4326-831e-1b641228b178](https://github.com/mickr777/InvokeAI/assets/115216705/915f1a53-968e-43eb-aa61-07cd8f1a733a)
-![4f9a3fa8-9be9-4236-8a3e-fcec66decd2a](https://github.com/mickr777/InvokeAI/assets/115216705/821ef89e-8a60-44f5-b94e-471a9d8690cc)
-![babd69c4-9d60-4a55-a834-5e8397f62610](https://github.com/mickr777/InvokeAI/assets/115216705/2befcb6d-49f4-4bfd-b5fc-1fee19274f89)
+<img src="https://github.com/mickr777/InvokeAI/assets/115216705/915f1a53-968e-43eb-aa61-07cd8f1a733a" width="300" />
+<img src="https://github.com/mickr777/InvokeAI/assets/115216705/821ef89e-8a60-44f5-b94e-471a9d8690cc" width="300" />
+<img src="https://github.com/mickr777/InvokeAI/assets/115216705/2befcb6d-49f4-4bfd-b5fc-1fee19274f89" width="300" />
 
 --------------------------------
+### Thresholding
 
+**Description:** This node generates masks for highlights, midtones, and shadows given an input image. You can optionally specify a blur for the lookup table used in making those masks from the source image.
+
+**Node Link:** https://github.com/JPPhoto/thresholding-node
+
+**Examples**
+
+Input:
+
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/c88ada13-fb3d-484c-a4fe-947b44712632" width="300" />
+
+Highlights/Midtones/Shadows:
+
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/727021c1-36ff-4ec8-90c8-105e00de986d" width="300" />
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/0b721bfc-f051-404e-b905-2f16b824ddfe" width="300" />
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/04c1297f-1c88-42b6-a7df-dd090b976286" width="300" />
+
+Highlights/Midtones/Shadows (with LUT blur enabled):
+
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/19aa718a-70c1-4668-8169-d68f4bd13771" width="300" />
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/0a440e43-697f-4d17-82ee-f287467df0a5" width="300" />
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/0701fd0f-2ca7-4fe2-8613-2b52547bafce" width="300" />
+
+--------------------------------
+### XY Image to Grid and Images to Grids nodes
+
+**Description:** Image to grid nodes and supporting tools.
+
+1. "Images To Grids" node - Takes a collection of images and creates a grid(s) of images. If there are more images than the size of a single grid then multiple grids will be created until it runs out of images.
+2. "XYImage To Grid" node - Converts a collection of XYImages into a labeled Grid of images. The XYImages collection has to be built using the supporting nodes. See example node setups for more details.
+
+See full docs here: https://github.com/skunkworxdark/XYGrid_nodes/edit/main/README.md
+
+**Node Link:** https://github.com/skunkworxdark/XYGrid_nodes
+
+--------------------------------
 ### Example Node Template
 
 **Description:** This node allows you to do super cool things with InvokeAI.
@@ -206,7 +331,7 @@ Results after using the depth controlnet
 
 **Output Examples** 
 
-![Example Image](https://invoke-ai.github.io/InvokeAI/assets/invoke_ai_banner.png){: style="height:115px;width:240px"}
+</br><img src="https://invoke-ai.github.io/InvokeAI/assets/invoke_ai_banner.png" width="500" />
 
 
 ## Disclaimer

docs/nodes/defaultNodes.md

@@ -1,6 +1,6 @@
 # List of Default Nodes
 
-The table below contains a list of the default nodes shipped with InvokeAI and their descriptions. 
+The table below contains a list of the default nodes shipped with InvokeAI and their descriptions.
 
 | Node <img width=160 align="right"> | Function                                                                              |
 |: ---------------------------------- | :--------------------------------------------------------------------------------------|
@@ -17,11 +17,12 @@ The table below contains a list of the default nodes shipped with InvokeAI and t
 |Conditioning Primitive 			| A conditioning tensor primitive value|
 |Content Shuffle Processor 			| Applies content shuffle processing to image|
 |ControlNet 			| Collects ControlNet info to pass to other nodes|
-|OpenCV Inpaint 			| Simple inpaint using opencv.|
 |Denoise Latents 			| Denoises noisy latents to decodable images|
 |Divide Integers 			| Divides two numbers|
 |Dynamic Prompt 			| Parses a prompt using adieyal/dynamicprompts' random or combinatorial generator|
-|Upscale (RealESRGAN) 			| Upscales an image using RealESRGAN.|
+|[FaceMask](./detailedNodes/faceTools.md#facemask) | Generates masks for faces in an image to use with Inpainting|
+|[FaceIdentifier](./detailedNodes/faceTools.md#faceidentifier)             | Identifies and labels faces in an image|
+|[FaceOff](./detailedNodes/faceTools.md#faceoff)             | Creates a new image that is a scaled bounding box with a mask on the face for Inpainting|
 |Float Math             | Perform basic math operations on two floats|
 |Float Primitive Collection 			| A collection of float primitive values|
 |Float Primitive 			| A float primitive value|
@@ -76,6 +77,7 @@ The table below contains a list of the default nodes shipped with InvokeAI and t
 |ONNX Prompt (Raw) 			| A node to process inputs and produce outputs. May use dependency injection in __init__ to receive providers.|
 |ONNX Text to Latents 			| Generates latents from conditionings.|
 |ONNX Model Loader 			| Loads a main model, outputting its submodels.|
+|OpenCV Inpaint 			| Simple inpaint using opencv.|
 |Openpose Processor 			| Applies Openpose processing to image|
 |PIDI Processor 			| Applies PIDI processing to image|
 |Prompts from File 			| Loads prompts from a text file|
@@ -97,5 +99,6 @@ The table below contains a list of the default nodes shipped with InvokeAI and t
 |String Primitive 			| A string primitive value|
 |Subtract Integers 			| Subtracts two numbers|
 |Tile Resample Processor 			| Tile resampler processor|
+|Upscale (RealESRGAN) 			| Upscales an image using RealESRGAN.|
 |VAE Loader 			| Loads a VAE model, outputting a VaeLoaderOutput|
 |Zoe (Depth) Processor 			| Applies Zoe depth processing to image|

docs/nodes/detailedNodes/faceTools.md

@@ -0,0 +1,154 @@
+# Face Nodes
+
+## FaceOff
+
+FaceOff mimics a user finding a face in an image and resizing the bounding box
+around the head in Canvas.
+
+Enter a face ID (found with FaceIdentifier) to choose which face to mask.
+
+Just as you would add more context inside the bounding box by making it larger
+in Canvas, the node gives you a padding input (in pixels) which will
+simultaneously add more context, and increase the resolution of the bounding box
+so the face remains the same size inside it.
+
+The "Minimum Confidence" input defaults to 0.5 (50%), and represents a pass/fail
+threshold a detected face must reach for it to be processed. Lowering this value
+may help if detection is failing. If the detected masks are imperfect and stray
+too far outside/inside of faces, the node gives you X & Y offsets to shrink/grow
+the masks by a multiplier.
+
+FaceOff will output the face in a bounded image, taking the face off of the
+original image for input into any node that accepts image inputs. The node also
+outputs a face mask with the dimensions of the bounded image. The X & Y outputs
+are for connecting to the X & Y inputs of the Paste Image node, which will place
+the bounded image back on the original image using these coordinates.
+
+###### Inputs/Outputs
+
+| Input              | Description                                                                                                                                                                              |
+| ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Image              | Image for face detection                                                                                                                                                                 |
+| Face ID            | The face ID to process, numbered from 0. Multiple faces not supported. Find a face's ID with FaceIdentifier node.                                                                        |
+| Minimum Confidence | Minimum confidence for face detection (lower if detection is failing)                                                                                                                    |
+| X Offset           | X-axis offset of the mask                                                                                                                                                                |
+| Y Offset           | Y-axis offset of the mask                                                                                                                                                                |
+| Padding            | All-axis padding around the mask in pixels                                                                                                                                               |
+| Chunk              | Chunk (or divide) the image into sections to greatly improve face detection success. Defaults to off, but will activate if no faces are detected normally. Activate to chunk by default. |
+
+| Output        | Description                                      |
+| ------------- | ------------------------------------------------ |
+| Bounded Image | Original image bound, cropped, and resized       |
+| Width         | The width of the bounded image in pixels         |
+| Height        | The height of the bounded image in pixels        |
+| Mask          | The output mask                                  |
+| X             | The x coordinate of the bounding box's left side |
+| Y             | The y coordinate of the bounding box's top side  |
+
+## FaceMask
+
+FaceMask mimics a user drawing masks on faces in an image in Canvas.
+
+The "Face IDs" input allows the user to select specific faces to be masked.
+Leave empty to detect and mask all faces, or a comma-separated list for a
+specific combination of faces (ex: `1,2,4`). A single integer will detect and
+mask that specific face. Find face IDs with the FaceIdentifier node.
+
+The "Minimum Confidence" input defaults to 0.5 (50%), and represents a pass/fail
+threshold a detected face must reach for it to be processed. Lowering this value
+may help if detection is failing.
+
+If the detected masks are imperfect and stray too far outside/inside of faces,
+the node gives you X & Y offsets to shrink/grow the masks by a multiplier. All
+masks shrink/grow together by the X & Y offset values.
+
+By default, masks are created to change faces. When masks are inverted, they
+change surrounding areas, protecting faces.
+
+###### Inputs/Outputs
+
+| Input              | Description                                                                                                                                                                              |
+| ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Image              | Image for face detection                                                                                                                                                                 |
+| Face IDs           | Comma-separated list of face ids to mask eg '0,2,7'. Numbered from 0. Leave empty to mask all. Find face IDs with FaceIdentifier node.                                                   |
+| Minimum Confidence | Minimum confidence for face detection (lower if detection is failing)                                                                                                                    |
+| X Offset           | X-axis offset of the mask                                                                                                                                                                |
+| Y Offset           | Y-axis offset of the mask                                                                                                                                                                |
+| Chunk              | Chunk (or divide) the image into sections to greatly improve face detection success. Defaults to off, but will activate if no faces are detected normally. Activate to chunk by default. |
+| Invert Mask        | Toggle to invert the face mask                                                                                                                                                           |
+
+| Output | Description                       |
+| ------ | --------------------------------- |
+| Image  | The original image                |
+| Width  | The width of the image in pixels  |
+| Height | The height of the image in pixels |
+| Mask   | The output face mask              |
+
+## FaceIdentifier
+
+FaceIdentifier outputs an image with detected face IDs printed in white numbers
+onto each face.
+
+Face IDs can then be used in FaceMask and FaceOff to selectively mask all, a
+specific combination, or single faces.
+
+The FaceIdentifier output image is generated for user reference, and isn't meant
+to be passed on to other image-processing nodes.
+
+The "Minimum Confidence" input defaults to 0.5 (50%), and represents a pass/fail
+threshold a detected face must reach for it to be processed. Lowering this value
+may help if detection is failing. If an image is changed in the slightest, run
+it through FaceIdentifier again to get updated FaceIDs.
+
+###### Inputs/Outputs
+
+| Input              | Description                                                                                                                                                                              |
+| ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Image              | Image for face detection                                                                                                                                                                 |
+| Minimum Confidence | Minimum confidence for face detection (lower if detection is failing)                                                                                                                    |
+| Chunk              | Chunk (or divide) the image into sections to greatly improve face detection success. Defaults to off, but will activate if no faces are detected normally. Activate to chunk by default. |
+
+| Output | Description                                                                                      |
+| ------ | ------------------------------------------------------------------------------------------------ |
+| Image  | The original image with small face ID numbers printed in white onto each face for user reference |
+| Width  | The width of the original image in pixels                                                        |
+| Height | The height of the original image in pixels                                                       |
+
+## Tips
+
+- If not all target faces are being detected, activate Chunk to bypass full
+  image face detection and greatly improve detection success.
+- Final results will vary between full-image detection and chunking for faces
+  that are detectable by both due to the nature of the process. Try either to
+  your taste.
+- Be sure Minimum Confidence is set the same when using FaceIdentifier with
+  FaceOff/FaceMask.
+- For FaceOff, use the color correction node before faceplace to correct edges
+  being noticeable in the final image (see example screenshot).
+- Non-inpainting models may struggle to paint/generate correctly around faces.
+- If your face won't change the way you want it to no matter what you change,
+  consider that the change you're trying to make is too much at that resolution.
+  For example, if an image is only 512x768 total, the face might only be 128x128
+  or 256x256, much smaller than the 512x512 your SD1.5 model was probably
+  trained on. Try increasing the resolution of the image by upscaling or
+  resizing, add padding to increase the bounding box's resolution, or use an
+  image where the face takes up more pixels.
+- If the resulting face seems out of place pasted back on the original image
+  (ie. too large, not proportional), add more padding on the FaceOff node to
+  give inpainting more context. Context and good prompting are important to
+  keeping things proportional.
+- If you find the mask is too big/small and going too far outside/inside the
+  area you want to affect, adjust the x & y offsets to shrink/grow the mask area
+- Use a higher denoise start value to resemble aspects of the original face or
+  surroundings. Denoise start = 0 & denoise end = 1 will make something new,
+  while denoise start = 0.50 & denoise end = 1 will be 50% old and 50% new.
+- mediapipe isn't good at detecting faces with lots of face paint, hair covering
+  the face, etc. Anything that obstructs the face will likely result in no faces
+  being detected.
+- If you find your face isn't being detected, try lowering the minimum
+  confidence value from 0.5. This could result in false positives, however
+  (random areas being detected as faces and masked).
+- After altering an image and wanting to process a different face in the newly
+  altered image, run the altered image through FaceIdentifier again to see the
+  new Face IDs. MediaPipe will most likely detect faces in a different order
+  after an image has been changed in the slightest.

docs/nodes/exampleWorkflows.md

@@ -9,5 +9,6 @@ If you're interested in finding more workflows, checkout the [#share-your-workfl
 * [SD1.5 / SD2 Text to Image](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/Text_to_Image.json)
 * [SDXL Text to Image](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/SDXL_Text_to_Image.json)
 * [SDXL (with Refiner) Text to Image](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/SDXL_Text_to_Image.json) 
-* [Tiled Upscaling with ControlNet](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/ESRGAN_img2img_upscale w_Canny_ControlNet.json)ß
-
+* [Tiled Upscaling with ControlNet](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/ESRGAN_img2img_upscale w_Canny_ControlNet.json)
+* [FaceMask](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/FaceMask.json)
+* [FaceOff with 2x Face Scaling](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/FaceOff_FaceScale2x.json)

installer/lib/installer.py

@@ -332,6 +332,7 @@ class InvokeAiInstance:
         Configure the InvokeAI runtime directory
         """
 
+        auto_install = False
         # set sys.argv to a consistent state
         new_argv = [sys.argv[0]]
         for i in range(1, len(sys.argv)):
@@ -340,13 +341,17 @@ class InvokeAiInstance:
                 new_argv.append(el)
                 new_argv.append(sys.argv[i + 1])
             elif el in ["-y", "--yes", "--yes-to-all"]:
-                new_argv.append(el)
+                auto_install = True
         sys.argv = new_argv
 
+        import messages
         import requests  # to catch download exceptions
-        from messages import introduction
 
-        introduction()
+        auto_install = auto_install or messages.user_wants_auto_configuration()
+        if auto_install:
+            sys.argv.append("--yes")
+        else:
+            messages.introduction()
 
         from invokeai.frontend.install.invokeai_configure import invokeai_configure
 

installer/lib/messages.py

@@ -7,7 +7,7 @@ import os
 import platform
 from pathlib import Path
 
-from prompt_toolkit import prompt
+from prompt_toolkit import HTML, prompt
 from prompt_toolkit.completion import PathCompleter
 from prompt_toolkit.validation import Validator
 from rich import box, print
@@ -65,17 +65,50 @@ def confirm_install(dest: Path) -> bool:
     if dest.exists():
         print(f":exclamation: Directory {dest} already exists :exclamation:")
         dest_confirmed = Confirm.ask(
-            ":stop_sign: Are you sure you want to (re)install in this location?",
+            ":stop_sign: (re)install in this location?",
             default=False,
         )
     else:
         print(f"InvokeAI will be installed in {dest}")
-        dest_confirmed = not Confirm.ask("Would you like to pick a different location?", default=False)
+        dest_confirmed = Confirm.ask("Use this location?", default=True)
     console.line()
 
     return dest_confirmed
 
 
+def user_wants_auto_configuration() -> bool:
+    """Prompt the user to choose between manual and auto configuration."""
+    console.rule("InvokeAI Configuration Section")
+    console.print(
+        Panel(
+            Group(
+                "\n".join(
+                    [
+                        "Libraries are installed and InvokeAI will now set up its root directory and configuration. Choose between:",
+                        "",
+                        "  * AUTOMATIC configuration:  install reasonable defaults and a minimal set of starter models.",
+                        "  * MANUAL configuration: manually inspect and adjust configuration options and pick from a larger set of starter models.",
+                        "",
+                        "Later you can fine tune your configuration by selecting option [6] 'Change InvokeAI startup options' from the invoke.bat/invoke.sh launcher script.",
+                    ]
+                ),
+            ),
+            box=box.MINIMAL,
+            padding=(1, 1),
+        )
+    )
+    choice = (
+        prompt(
+            HTML("Choose <b>&lt;a&gt;</b>utomatic or <b>&lt;m&gt;</b>anual configuration [a/m] (a): "),
+            validator=Validator.from_callable(
+                lambda n: n == "" or n.startswith(("a", "A", "m", "M")), error_message="Please select 'a' or 'm'"
+            ),
+        )
+        or "a"
+    )
+    return choice.lower().startswith("a")
+
+
 def dest_path(dest=None) -> Path:
     """
     Prompt the user for the destination path and create the path

installer/templates/invoke.bat.in

@@ -17,9 +17,10 @@ echo 6. Change InvokeAI startup options
 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
+echo 10. Run the InvokeAI image database maintenance script
+echo 11. Command-line help
 echo Q - Quit
-set /P choice="Please enter 1-10, Q: [1] "
+set /P choice="Please enter 1-11, Q: [1] "
 if not defined choice set choice=1
 IF /I "%choice%" == "1" (
     echo Starting the InvokeAI browser-based UI..
@@ -58,8 +59,11 @@ IF /I "%choice%" == "1" (
    echo Running invokeai-update...
    python -m invokeai.frontend.install.invokeai_update
 ) ELSE IF /I "%choice%" == "10" (
+   echo Running the db maintenance script...
+   python .venv\Scripts\invokeai-db-maintenance.exe
+) ELSE IF /I "%choice%" == "11" (
     echo Displaying command line help...
-    python .venv\Scripts\invokeai.exe --help %*
+    python .venv\Scripts\invokeai-web.exe --help %*
     pause
     exit /b
 ) ELSE IF /I "%choice%" == "q" (

installer/templates/invoke.sh.in

@@ -46,6 +46,9 @@ if [ "$(uname -s)" == "Darwin" ]; then
     export PYTORCH_ENABLE_MPS_FALLBACK=1
 fi
 
+# Avoid glibc memory fragmentation. See invokeai/backend/model_management/README.md for details.
+export MALLOC_MMAP_THRESHOLD_=1048576
+
 # Primary function for the case statement to determine user input
 do_choice() {
     case $1 in
@@ -97,13 +100,13 @@ do_choice() {
         ;;
     10)
         clear
-        printf "Command-line help\n"
-        invokeai --help
+        printf "Running the db maintenance script\n"
+        invokeai-db-maintenance --root ${INVOKEAI_ROOT}
         ;;
-    "HELP 1")
+    11)
         clear
         printf "Command-line help\n"
-        invokeai --help
+        invokeai-web --help
         ;;
     *)
         clear
@@ -125,7 +128,10 @@ do_dialog() {
         6 "Change InvokeAI startup options"
         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")
+        9 "Update InvokeAI"
+	10 "Run the InvokeAI image database maintenance script"
+	11 "Command-line help"
+    )
 
     choice=$(dialog --clear \
         --backtitle "\Zb\Zu\Z3InvokeAI" \
@@ -157,9 +163,10 @@ do_line_input() {
     printf "7: Re-run the configure script to fix a broken install\n"
     printf "8: Open the developer console\n"
     printf "9: Update InvokeAI\n"
-    printf "10: Command-line help\n"
+    printf "10: Run the InvokeAI image database maintenance script\n"
+    printf "11: Command-line help\n"
     printf "Q: Quit\n\n"
-    read -p "Please enter 1-10, Q: [1] " yn
+    read -p "Please enter 1-11, Q: [1] " yn
     choice=${yn:='1'}
     do_choice $choice
     clear

invokeai/app/api/dependencies.py

@@ -1,5 +1,6 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
+import sqlite3
 from logging import Logger
 
 from invokeai.app.services.board_image_record_storage import SqliteBoardImageRecordStorage
@@ -9,7 +10,10 @@ from invokeai.app.services.boards import BoardService, BoardServiceDependencies
 from invokeai.app.services.config import InvokeAIAppConfig
 from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
 from invokeai.app.services.images import ImageService, ImageServiceDependencies
+from invokeai.app.services.invocation_cache.invocation_cache_memory import MemoryInvocationCache
 from invokeai.app.services.resource_name import SimpleNameService
+from invokeai.app.services.session_processor.session_processor_default import DefaultSessionProcessor
+from invokeai.app.services.session_queue.session_queue_sqlite import SqliteSessionQueue
 from invokeai.app.services.urls import LocalUrlService
 from invokeai.backend.util.logging import InvokeAILogger
 from invokeai.version.invokeai_version import __version__
@@ -25,6 +29,7 @@ from ..services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsSto
 from ..services.model_manager_service import ModelManagerService
 from ..services.processor import DefaultInvocationProcessor
 from ..services.sqlite import SqliteItemStorage
+from ..services.thread import lock
 from .events import FastAPIEventService
 
 
@@ -44,7 +49,7 @@ def check_internet() -> bool:
         return False
 
 
-logger = InvokeAILogger.getLogger()
+logger = InvokeAILogger.get_logger()
 
 
 class ApiDependencies:
@@ -63,22 +68,32 @@ class ApiDependencies:
         output_folder = config.output_path
 
         # TODO: build a file/path manager?
-        db_path = config.db_path
-        db_path.parent.mkdir(parents=True, exist_ok=True)
-        db_location = str(db_path)
+        if config.use_memory_db:
+            db_location = ":memory:"
+        else:
+            db_path = config.db_path
+            db_path.parent.mkdir(parents=True, exist_ok=True)
+            db_location = str(db_path)
+
+        logger.info(f"Using database at {db_location}")
+        db_conn = sqlite3.connect(db_location, check_same_thread=False)  # TODO: figure out a better threading solution
+
+        if config.log_sql:
+            db_conn.set_trace_callback(print)
+        db_conn.execute("PRAGMA foreign_keys = ON;")
 
         graph_execution_manager = SqliteItemStorage[GraphExecutionState](
-            filename=db_location, table_name="graph_executions"
+            conn=db_conn, table_name="graph_executions", lock=lock
         )
 
         urls = LocalUrlService()
-        image_record_storage = SqliteImageRecordStorage(db_location)
+        image_record_storage = SqliteImageRecordStorage(conn=db_conn, lock=lock)
         image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
         names = SimpleNameService()
         latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f"{output_folder}/latents"))
 
-        board_record_storage = SqliteBoardRecordStorage(db_location)
-        board_image_record_storage = SqliteBoardImageRecordStorage(db_location)
+        board_record_storage = SqliteBoardRecordStorage(conn=db_conn, lock=lock)
+        board_image_record_storage = SqliteBoardImageRecordStorage(conn=db_conn, lock=lock)
 
         boards = BoardService(
             services=BoardServiceDependencies(
@@ -120,18 +135,29 @@ class ApiDependencies:
             boards=boards,
             board_images=board_images,
             queue=MemoryInvocationQueue(),
-            graph_library=SqliteItemStorage[LibraryGraph](filename=db_location, table_name="graphs"),
+            graph_library=SqliteItemStorage[LibraryGraph](conn=db_conn, lock=lock, table_name="graphs"),
             graph_execution_manager=graph_execution_manager,
             processor=DefaultInvocationProcessor(),
             configuration=config,
             performance_statistics=InvocationStatsService(graph_execution_manager),
             logger=logger,
+            session_queue=SqliteSessionQueue(conn=db_conn, lock=lock),
+            session_processor=DefaultSessionProcessor(),
+            invocation_cache=MemoryInvocationCache(max_cache_size=config.node_cache_size),
         )
 
         create_system_graphs(services.graph_library)
 
         ApiDependencies.invoker = Invoker(services)
 
+        try:
+            lock.acquire()
+            db_conn.execute("VACUUM;")
+            db_conn.commit()
+            logger.info("Cleaned database")
+        finally:
+            lock.release()
+
     @staticmethod
     def shutdown():
         if ApiDependencies.invoker:

invokeai/app/api/routers/app_info.py

@@ -7,6 +7,7 @@ from fastapi.routing import APIRouter
 from pydantic import BaseModel, Field
 
 from invokeai.app.invocations.upscale import ESRGAN_MODELS
+from invokeai.app.services.invocation_cache.invocation_cache_common import InvocationCacheStatus
 from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark
 from invokeai.backend.image_util.patchmatch import PatchMatch
 from invokeai.backend.image_util.safety_checker import SafetyChecker
@@ -103,3 +104,43 @@ async def set_log_level(
     """Sets the log verbosity level"""
     ApiDependencies.invoker.services.logger.setLevel(level)
     return LogLevel(ApiDependencies.invoker.services.logger.level)
+
+
+@app_router.delete(
+    "/invocation_cache",
+    operation_id="clear_invocation_cache",
+    responses={200: {"description": "The operation was successful"}},
+)
+async def clear_invocation_cache() -> None:
+    """Clears the invocation cache"""
+    ApiDependencies.invoker.services.invocation_cache.clear()
+
+
+@app_router.put(
+    "/invocation_cache/enable",
+    operation_id="enable_invocation_cache",
+    responses={200: {"description": "The operation was successful"}},
+)
+async def enable_invocation_cache() -> None:
+    """Clears the invocation cache"""
+    ApiDependencies.invoker.services.invocation_cache.enable()
+
+
+@app_router.put(
+    "/invocation_cache/disable",
+    operation_id="disable_invocation_cache",
+    responses={200: {"description": "The operation was successful"}},
+)
+async def disable_invocation_cache() -> None:
+    """Clears the invocation cache"""
+    ApiDependencies.invoker.services.invocation_cache.disable()
+
+
+@app_router.get(
+    "/invocation_cache/status",
+    operation_id="get_invocation_cache_status",
+    responses={200: {"model": InvocationCacheStatus}},
+)
+async def get_invocation_cache_status() -> InvocationCacheStatus:
+    """Clears the invocation cache"""
+    return ApiDependencies.invoker.services.invocation_cache.get_status()

invokeai/app/api/routers/images.py

@@ -322,3 +322,20 @@ async def unstar_images_in_list(
         return ImagesUpdatedFromListResult(updated_image_names=updated_image_names)
     except Exception:
         raise HTTPException(status_code=500, detail="Failed to unstar images")
+
+
+class ImagesDownloaded(BaseModel):
+    response: Optional[str] = Field(
+        description="If defined, the message to display to the user when images begin downloading"
+    )
+
+
+@images_router.post("/download", operation_id="download_images_from_list", response_model=ImagesDownloaded)
+async def download_images_from_list(
+    image_names: list[str] = Body(description="The list of names of images to download", embed=True),
+    board_id: Optional[str] = Body(
+        default=None, description="The board from which image should be downloaded from", embed=True
+    ),
+) -> ImagesDownloaded:
+    # return ImagesDownloaded(response="Your images are downloading")
+    raise HTTPException(status_code=501, detail="Endpoint is not yet implemented")

invokeai/app/api/routers/models.py

@@ -146,7 +146,8 @@ async def update_model(
 async def import_model(
     location: str = Body(description="A model path, repo_id or URL to import"),
     prediction_type: Optional[Literal["v_prediction", "epsilon", "sample"]] = Body(
-        description="Prediction type for SDv2 checkpoint files", default="v_prediction"
+        description="Prediction type for SDv2 checkpoints and rare SDv1 checkpoints",
+        default=None,
     ),
 ) -> ImportModelResponse:
     """Add a model using its local path, repo_id, or remote URL. Model characteristics will be probed and configured automatically"""

invokeai/app/api/routers/session_queue.py

@@ -0,0 +1,247 @@
+from typing import Optional
+
+from fastapi import Body, Path, Query
+from fastapi.routing import APIRouter
+from pydantic import BaseModel
+
+from invokeai.app.services.session_processor.session_processor_common import SessionProcessorStatus
+from invokeai.app.services.session_queue.session_queue_common import (
+    QUEUE_ITEM_STATUS,
+    Batch,
+    BatchStatus,
+    CancelByBatchIDsResult,
+    ClearResult,
+    EnqueueBatchResult,
+    EnqueueGraphResult,
+    PruneResult,
+    SessionQueueItem,
+    SessionQueueItemDTO,
+    SessionQueueStatus,
+)
+from invokeai.app.services.shared.models import CursorPaginatedResults
+
+from ...services.graph import Graph
+from ..dependencies import ApiDependencies
+
+session_queue_router = APIRouter(prefix="/v1/queue", tags=["queue"])
+
+
+class SessionQueueAndProcessorStatus(BaseModel):
+    """The overall status of session queue and processor"""
+
+    queue: SessionQueueStatus
+    processor: SessionProcessorStatus
+
+
+@session_queue_router.post(
+    "/{queue_id}/enqueue_graph",
+    operation_id="enqueue_graph",
+    responses={
+        201: {"model": EnqueueGraphResult},
+    },
+)
+async def enqueue_graph(
+    queue_id: str = Path(description="The queue id to perform this operation on"),
+    graph: Graph = Body(description="The graph to enqueue"),
+    prepend: bool = Body(default=False, description="Whether or not to prepend this batch in the queue"),
+) -> EnqueueGraphResult:
+    """Enqueues a graph for single execution."""
+
+    return ApiDependencies.invoker.services.session_queue.enqueue_graph(queue_id=queue_id, graph=graph, prepend=prepend)
+
+
+@session_queue_router.post(
+    "/{queue_id}/enqueue_batch",
+    operation_id="enqueue_batch",
+    responses={
+        201: {"model": EnqueueBatchResult},
+    },
+)
+async def enqueue_batch(
+    queue_id: str = Path(description="The queue id to perform this operation on"),
+    batch: Batch = Body(description="Batch to process"),
+    prepend: bool = Body(default=False, description="Whether or not to prepend this batch in the queue"),
+) -> EnqueueBatchResult:
+    """Processes a batch and enqueues the output graphs for execution."""
+
+    return ApiDependencies.invoker.services.session_queue.enqueue_batch(queue_id=queue_id, batch=batch, prepend=prepend)
+
+
+@session_queue_router.get(
+    "/{queue_id}/list",
+    operation_id="list_queue_items",
+    responses={
+        200: {"model": CursorPaginatedResults[SessionQueueItemDTO]},
+    },
+)
+async def list_queue_items(
+    queue_id: str = Path(description="The queue id to perform this operation on"),
+    limit: int = Query(default=50, description="The number of items to fetch"),
+    status: Optional[QUEUE_ITEM_STATUS] = Query(default=None, description="The status of items to fetch"),
+    cursor: Optional[int] = Query(default=None, description="The pagination cursor"),
+    priority: int = Query(default=0, description="The pagination cursor priority"),
+) -> CursorPaginatedResults[SessionQueueItemDTO]:
+    """Gets all queue items (without graphs)"""
+
+    return ApiDependencies.invoker.services.session_queue.list_queue_items(
+        queue_id=queue_id, limit=limit, status=status, cursor=cursor, priority=priority
+    )
+
+
+@session_queue_router.put(
+    "/{queue_id}/processor/resume",
+    operation_id="resume",
+    responses={200: {"model": SessionProcessorStatus}},
+)
+async def resume(
+    queue_id: str = Path(description="The queue id to perform this operation on"),
+) -> SessionProcessorStatus:
+    """Resumes session processor"""
+    return ApiDependencies.invoker.services.session_processor.resume()
+
+
+@session_queue_router.put(
+    "/{queue_id}/processor/pause",
+    operation_id="pause",
+    responses={200: {"model": SessionProcessorStatus}},
+)
+async def Pause(
+    queue_id: str = Path(description="The queue id to perform this operation on"),
+) -> SessionProcessorStatus:
+    """Pauses session processor"""
+    return ApiDependencies.invoker.services.session_processor.pause()
+
+
+@session_queue_router.put(
+    "/{queue_id}/cancel_by_batch_ids",
+    operation_id="cancel_by_batch_ids",
+    responses={200: {"model": CancelByBatchIDsResult}},
+)
+async def cancel_by_batch_ids(
+    queue_id: str = Path(description="The queue id to perform this operation on"),
+    batch_ids: list[str] = Body(description="The list of batch_ids to cancel all queue items for", embed=True),
+) -> CancelByBatchIDsResult:
+    """Immediately cancels all queue items from the given batch ids"""
+    return ApiDependencies.invoker.services.session_queue.cancel_by_batch_ids(queue_id=queue_id, batch_ids=batch_ids)
+
+
+@session_queue_router.put(
+    "/{queue_id}/clear",
+    operation_id="clear",
+    responses={
+        200: {"model": ClearResult},
+    },
+)
+async def clear(
+    queue_id: str = Path(description="The queue id to perform this operation on"),
+) -> ClearResult:
+    """Clears the queue entirely, immediately canceling the currently-executing session"""
+    queue_item = ApiDependencies.invoker.services.session_queue.get_current(queue_id)
+    if queue_item is not None:
+        ApiDependencies.invoker.services.session_queue.cancel_queue_item(queue_item.item_id)
+    clear_result = ApiDependencies.invoker.services.session_queue.clear(queue_id)
+    return clear_result
+
+
+@session_queue_router.put(
+    "/{queue_id}/prune",
+    operation_id="prune",
+    responses={
+        200: {"model": PruneResult},
+    },
+)
+async def prune(
+    queue_id: str = Path(description="The queue id to perform this operation on"),
+) -> PruneResult:
+    """Prunes all completed or errored queue items"""
+    return ApiDependencies.invoker.services.session_queue.prune(queue_id)
+
+
+@session_queue_router.get(
+    "/{queue_id}/current",
+    operation_id="get_current_queue_item",
+    responses={
+        200: {"model": Optional[SessionQueueItem]},
+    },
+)
+async def get_current_queue_item(
+    queue_id: str = Path(description="The queue id to perform this operation on"),
+) -> Optional[SessionQueueItem]:
+    """Gets the currently execution queue item"""
+    return ApiDependencies.invoker.services.session_queue.get_current(queue_id)
+
+
+@session_queue_router.get(
+    "/{queue_id}/next",
+    operation_id="get_next_queue_item",
+    responses={
+        200: {"model": Optional[SessionQueueItem]},
+    },
+)
+async def get_next_queue_item(
+    queue_id: str = Path(description="The queue id to perform this operation on"),
+) -> Optional[SessionQueueItem]:
+    """Gets the next queue item, without executing it"""
+    return ApiDependencies.invoker.services.session_queue.get_next(queue_id)
+
+
+@session_queue_router.get(
+    "/{queue_id}/status",
+    operation_id="get_queue_status",
+    responses={
+        200: {"model": SessionQueueAndProcessorStatus},
+    },
+)
+async def get_queue_status(
+    queue_id: str = Path(description="The queue id to perform this operation on"),
+) -> SessionQueueAndProcessorStatus:
+    """Gets the status of the session queue"""
+    queue = ApiDependencies.invoker.services.session_queue.get_queue_status(queue_id)
+    processor = ApiDependencies.invoker.services.session_processor.get_status()
+    return SessionQueueAndProcessorStatus(queue=queue, processor=processor)
+
+
+@session_queue_router.get(
+    "/{queue_id}/b/{batch_id}/status",
+    operation_id="get_batch_status",
+    responses={
+        200: {"model": BatchStatus},
+    },
+)
+async def get_batch_status(
+    queue_id: str = Path(description="The queue id to perform this operation on"),
+    batch_id: str = Path(description="The batch to get the status of"),
+) -> BatchStatus:
+    """Gets the status of the session queue"""
+    return ApiDependencies.invoker.services.session_queue.get_batch_status(queue_id=queue_id, batch_id=batch_id)
+
+
+@session_queue_router.get(
+    "/{queue_id}/i/{item_id}",
+    operation_id="get_queue_item",
+    responses={
+        200: {"model": SessionQueueItem},
+    },
+)
+async def get_queue_item(
+    queue_id: str = Path(description="The queue id to perform this operation on"),
+    item_id: int = Path(description="The queue item to get"),
+) -> SessionQueueItem:
+    """Gets a queue item"""
+    return ApiDependencies.invoker.services.session_queue.get_queue_item(item_id)
+
+
+@session_queue_router.put(
+    "/{queue_id}/i/{item_id}/cancel",
+    operation_id="cancel_queue_item",
+    responses={
+        200: {"model": SessionQueueItem},
+    },
+)
+async def cancel_queue_item(
+    queue_id: str = Path(description="The queue id to perform this operation on"),
+    item_id: int = Path(description="The queue item to cancel"),
+) -> SessionQueueItem:
+    """Deletes a queue item"""
+
+    return ApiDependencies.invoker.services.session_queue.cancel_queue_item(item_id)

invokeai/app/api/routers/sessions.py

@@ -23,12 +23,14 @@ session_router = APIRouter(prefix="/v1/sessions", tags=["sessions"])
         200: {"model": GraphExecutionState},
         400: {"description": "Invalid json"},
     },
+    deprecated=True,
 )
 async def create_session(
-    graph: Optional[Graph] = Body(default=None, description="The graph to initialize the session with")
+    queue_id: str = Query(default="", description="The id of the queue to associate the session with"),
+    graph: Optional[Graph] = Body(default=None, description="The graph to initialize the session with"),
 ) -> GraphExecutionState:
     """Creates a new session, optionally initializing it with an invocation graph"""
-    session = ApiDependencies.invoker.create_execution_state(graph)
+    session = ApiDependencies.invoker.create_execution_state(queue_id=queue_id, graph=graph)
     return session
 
 
@@ -36,6 +38,7 @@ async def create_session(
     "/",
     operation_id="list_sessions",
     responses={200: {"model": PaginatedResults[GraphExecutionState]}},
+    deprecated=True,
 )
 async def list_sessions(
     page: int = Query(default=0, description="The page of results to get"),
@@ -57,6 +60,7 @@ async def list_sessions(
         200: {"model": GraphExecutionState},
         404: {"description": "Session not found"},
     },
+    deprecated=True,
 )
 async def get_session(
     session_id: str = Path(description="The id of the session to get"),
@@ -77,6 +81,7 @@ async def get_session(
         400: {"description": "Invalid node or link"},
         404: {"description": "Session not found"},
     },
+    deprecated=True,
 )
 async def add_node(
     session_id: str = Path(description="The id of the session"),
@@ -109,6 +114,7 @@ async def add_node(
         400: {"description": "Invalid node or link"},
         404: {"description": "Session not found"},
     },
+    deprecated=True,
 )
 async def update_node(
     session_id: str = Path(description="The id of the session"),
@@ -142,6 +148,7 @@ async def update_node(
         400: {"description": "Invalid node or link"},
         404: {"description": "Session not found"},
     },
+    deprecated=True,
 )
 async def delete_node(
     session_id: str = Path(description="The id of the session"),
@@ -172,6 +179,7 @@ async def delete_node(
         400: {"description": "Invalid node or link"},
         404: {"description": "Session not found"},
     },
+    deprecated=True,
 )
 async def add_edge(
     session_id: str = Path(description="The id of the session"),
@@ -203,6 +211,7 @@ async def add_edge(
         400: {"description": "Invalid node or link"},
         404: {"description": "Session not found"},
     },
+    deprecated=True,
 )
 async def delete_edge(
     session_id: str = Path(description="The id of the session"),
@@ -241,8 +250,10 @@ async def delete_edge(
         400: {"description": "The session has no invocations ready to invoke"},
         404: {"description": "Session not found"},
     },
+    deprecated=True,
 )
 async def invoke_session(
+    queue_id: str = Query(description="The id of the queue to associate the session with"),
     session_id: str = Path(description="The id of the session to invoke"),
     all: bool = Query(default=False, description="Whether or not to invoke all remaining invocations"),
 ) -> Response:
@@ -254,7 +265,7 @@ async def invoke_session(
     if session.is_complete():
         raise HTTPException(status_code=400)
 
-    ApiDependencies.invoker.invoke(session, invoke_all=all)
+    ApiDependencies.invoker.invoke(queue_id, session, invoke_all=all)
     return Response(status_code=202)
 
 
@@ -262,6 +273,7 @@ async def invoke_session(
     "/{session_id}/invoke",
     operation_id="cancel_session_invoke",
     responses={202: {"description": "The invocation is canceled"}},
+    deprecated=True,
 )
 async def cancel_session_invoke(
     session_id: str = Path(description="The id of the session to cancel"),

invokeai/app/api/routers/utilities.py

@@ -0,0 +1,41 @@
+from typing import Optional
+
+from dynamicprompts.generators import CombinatorialPromptGenerator, RandomPromptGenerator
+from fastapi import Body
+from fastapi.routing import APIRouter
+from pydantic import BaseModel
+from pyparsing import ParseException
+
+utilities_router = APIRouter(prefix="/v1/utilities", tags=["utilities"])
+
+
+class DynamicPromptsResponse(BaseModel):
+    prompts: list[str]
+    error: Optional[str] = None
+
+
+@utilities_router.post(
+    "/dynamicprompts",
+    operation_id="parse_dynamicprompts",
+    responses={
+        200: {"model": DynamicPromptsResponse},
+    },
+)
+async def parse_dynamicprompts(
+    prompt: str = Body(description="The prompt to parse with dynamicprompts"),
+    max_prompts: int = Body(default=1000, description="The max number of prompts to generate"),
+    combinatorial: bool = Body(default=True, description="Whether to use the combinatorial generator"),
+) -> DynamicPromptsResponse:
+    """Creates a batch process"""
+    try:
+        error: Optional[str] = None
+        if combinatorial:
+            generator = CombinatorialPromptGenerator()
+            prompts = generator.generate(prompt, max_prompts=max_prompts)
+        else:
+            generator = RandomPromptGenerator()
+            prompts = generator.generate(prompt, num_images=max_prompts)
+    except ParseException as e:
+        prompts = [prompt]
+        error = str(e)
+    return DynamicPromptsResponse(prompts=prompts if prompts else [""], error=error)

invokeai/app/api/sockets.py

@@ -3,34 +3,35 @@
 from fastapi import FastAPI
 from fastapi_events.handlers.local import local_handler
 from fastapi_events.typing import Event
-from fastapi_socketio import SocketManager
+from socketio import ASGIApp, AsyncServer
 
 from ..services.events import EventServiceBase
 
 
 class SocketIO:
-    __sio: SocketManager
+    __sio: AsyncServer
+    __app: ASGIApp
 
     def __init__(self, app: FastAPI):
-        self.__sio = SocketManager(app=app)
-        self.__sio.on("subscribe", handler=self._handle_sub)
-        self.__sio.on("unsubscribe", handler=self._handle_unsub)
+        self.__sio = AsyncServer(async_mode="asgi", cors_allowed_origins="*")
+        self.__app = ASGIApp(socketio_server=self.__sio, socketio_path="socket.io")
+        app.mount("/ws", self.__app)
 
-        local_handler.register(event_name=EventServiceBase.session_event, _func=self._handle_session_event)
+        self.__sio.on("subscribe_queue", handler=self._handle_sub_queue)
+        self.__sio.on("unsubscribe_queue", handler=self._handle_unsub_queue)
+        local_handler.register(event_name=EventServiceBase.queue_event, _func=self._handle_queue_event)
 
-    async def _handle_session_event(self, event: Event):
+    async def _handle_queue_event(self, event: Event):
         await self.__sio.emit(
             event=event[1]["event"],
             data=event[1]["data"],
-            room=event[1]["data"]["graph_execution_state_id"],
+            room=event[1]["data"]["queue_id"],
         )
 
-    async def _handle_sub(self, sid, data, *args, **kwargs):
-        if "session" in data:
-            self.__sio.enter_room(sid, data["session"])
+    async def _handle_sub_queue(self, sid, data, *args, **kwargs):
+        if "queue_id" in data:
+            await self.__sio.enter_room(sid, data["queue_id"])
 
-        # @app.sio.on('unsubscribe')
-
-    async def _handle_unsub(self, sid, data, *args, **kwargs):
-        if "session" in data:
-            self.__sio.leave_room(sid, data["session"])
+    async def _handle_unsub_queue(self, sid, data, *args, **kwargs):
+        if "queue_id" in data:
+            await self.__sio.enter_room(sid, data["queue_id"])

invokeai/app/api_app.py

@@ -1,4 +1,3 @@
-# Copyright (c) 2022-2023 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
 from .services.config import InvokeAIAppConfig
 
 # parse_args() must be called before any other imports. if it is not called first, consumers of the config
@@ -9,7 +8,6 @@ app_config.parse_args()
 
 if True:  # hack to make flake8 happy with imports coming after setting up the config
     import asyncio
-    import logging
     import mimetypes
     import socket
     from inspect import signature
@@ -33,7 +31,7 @@ if True:  # hack to make flake8 happy with imports coming after setting up the c
 
     from ..backend.util.logging import InvokeAILogger
     from .api.dependencies import ApiDependencies
-    from .api.routers import app_info, board_images, boards, images, models, sessions
+    from .api.routers import app_info, board_images, boards, images, models, session_queue, sessions, utilities
     from .api.sockets import SocketIO
     from .invocations.baseinvocation import BaseInvocation, UIConfigBase, _InputField, _OutputField
 
@@ -42,7 +40,9 @@ if True:  # hack to make flake8 happy with imports coming after setting up the c
         import invokeai.backend.util.mps_fixes  # noqa: F401 (monkeypatching on import)
 
 
-logger = InvokeAILogger.getLogger(config=app_config)
+app_config = InvokeAIAppConfig.get_config()
+app_config.parse_args()
+logger = InvokeAILogger.get_logger(config=app_config)
 
 # fix for windows mimetypes registry entries being borked
 # see https://github.com/invoke-ai/InvokeAI/discussions/3684#discussioncomment-6391352
@@ -92,6 +92,8 @@ async def shutdown_event():
 
 app.include_router(sessions.session_router, prefix="/api")
 
+app.include_router(utilities.utilities_router, prefix="/api")
+
 app.include_router(models.models_router, prefix="/api")
 
 app.include_router(images.images_router, prefix="/api")
@@ -102,6 +104,8 @@ app.include_router(board_images.board_images_router, prefix="/api")
 
 app.include_router(app_info.app_router, prefix="/api")
 
+app.include_router(session_queue.session_queue_router, prefix="/api")
+
 
 # Build a custom OpenAPI to include all outputs
 # TODO: can outputs be included on metadata of invocation schemas somehow?
@@ -220,7 +224,7 @@ def invoke_api():
                 exc_info=e,
             )
         else:
-            jurigged.watch(logger=InvokeAILogger.getLogger(name="jurigged").info)
+            jurigged.watch(logger=InvokeAILogger.get_logger(name="jurigged").info)
 
     port = find_port(app_config.port)
     if port != app_config.port:
@@ -239,7 +243,7 @@ def invoke_api():
 
     # replace uvicorn's loggers with InvokeAI's for consistent appearance
     for logname in ["uvicorn.access", "uvicorn"]:
-        log = logging.getLogger(logname)
+        log = InvokeAILogger.get_logger(logname)
         log.handlers.clear()
         for ch in logger.handlers:
             log.addHandler(ch)

invokeai/app/cli_app.py

@@ -1,17 +1,18 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
+
+from invokeai.app.services.invocation_cache.invocation_cache_memory import MemoryInvocationCache
 
 from .services.config import InvokeAIAppConfig
 
 # parse_args() must be called before any other imports. if it is not called first, consumers of the config
 # which are imported/used before parse_args() is called will get the default config values instead of the
 # values from the command line or config file.
-config = InvokeAIAppConfig.get_config()
-config.parse_args()
 
 if True:  # hack to make flake8 happy with imports coming after setting up the config
     import argparse
     import re
     import shlex
+    import sqlite3
     import sys
     import time
     from typing import Optional, Union, get_type_hints
@@ -58,8 +59,9 @@ if True:  # hack to make flake8 happy with imports coming after setting up the c
     if torch.backends.mps.is_available():
         import invokeai.backend.util.mps_fixes  # noqa: F401 (monkeypatching on import)
 
-
-logger = InvokeAILogger().getLogger(config=config)
+config = InvokeAIAppConfig.get_config()
+config.parse_args()
+logger = InvokeAILogger().get_logger(config=config)
 
 
 class CliCommand(BaseModel):
@@ -249,19 +251,18 @@ def invoke_cli():
         db_location = config.db_path
         db_location.parent.mkdir(parents=True, exist_ok=True)
 
+    db_conn = sqlite3.connect(db_location, check_same_thread=False)  # TODO: figure out a better threading solution
     logger.info(f'InvokeAI database location is "{db_location}"')
 
-    graph_execution_manager = SqliteItemStorage[GraphExecutionState](
-        filename=db_location, table_name="graph_executions"
-    )
+    graph_execution_manager = SqliteItemStorage[GraphExecutionState](conn=db_conn, table_name="graph_executions")
 
     urls = LocalUrlService()
-    image_record_storage = SqliteImageRecordStorage(db_location)
+    image_record_storage = SqliteImageRecordStorage(conn=db_conn)
     image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
     names = SimpleNameService()
 
-    board_record_storage = SqliteBoardRecordStorage(db_location)
-    board_image_record_storage = SqliteBoardImageRecordStorage(db_location)
+    board_record_storage = SqliteBoardRecordStorage(conn=db_conn)
+    board_image_record_storage = SqliteBoardImageRecordStorage(conn=db_conn)
 
     boards = BoardService(
         services=BoardServiceDependencies(
@@ -303,12 +304,13 @@ def invoke_cli():
         boards=boards,
         board_images=board_images,
         queue=MemoryInvocationQueue(),
-        graph_library=SqliteItemStorage[LibraryGraph](filename=db_location, table_name="graphs"),
+        graph_library=SqliteItemStorage[LibraryGraph](conn=db_conn, table_name="graphs"),
         graph_execution_manager=graph_execution_manager,
         processor=DefaultInvocationProcessor(),
         performance_statistics=InvocationStatsService(graph_execution_manager),
         logger=logger,
         configuration=config,
+        invocation_cache=MemoryInvocationCache(max_cache_size=config.node_cache_size),
     )
 
     system_graphs = create_system_graphs(services.graph_library)

invokeai/app/invocations/baseinvocation.py

@@ -67,6 +67,8 @@ class FieldDescriptions:
     width = "Width of output (px)"
     height = "Height of output (px)"
     control = "ControlNet(s) to apply"
+    ip_adapter = "IP-Adapter to apply"
+    t2i_adapter = "T2I-Adapter(s) to apply"
     denoised_latents = "Denoised latents tensor"
     latents = "Latents tensor"
     strength = "Strength of denoising (proportional to steps)"
@@ -87,6 +89,12 @@ class FieldDescriptions:
     num_1 = "The first number"
     num_2 = "The second number"
     mask = "The mask to use for the operation"
+    board = "The board to save the image to"
+    image = "The image to process"
+    tile_size = "Tile size"
+    inclusive_low = "The inclusive low value"
+    exclusive_high = "The exclusive high value"
+    decimal_places = "The number of decimal places to round to"
 
 
 class Input(str, Enum):
@@ -155,6 +163,7 @@ class UIType(str, Enum):
     VaeModel = "VaeModelField"
     LoRAModel = "LoRAModelField"
     ControlNetModel = "ControlNetModelField"
+    IPAdapterModel = "IPAdapterModelField"
     UNet = "UNetField"
     Vae = "VaeField"
     CLIP = "ClipField"
@@ -171,6 +180,7 @@ class UIType(str, Enum):
     WorkflowField = "WorkflowField"
     IsIntermediate = "IsIntermediate"
     MetadataField = "MetadataField"
+    BoardField = "BoardField"
     # endregion
 
 
@@ -417,12 +427,27 @@ class UIConfigBase(BaseModel):
 
 
 class InvocationContext:
+    """Initialized and provided to on execution of invocations."""
+
     services: InvocationServices
     graph_execution_state_id: str
+    queue_id: str
+    queue_item_id: int
+    queue_batch_id: str
 
-    def __init__(self, services: InvocationServices, graph_execution_state_id: str):
+    def __init__(
+        self,
+        services: InvocationServices,
+        queue_id: str,
+        queue_item_id: int,
+        queue_batch_id: str,
+        graph_execution_state_id: str,
+    ):
         self.services = services
         self.graph_execution_state_id = graph_execution_state_id
+        self.queue_id = queue_id
+        self.queue_item_id = queue_item_id
+        self.queue_batch_id = queue_batch_id
 
 
 class BaseInvocationOutput(BaseModel):
@@ -520,6 +545,9 @@ class BaseInvocation(ABC, BaseModel):
         return signature(cls.invoke).return_annotation
 
     class Config:
+        validate_assignment = True
+        validate_all = True
+
         @staticmethod
         def schema_extra(schema: dict[str, Any], model_class: Type[BaseModel]) -> None:
             uiconfig = getattr(model_class, "UIConfig", None)
@@ -568,7 +596,29 @@ class BaseInvocation(ABC, BaseModel):
                     raise RequiredConnectionException(self.__fields__["type"].default, field_name)
                 elif _input == Input.Any:
                     raise MissingInputException(self.__fields__["type"].default, field_name)
-        return self.invoke(context)
+
+        # skip node cache codepath if it's disabled
+        if context.services.configuration.node_cache_size == 0:
+            return self.invoke(context)
+
+        output: BaseInvocationOutput
+        if self.use_cache:
+            key = context.services.invocation_cache.create_key(self)
+            cached_value = context.services.invocation_cache.get(key)
+            if cached_value is None:
+                context.services.logger.debug(f'Invocation cache miss for type "{self.get_type()}": {self.id}')
+                output = self.invoke(context)
+                context.services.invocation_cache.save(key, output)
+                return output
+            else:
+                context.services.logger.debug(f'Invocation cache hit for type "{self.get_type()}": {self.id}')
+                return cached_value
+        else:
+            context.services.logger.debug(f'Skipping invocation cache for "{self.get_type()}": {self.id}')
+            return self.invoke(context)
+
+    def get_type(self) -> str:
+        return self.__fields__["type"].default
 
     id: str = Field(
         description="The id of this instance of an invocation. Must be unique among all instances of invocations."
@@ -581,6 +631,7 @@ class BaseInvocation(ABC, BaseModel):
         description="The workflow to save with the image",
         ui_type=UIType.WorkflowField,
     )
+    use_cache: bool = InputField(default=True, description="Whether or not to use the cache")
 
     @validator("workflow", pre=True)
     def validate_workflow_is_json(cls, v):
@@ -604,6 +655,7 @@ def invocation(
     tags: Optional[list[str]] = None,
     category: Optional[str] = None,
     version: Optional[str] = None,
+    use_cache: Optional[bool] = True,
 ) -> Callable[[Type[GenericBaseInvocation]], Type[GenericBaseInvocation]]:
     """
     Adds metadata to an invocation.
@@ -612,6 +664,8 @@ def invocation(
     :param Optional[str] title: Adds a title to the invocation. Use if the auto-generated title isn't quite right. Defaults to None.
     :param Optional[list[str]] tags: Adds tags to the invocation. Invocations may be searched for by their tags. Defaults to None.
     :param Optional[str] category: Adds a category to the invocation. Used to group the invocations in the UI. Defaults to None.
+    :param Optional[str] version: Adds a version to the invocation. Must be a valid semver string. Defaults to None.
+    :param Optional[bool] use_cache: Whether or not to use the invocation cache. Defaults to True. The user may override this in the workflow editor.
     """
 
     def wrapper(cls: Type[GenericBaseInvocation]) -> Type[GenericBaseInvocation]:
@@ -636,6 +690,8 @@ def invocation(
             except ValueError as e:
                 raise InvalidVersionError(f'Invalid version string for node "{invocation_type}": "{version}"') from e
             cls.UIConfig.version = version
+        if use_cache is not None:
+            cls.__fields__["use_cache"].default = use_cache
 
         # Add the invocation type to the pydantic model of the invocation
         invocation_type_annotation = Literal[invocation_type]  # type: ignore

invokeai/app/invocations/collections.py

@@ -56,6 +56,7 @@ class RangeOfSizeInvocation(BaseInvocation):
     tags=["range", "integer", "random", "collection"],
     category="collections",
     version="1.0.0",
+    use_cache=False,
 )
 class RandomRangeInvocation(BaseInvocation):
     """Creates a collection of random numbers"""

invokeai/app/invocations/compel.py

@@ -7,14 +7,14 @@ from compel import Compel, ReturnedEmbeddingsType
 from compel.prompt_parser import Blend, Conjunction, CrossAttentionControlSubstitute, FlattenedPrompt, Fragment
 
 from invokeai.app.invocations.primitives import ConditioningField, ConditioningOutput
-from invokeai.backend.stable_diffusion.diffusion.shared_invokeai_diffusion import (
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
     BasicConditioningInfo,
+    ExtraConditioningInfo,
     SDXLConditioningInfo,
 )
 
 from ...backend.model_management.lora import ModelPatcher
 from ...backend.model_management.models import ModelNotFoundException, ModelType
-from ...backend.stable_diffusion.diffusion import InvokeAIDiffuserComponent
 from ...backend.util.devices import torch_dtype
 from .baseinvocation import (
     BaseInvocation,
@@ -99,14 +99,15 @@ class CompelInvocation(BaseInvocation):
                 # print(traceback.format_exc())
                 print(f'Warn: trigger: "{trigger}" not found')
 
-        with ModelPatcher.apply_lora_text_encoder(
-            text_encoder_info.context.model, _lora_loader()
-        ), ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
-            tokenizer,
-            ti_manager,
-        ), ModelPatcher.apply_clip_skip(
-            text_encoder_info.context.model, self.clip.skipped_layers
-        ), text_encoder_info as text_encoder:
+        with (
+            ModelPatcher.apply_lora_text_encoder(text_encoder_info.context.model, _lora_loader()),
+            ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
+                tokenizer,
+                ti_manager,
+            ),
+            ModelPatcher.apply_clip_skip(text_encoder_info.context.model, self.clip.skipped_layers),
+            text_encoder_info as text_encoder,
+        ):
             compel = Compel(
                 tokenizer=tokenizer,
                 text_encoder=text_encoder,
@@ -122,7 +123,7 @@ class CompelInvocation(BaseInvocation):
 
             c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
 
-            ec = InvokeAIDiffuserComponent.ExtraConditioningInfo(
+            ec = ExtraConditioningInfo(
                 tokens_count_including_eos_bos=get_max_token_count(tokenizer, conjunction),
                 cross_attention_control_args=options.get("cross_attention_control", None),
             )
@@ -213,14 +214,15 @@ class SDXLPromptInvocationBase:
                 # print(traceback.format_exc())
                 print(f'Warn: trigger: "{trigger}" not found')
 
-        with ModelPatcher.apply_lora(
-            text_encoder_info.context.model, _lora_loader(), lora_prefix
-        ), ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
-            tokenizer,
-            ti_manager,
-        ), ModelPatcher.apply_clip_skip(
-            text_encoder_info.context.model, clip_field.skipped_layers
-        ), text_encoder_info as text_encoder:
+        with (
+            ModelPatcher.apply_lora(text_encoder_info.context.model, _lora_loader(), lora_prefix),
+            ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
+                tokenizer,
+                ti_manager,
+            ),
+            ModelPatcher.apply_clip_skip(text_encoder_info.context.model, clip_field.skipped_layers),
+            text_encoder_info as text_encoder,
+        ):
             compel = Compel(
                 tokenizer=tokenizer,
                 text_encoder=text_encoder,
@@ -244,7 +246,7 @@ class SDXLPromptInvocationBase:
             else:
                 c_pooled = None
 
-            ec = InvokeAIDiffuserComponent.ExtraConditioningInfo(
+            ec = ExtraConditioningInfo(
                 tokens_count_including_eos_bos=get_max_token_count(tokenizer, conjunction),
                 cross_attention_control_args=options.get("cross_attention_control", None),
             )
@@ -436,9 +438,11 @@ def get_tokens_for_prompt_object(tokenizer, parsed_prompt: FlattenedPrompt, trun
         raise ValueError("Blend is not supported here - you need to get tokens for each of its .children")
 
     text_fragments = [
-        x.text
-        if type(x) is Fragment
-        else (" ".join([f.text for f in x.original]) if type(x) is CrossAttentionControlSubstitute else str(x))
+        (
+            x.text
+            if type(x) is Fragment
+            else (" ".join([f.text for f in x.original]) if type(x) is CrossAttentionControlSubstitute else str(x))
+        )
         for x in parsed_prompt.children
     ]
     text = " ".join(text_fragments)

invokeai/app/invocations/controlnet_image_processors.py

@@ -38,7 +38,6 @@ from .baseinvocation import (
     InputField,
     InvocationContext,
     OutputField,
-    UIType,
     invocation,
     invocation_output,
 )
@@ -100,7 +99,7 @@ class ControlNetInvocation(BaseInvocation):
     image: ImageField = InputField(description="The control image")
     control_model: ControlNetModelField = InputField(description=FieldDescriptions.controlnet_model, input=Input.Direct)
     control_weight: Union[float, List[float]] = InputField(
-        default=1.0, description="The weight given to the ControlNet", ui_type=UIType.Float
+        default=1.0, description="The weight given to the ControlNet"
     )
     begin_step_percent: float = InputField(
         default=0, ge=-1, le=2, description="When the ControlNet is first applied (% of total steps)"
@@ -560,3 +559,33 @@ class SamDetectorReproducibleColors(SamDetector):
             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)
+
+
+@invocation(
+    "color_map_image_processor",
+    title="Color Map Processor",
+    tags=["controlnet"],
+    category="controlnet",
+    version="1.0.0",
+)
+class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
+    """Generates a color map from the provided image"""
+
+    color_map_tile_size: int = InputField(default=64, ge=0, description=FieldDescriptions.tile_size)
+
+    def run_processor(self, image: Image.Image):
+        image = image.convert("RGB")
+        image = np.array(image, dtype=np.uint8)
+        height, width = image.shape[:2]
+
+        width_tile_size = min(self.color_map_tile_size, width)
+        height_tile_size = min(self.color_map_tile_size, height)
+
+        color_map = cv2.resize(
+            image,
+            (width // width_tile_size, height // height_tile_size),
+            interpolation=cv2.INTER_CUBIC,
+        )
+        color_map = cv2.resize(color_map, (width, height), interpolation=cv2.INTER_NEAREST)
+        color_map = Image.fromarray(color_map)
+        return color_map

invokeai/app/invocations/facetools.py

@@ -0,0 +1,724 @@
+import math
+import re
+from pathlib import Path
+from typing import Optional, TypedDict
+
+import cv2
+import numpy as np
+from mediapipe.python.solutions.face_mesh import FaceMesh  # type: ignore[import]
+from PIL import Image, ImageDraw, ImageFilter, ImageFont, ImageOps
+from PIL.Image import Image as ImageType
+from pydantic import validator
+
+import invokeai.assets.fonts as font_assets
+from invokeai.app.invocations.baseinvocation import (
+    BaseInvocation,
+    InputField,
+    InvocationContext,
+    OutputField,
+    invocation,
+    invocation_output,
+)
+from invokeai.app.invocations.primitives import ImageField, ImageOutput
+from invokeai.app.models.image import ImageCategory, ResourceOrigin
+
+
+@invocation_output("face_mask_output")
+class FaceMaskOutput(ImageOutput):
+    """Base class for FaceMask output"""
+
+    mask: ImageField = OutputField(description="The output mask")
+
+
+@invocation_output("face_off_output")
+class FaceOffOutput(ImageOutput):
+    """Base class for FaceOff Output"""
+
+    mask: ImageField = OutputField(description="The output mask")
+    x: int = OutputField(description="The x coordinate of the bounding box's left side")
+    y: int = OutputField(description="The y coordinate of the bounding box's top side")
+
+
+class FaceResultData(TypedDict):
+    image: ImageType
+    mask: ImageType
+    x_center: float
+    y_center: float
+    mesh_width: int
+    mesh_height: int
+    chunk_x_offset: int
+    chunk_y_offset: int
+
+
+class FaceResultDataWithId(FaceResultData):
+    face_id: int
+
+
+class ExtractFaceData(TypedDict):
+    bounded_image: ImageType
+    bounded_mask: ImageType
+    x_min: int
+    y_min: int
+    x_max: int
+    y_max: int
+
+
+class FaceMaskResult(TypedDict):
+    image: ImageType
+    mask: ImageType
+
+
+def create_white_image(w: int, h: int) -> ImageType:
+    return Image.new("L", (w, h), color=255)
+
+
+def create_black_image(w: int, h: int) -> ImageType:
+    return Image.new("L", (w, h), color=0)
+
+
+FONT_SIZE = 32
+FONT_STROKE_WIDTH = 4
+
+
+def coalesce_faces(face1: FaceResultData, face2: FaceResultData) -> FaceResultData:
+    face1_x_offset = face1["chunk_x_offset"] - min(face1["chunk_x_offset"], face2["chunk_x_offset"])
+    face2_x_offset = face2["chunk_x_offset"] - min(face1["chunk_x_offset"], face2["chunk_x_offset"])
+    face1_y_offset = face1["chunk_y_offset"] - min(face1["chunk_y_offset"], face2["chunk_y_offset"])
+    face2_y_offset = face2["chunk_y_offset"] - min(face1["chunk_y_offset"], face2["chunk_y_offset"])
+
+    new_im_width = (
+        max(face1["image"].width, face2["image"].width)
+        + max(face1["chunk_x_offset"], face2["chunk_x_offset"])
+        - min(face1["chunk_x_offset"], face2["chunk_x_offset"])
+    )
+    new_im_height = (
+        max(face1["image"].height, face2["image"].height)
+        + max(face1["chunk_y_offset"], face2["chunk_y_offset"])
+        - min(face1["chunk_y_offset"], face2["chunk_y_offset"])
+    )
+    pil_image = Image.new(mode=face1["image"].mode, size=(new_im_width, new_im_height))
+    pil_image.paste(face1["image"], (face1_x_offset, face1_y_offset))
+    pil_image.paste(face2["image"], (face2_x_offset, face2_y_offset))
+
+    # Mask images are always from the origin
+    new_mask_im_width = max(face1["mask"].width, face2["mask"].width)
+    new_mask_im_height = max(face1["mask"].height, face2["mask"].height)
+    mask_pil = create_white_image(new_mask_im_width, new_mask_im_height)
+    black_image = create_black_image(face1["mask"].width, face1["mask"].height)
+    mask_pil.paste(black_image, (0, 0), ImageOps.invert(face1["mask"]))
+    black_image = create_black_image(face2["mask"].width, face2["mask"].height)
+    mask_pil.paste(black_image, (0, 0), ImageOps.invert(face2["mask"]))
+
+    new_face = FaceResultData(
+        image=pil_image,
+        mask=mask_pil,
+        x_center=max(face1["x_center"], face2["x_center"]),
+        y_center=max(face1["y_center"], face2["y_center"]),
+        mesh_width=max(face1["mesh_width"], face2["mesh_width"]),
+        mesh_height=max(face1["mesh_height"], face2["mesh_height"]),
+        chunk_x_offset=max(face1["chunk_x_offset"], face2["chunk_x_offset"]),
+        chunk_y_offset=max(face2["chunk_y_offset"], face2["chunk_y_offset"]),
+    )
+    return new_face
+
+
+def prepare_faces_list(
+    face_result_list: list[FaceResultData],
+) -> list[FaceResultDataWithId]:
+    """Deduplicates a list of faces, adding IDs to them."""
+    deduped_faces: list[FaceResultData] = []
+
+    if len(face_result_list) == 0:
+        return list()
+
+    for candidate in face_result_list:
+        should_add = True
+        candidate_x_center = candidate["x_center"]
+        candidate_y_center = candidate["y_center"]
+        for idx, face in enumerate(deduped_faces):
+            face_center_x = face["x_center"]
+            face_center_y = face["y_center"]
+            face_radius_w = face["mesh_width"] / 2
+            face_radius_h = face["mesh_height"] / 2
+            # Determine if the center of the candidate_face is inside the ellipse of the added face
+            # p < 1 -> Inside
+            # p = 1 -> Exactly on the ellipse
+            # p > 1 -> Outside
+            p = (math.pow((candidate_x_center - face_center_x), 2) / math.pow(face_radius_w, 2)) + (
+                math.pow((candidate_y_center - face_center_y), 2) / math.pow(face_radius_h, 2)
+            )
+
+            if p < 1:  # Inside of the already-added face's radius
+                deduped_faces[idx] = coalesce_faces(face, candidate)
+                should_add = False
+                break
+
+        if should_add is True:
+            deduped_faces.append(candidate)
+
+    sorted_faces = sorted(deduped_faces, key=lambda x: x["y_center"])
+    sorted_faces = sorted(sorted_faces, key=lambda x: x["x_center"])
+
+    # add face_id for reference
+    sorted_faces_with_ids: list[FaceResultDataWithId] = []
+    face_id_counter = 0
+    for face in sorted_faces:
+        sorted_faces_with_ids.append(
+            FaceResultDataWithId(
+                **face,
+                face_id=face_id_counter,
+            )
+        )
+        face_id_counter += 1
+
+    return sorted_faces_with_ids
+
+
+def generate_face_box_mask(
+    context: InvocationContext,
+    minimum_confidence: float,
+    x_offset: float,
+    y_offset: float,
+    pil_image: ImageType,
+    chunk_x_offset: int = 0,
+    chunk_y_offset: int = 0,
+    draw_mesh: bool = True,
+) -> list[FaceResultData]:
+    result = []
+    mask_pil = None
+
+    # Convert the PIL image to a NumPy array.
+    np_image = np.array(pil_image, dtype=np.uint8)
+
+    # Check if the input image has four channels (RGBA).
+    if np_image.shape[2] == 4:
+        # Convert RGBA to RGB by removing the alpha channel.
+        np_image = np_image[:, :, :3]
+
+    # Create a FaceMesh object for face landmark detection and mesh generation.
+    face_mesh = FaceMesh(
+        max_num_faces=999,
+        min_detection_confidence=minimum_confidence,
+        min_tracking_confidence=minimum_confidence,
+    )
+
+    # Detect the face landmarks and mesh in the input image.
+    results = face_mesh.process(np_image)
+
+    # Check if any face is detected.
+    if results.multi_face_landmarks:  # type: ignore # this are via protobuf and not typed
+        # Search for the face_id in the detected faces.
+        for face_id, face_landmarks in enumerate(results.multi_face_landmarks):  # type: ignore #this are via protobuf and not typed
+            # Get the bounding box of the face mesh.
+            x_coordinates = [landmark.x for landmark in face_landmarks.landmark]
+            y_coordinates = [landmark.y for landmark in face_landmarks.landmark]
+            x_min, x_max = min(x_coordinates), max(x_coordinates)
+            y_min, y_max = min(y_coordinates), max(y_coordinates)
+
+            # Calculate the width and height of the face mesh.
+            mesh_width = int((x_max - x_min) * np_image.shape[1])
+            mesh_height = int((y_max - y_min) * np_image.shape[0])
+
+            # Get the center of the face.
+            x_center = np.mean([landmark.x * np_image.shape[1] for landmark in face_landmarks.landmark])
+            y_center = np.mean([landmark.y * np_image.shape[0] for landmark in face_landmarks.landmark])
+
+            face_landmark_points = np.array(
+                [
+                    [landmark.x * np_image.shape[1], landmark.y * np_image.shape[0]]
+                    for landmark in face_landmarks.landmark
+                ]
+            )
+
+            # Apply the scaling offsets to the face landmark points with a multiplier.
+            scale_multiplier = 0.2
+            x_center = np.mean(face_landmark_points[:, 0])
+            y_center = np.mean(face_landmark_points[:, 1])
+
+            if draw_mesh:
+                x_scaled = face_landmark_points[:, 0] + scale_multiplier * x_offset * (
+                    face_landmark_points[:, 0] - x_center
+                )
+                y_scaled = face_landmark_points[:, 1] + scale_multiplier * y_offset * (
+                    face_landmark_points[:, 1] - y_center
+                )
+
+                convex_hull = cv2.convexHull(np.column_stack((x_scaled, y_scaled)).astype(np.int32))
+
+                # Generate a binary face mask using the face mesh.
+                mask_image = np.ones(np_image.shape[:2], dtype=np.uint8) * 255
+                cv2.fillConvexPoly(mask_image, convex_hull, 0)
+
+                # Convert the binary mask image to a PIL Image.
+                init_mask_pil = Image.fromarray(mask_image, mode="L")
+                w, h = init_mask_pil.size
+                mask_pil = create_white_image(w + chunk_x_offset, h + chunk_y_offset)
+                mask_pil.paste(init_mask_pil, (chunk_x_offset, chunk_y_offset))
+
+            x_center = float(x_center)
+            y_center = float(y_center)
+            face = FaceResultData(
+                image=pil_image,
+                mask=mask_pil or create_white_image(*pil_image.size),
+                x_center=x_center + chunk_x_offset,
+                y_center=y_center + chunk_y_offset,
+                mesh_width=mesh_width,
+                mesh_height=mesh_height,
+                chunk_x_offset=chunk_x_offset,
+                chunk_y_offset=chunk_y_offset,
+            )
+
+            result.append(face)
+
+    return result
+
+
+def extract_face(
+    context: InvocationContext,
+    image: ImageType,
+    face: FaceResultData,
+    padding: int,
+) -> ExtractFaceData:
+    mask = face["mask"]
+    center_x = face["x_center"]
+    center_y = face["y_center"]
+    mesh_width = face["mesh_width"]
+    mesh_height = face["mesh_height"]
+
+    # Determine the minimum size of the square crop
+    min_size = min(mask.width, mask.height)
+
+    # Calculate the crop boundaries for the output image and mask.
+    mesh_width += 128 + padding  # add pixels to account for mask variance
+    mesh_height += 128 + padding  # add pixels to account for mask variance
+    crop_size = min(
+        max(mesh_width, mesh_height, 128), min_size
+    )  # Choose the smaller of the two (given value or face mask size)
+    if crop_size > 128:
+        crop_size = (crop_size + 7) // 8 * 8  # Ensure crop side is multiple of 8
+
+    # Calculate the actual crop boundaries within the bounds of the original image.
+    x_min = int(center_x - crop_size / 2)
+    y_min = int(center_y - crop_size / 2)
+    x_max = int(center_x + crop_size / 2)
+    y_max = int(center_y + crop_size / 2)
+
+    # Adjust the crop boundaries to stay within the original image's dimensions
+    if x_min < 0:
+        context.services.logger.warning("FaceTools --> -X-axis padding reached image edge.")
+        x_max -= x_min
+        x_min = 0
+    elif x_max > mask.width:
+        context.services.logger.warning("FaceTools --> +X-axis padding reached image edge.")
+        x_min -= x_max - mask.width
+        x_max = mask.width
+
+    if y_min < 0:
+        context.services.logger.warning("FaceTools --> +Y-axis padding reached image edge.")
+        y_max -= y_min
+        y_min = 0
+    elif y_max > mask.height:
+        context.services.logger.warning("FaceTools --> -Y-axis padding reached image edge.")
+        y_min -= y_max - mask.height
+        y_max = mask.height
+
+    # Ensure the crop is square and adjust the boundaries if needed
+    if x_max - x_min != crop_size:
+        context.services.logger.warning("FaceTools --> Limiting x-axis padding to constrain bounding box to a square.")
+        diff = crop_size - (x_max - x_min)
+        x_min -= diff // 2
+        x_max += diff - diff // 2
+
+    if y_max - y_min != crop_size:
+        context.services.logger.warning("FaceTools --> Limiting y-axis padding to constrain bounding box to a square.")
+        diff = crop_size - (y_max - y_min)
+        y_min -= diff // 2
+        y_max += diff - diff // 2
+
+    context.services.logger.info(f"FaceTools --> Calculated bounding box (8 multiple): {crop_size}")
+
+    # Crop the output image to the specified size with the center of the face mesh as the center.
+    mask = mask.crop((x_min, y_min, x_max, y_max))
+    bounded_image = image.crop((x_min, y_min, x_max, y_max))
+
+    # blur mask edge by small radius
+    mask = mask.filter(ImageFilter.GaussianBlur(radius=2))
+
+    return ExtractFaceData(
+        bounded_image=bounded_image,
+        bounded_mask=mask,
+        x_min=x_min,
+        y_min=y_min,
+        x_max=x_max,
+        y_max=y_max,
+    )
+
+
+def get_faces_list(
+    context: InvocationContext,
+    image: ImageType,
+    should_chunk: bool,
+    minimum_confidence: float,
+    x_offset: float,
+    y_offset: float,
+    draw_mesh: bool = True,
+) -> list[FaceResultDataWithId]:
+    result = []
+
+    # Generate the face box mask and get the center of the face.
+    if not should_chunk:
+        context.services.logger.info("FaceTools --> Attempting full image face detection.")
+        result = generate_face_box_mask(
+            context=context,
+            minimum_confidence=minimum_confidence,
+            x_offset=x_offset,
+            y_offset=y_offset,
+            pil_image=image,
+            chunk_x_offset=0,
+            chunk_y_offset=0,
+            draw_mesh=draw_mesh,
+        )
+    if should_chunk or len(result) == 0:
+        context.services.logger.info("FaceTools --> Chunking image (chunk toggled on, or no face found in full image).")
+        width, height = image.size
+        image_chunks = []
+        x_offsets = []
+        y_offsets = []
+        result = []
+
+        # If width == height, there's nothing more we can do... otherwise...
+        if width > height:
+            # Landscape - slice the image horizontally
+            fx = 0.0
+            steps = int(width * 2 / height) + 1
+            increment = (width - height) / (steps - 1)
+            while fx <= (width - height):
+                x = int(fx)
+                image_chunks.append(image.crop((x, 0, x + height, height)))
+                x_offsets.append(x)
+                y_offsets.append(0)
+                fx += increment
+                context.services.logger.info(f"FaceTools --> Chunk starting at x = {x}")
+        elif height > width:
+            # Portrait - slice the image vertically
+            fy = 0.0
+            steps = int(height * 2 / width) + 1
+            increment = (height - width) / (steps - 1)
+            while fy <= (height - width):
+                y = int(fy)
+                image_chunks.append(image.crop((0, y, width, y + width)))
+                x_offsets.append(0)
+                y_offsets.append(y)
+                fy += increment
+                context.services.logger.info(f"FaceTools --> Chunk starting at y = {y}")
+
+        for idx in range(len(image_chunks)):
+            context.services.logger.info(f"FaceTools --> Evaluating faces in chunk {idx}")
+            result = result + generate_face_box_mask(
+                context=context,
+                minimum_confidence=minimum_confidence,
+                x_offset=x_offset,
+                y_offset=y_offset,
+                pil_image=image_chunks[idx],
+                chunk_x_offset=x_offsets[idx],
+                chunk_y_offset=y_offsets[idx],
+                draw_mesh=draw_mesh,
+            )
+
+        if len(result) == 0:
+            # Give up
+            context.services.logger.warning(
+                "FaceTools --> No face detected in chunked input image. Passing through original image."
+            )
+
+    all_faces = prepare_faces_list(result)
+
+    return all_faces
+
+
+@invocation("face_off", title="FaceOff", tags=["image", "faceoff", "face", "mask"], category="image", version="1.0.2")
+class FaceOffInvocation(BaseInvocation):
+    """Bound, extract, and mask a face from an image using MediaPipe detection"""
+
+    image: ImageField = InputField(description="Image for face detection")
+    face_id: int = InputField(
+        default=0,
+        ge=0,
+        description="The face ID to process, numbered from 0. Multiple faces not supported. Find a face's ID with FaceIdentifier node.",
+    )
+    minimum_confidence: float = InputField(
+        default=0.5, description="Minimum confidence for face detection (lower if detection is failing)"
+    )
+    x_offset: float = InputField(default=0.0, description="X-axis offset of the mask")
+    y_offset: float = InputField(default=0.0, description="Y-axis offset of the mask")
+    padding: int = InputField(default=0, description="All-axis padding around the mask in pixels")
+    chunk: bool = InputField(
+        default=False,
+        description="Whether to bypass full image face detection and default to image chunking. Chunking will occur if no faces are found in the full image.",
+    )
+
+    def faceoff(self, context: InvocationContext, image: ImageType) -> Optional[ExtractFaceData]:
+        all_faces = get_faces_list(
+            context=context,
+            image=image,
+            should_chunk=self.chunk,
+            minimum_confidence=self.minimum_confidence,
+            x_offset=self.x_offset,
+            y_offset=self.y_offset,
+            draw_mesh=True,
+        )
+
+        if len(all_faces) == 0:
+            context.services.logger.warning("FaceOff --> No faces detected. Passing through original image.")
+            return None
+
+        if self.face_id > len(all_faces) - 1:
+            context.services.logger.warning(
+                f"FaceOff --> Face ID {self.face_id} is outside of the number of faces detected ({len(all_faces)}). Passing through original image."
+            )
+            return None
+
+        face_data = extract_face(context=context, image=image, face=all_faces[self.face_id], padding=self.padding)
+        # Convert the input image to RGBA mode to ensure it has an alpha channel.
+        face_data["bounded_image"] = face_data["bounded_image"].convert("RGBA")
+
+        return face_data
+
+    def invoke(self, context: InvocationContext) -> FaceOffOutput:
+        image = context.services.images.get_pil_image(self.image.image_name)
+        result = self.faceoff(context=context, image=image)
+
+        if result is None:
+            result_image = image
+            result_mask = create_white_image(*image.size)
+            x = 0
+            y = 0
+        else:
+            result_image = result["bounded_image"]
+            result_mask = result["bounded_mask"]
+            x = result["x_min"]
+            y = result["y_min"]
+
+        image_dto = context.services.images.create(
+            image=result_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+            workflow=self.workflow,
+        )
+
+        mask_dto = context.services.images.create(
+            image=result_mask,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.MASK,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        output = FaceOffOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+            mask=ImageField(image_name=mask_dto.image_name),
+            x=x,
+            y=y,
+        )
+
+        return output
+
+
+@invocation("face_mask_detection", title="FaceMask", tags=["image", "face", "mask"], category="image", version="1.0.2")
+class FaceMaskInvocation(BaseInvocation):
+    """Face mask creation using mediapipe face detection"""
+
+    image: ImageField = InputField(description="Image to face detect")
+    face_ids: str = InputField(
+        default="",
+        description="Comma-separated list of face ids to mask eg '0,2,7'. Numbered from 0. Leave empty to mask all. Find face IDs with FaceIdentifier node.",
+    )
+    minimum_confidence: float = InputField(
+        default=0.5, description="Minimum confidence for face detection (lower if detection is failing)"
+    )
+    x_offset: float = InputField(default=0.0, description="Offset for the X-axis of the face mask")
+    y_offset: float = InputField(default=0.0, description="Offset for the Y-axis of the face mask")
+    chunk: bool = InputField(
+        default=False,
+        description="Whether to bypass full image face detection and default to image chunking. Chunking will occur if no faces are found in the full image.",
+    )
+    invert_mask: bool = InputField(default=False, description="Toggle to invert the mask")
+
+    @validator("face_ids")
+    def validate_comma_separated_ints(cls, v) -> str:
+        comma_separated_ints_regex = re.compile(r"^\d*(,\d+)*$")
+        if comma_separated_ints_regex.match(v) is None:
+            raise ValueError('Face IDs must be a comma-separated list of integers (e.g. "1,2,3")')
+        return v
+
+    def facemask(self, context: InvocationContext, image: ImageType) -> FaceMaskResult:
+        all_faces = get_faces_list(
+            context=context,
+            image=image,
+            should_chunk=self.chunk,
+            minimum_confidence=self.minimum_confidence,
+            x_offset=self.x_offset,
+            y_offset=self.y_offset,
+            draw_mesh=True,
+        )
+
+        mask_pil = create_white_image(*image.size)
+
+        id_range = list(range(0, len(all_faces)))
+        ids_to_extract = id_range
+        if self.face_ids != "":
+            parsed_face_ids = [int(id) for id in self.face_ids.split(",")]
+            # get requested face_ids that are in range
+            intersected_face_ids = set(parsed_face_ids) & set(id_range)
+
+            if len(intersected_face_ids) == 0:
+                id_range_str = ",".join([str(id) for id in id_range])
+                context.services.logger.warning(
+                    f"Face IDs must be in range of detected faces - requested {self.face_ids}, detected {id_range_str}. Passing through original image."
+                )
+                return FaceMaskResult(
+                    image=image,  # original image
+                    mask=mask_pil,  # white mask
+                )
+
+            ids_to_extract = list(intersected_face_ids)
+
+        for face_id in ids_to_extract:
+            face_data = extract_face(context=context, image=image, face=all_faces[face_id], padding=0)
+            face_mask_pil = face_data["bounded_mask"]
+            x_min = face_data["x_min"]
+            y_min = face_data["y_min"]
+            x_max = face_data["x_max"]
+            y_max = face_data["y_max"]
+
+            mask_pil.paste(
+                create_black_image(x_max - x_min, y_max - y_min),
+                box=(x_min, y_min),
+                mask=ImageOps.invert(face_mask_pil),
+            )
+
+        if self.invert_mask:
+            mask_pil = ImageOps.invert(mask_pil)
+
+        # Create an RGBA image with transparency
+        image = image.convert("RGBA")
+
+        return FaceMaskResult(
+            image=image,
+            mask=mask_pil,
+        )
+
+    def invoke(self, context: InvocationContext) -> FaceMaskOutput:
+        image = context.services.images.get_pil_image(self.image.image_name)
+        result = self.facemask(context=context, image=image)
+
+        image_dto = context.services.images.create(
+            image=result["image"],
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+            workflow=self.workflow,
+        )
+
+        mask_dto = context.services.images.create(
+            image=result["mask"],
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.MASK,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        output = FaceMaskOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+            mask=ImageField(image_name=mask_dto.image_name),
+        )
+
+        return output
+
+
+@invocation(
+    "face_identifier", title="FaceIdentifier", tags=["image", "face", "identifier"], category="image", version="1.0.2"
+)
+class FaceIdentifierInvocation(BaseInvocation):
+    """Outputs an image with detected face IDs printed on each face. For use with other FaceTools."""
+
+    image: ImageField = InputField(description="Image to face detect")
+    minimum_confidence: float = InputField(
+        default=0.5, description="Minimum confidence for face detection (lower if detection is failing)"
+    )
+    chunk: bool = InputField(
+        default=False,
+        description="Whether to bypass full image face detection and default to image chunking. Chunking will occur if no faces are found in the full image.",
+    )
+
+    def faceidentifier(self, context: InvocationContext, image: ImageType) -> ImageType:
+        image = image.copy()
+
+        all_faces = get_faces_list(
+            context=context,
+            image=image,
+            should_chunk=self.chunk,
+            minimum_confidence=self.minimum_confidence,
+            x_offset=0,
+            y_offset=0,
+            draw_mesh=False,
+        )
+
+        # Note - font may be found either in the repo if running an editable install, or in the venv if running a package install
+        font_path = [x for x in [Path(y, "inter/Inter-Regular.ttf") for y in font_assets.__path__] if x.exists()]
+        font = ImageFont.truetype(font_path[0].as_posix(), FONT_SIZE)
+
+        # Paste face IDs on the output image
+        draw = ImageDraw.Draw(image)
+        for face in all_faces:
+            x_coord = face["x_center"]
+            y_coord = face["y_center"]
+            text = str(face["face_id"])
+            # get bbox of the text so we can center the id on the face
+            _, _, bbox_w, bbox_h = draw.textbbox(xy=(0, 0), text=text, font=font, stroke_width=FONT_STROKE_WIDTH)
+            x = x_coord - bbox_w / 2
+            y = y_coord - bbox_h / 2
+            draw.text(
+                xy=(x, y),
+                text=str(text),
+                fill=(255, 255, 255, 255),
+                font=font,
+                stroke_width=FONT_STROKE_WIDTH,
+                stroke_fill=(0, 0, 0, 255),
+            )
+
+        # Create an RGBA image with transparency
+        image = image.convert("RGBA")
+
+        return image
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(self.image.image_name)
+        result_image = self.faceidentifier(context=context, image=image)
+
+        image_dto = context.services.images.create(
+            image=result_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+            workflow=self.workflow,
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )

invokeai/app/invocations/image.py

@@ -8,12 +8,12 @@ import numpy
 from PIL import Image, ImageChops, ImageFilter, ImageOps
 
 from invokeai.app.invocations.metadata import CoreMetadata
-from invokeai.app.invocations.primitives import ColorField, ImageField, ImageOutput
+from invokeai.app.invocations.primitives import BoardField, ColorField, ImageField, ImageOutput
 from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark
 from invokeai.backend.image_util.safety_checker import SafetyChecker
 
 from ..models.image import ImageCategory, ResourceOrigin
-from .baseinvocation import BaseInvocation, FieldDescriptions, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, FieldDescriptions, Input, InputField, InvocationContext, invocation
 
 
 @invocation("show_image", title="Show Image", tags=["image"], category="image", version="1.0.0")
@@ -965,3 +965,44 @@ class ImageChannelMultiplyInvocation(BaseInvocation):
             width=image_dto.width,
             height=image_dto.height,
         )
+
+
+@invocation(
+    "save_image",
+    title="Save Image",
+    tags=["primitives", "image"],
+    category="primitives",
+    version="1.0.1",
+    use_cache=False,
+)
+class SaveImageInvocation(BaseInvocation):
+    """Saves an image. Unlike an image primitive, this invocation stores a copy of the image."""
+
+    image: ImageField = InputField(description=FieldDescriptions.image)
+    board: Optional[BoardField] = InputField(default=None, description=FieldDescriptions.board, input=Input.Direct)
+    metadata: CoreMetadata = InputField(
+        default=None,
+        description=FieldDescriptions.core_metadata,
+        ui_hidden=True,
+    )
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(self.image.image_name)
+
+        image_dto = context.services.images.create(
+            image=image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            board_id=self.board.board_id if self.board else None,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+            metadata=self.metadata.dict() if self.metadata else None,
+            workflow=self.workflow,
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )

invokeai/app/invocations/infill.py

@@ -269,7 +269,7 @@ class LaMaInfillInvocation(BaseInvocation):
         )
 
 
-@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint")
+@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0")
 class CV2InfillInvocation(BaseInvocation):
     """Infills transparent areas of an image using OpenCV Inpainting"""
 

invokeai/app/invocations/ip_adapter.py

@@ -0,0 +1,103 @@
+import os
+from builtins import float
+from typing import List, Union
+
+from pydantic import BaseModel, Field
+
+from invokeai.app.invocations.baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    FieldDescriptions,
+    Input,
+    InputField,
+    InvocationContext,
+    OutputField,
+    UIType,
+    invocation,
+    invocation_output,
+)
+from invokeai.app.invocations.primitives import ImageField
+from invokeai.backend.model_management.models.base import BaseModelType, ModelType
+from invokeai.backend.model_management.models.ip_adapter import get_ip_adapter_image_encoder_model_id
+
+
+class IPAdapterModelField(BaseModel):
+    model_name: str = Field(description="Name of the IP-Adapter model")
+    base_model: BaseModelType = Field(description="Base model")
+
+
+class CLIPVisionModelField(BaseModel):
+    model_name: str = Field(description="Name of the CLIP Vision image encoder model")
+    base_model: BaseModelType = Field(description="Base model (usually 'Any')")
+
+
+class IPAdapterField(BaseModel):
+    image: ImageField = Field(description="The IP-Adapter image prompt.")
+    ip_adapter_model: IPAdapterModelField = Field(description="The IP-Adapter model to use.")
+    image_encoder_model: CLIPVisionModelField = Field(description="The name of the CLIP image encoder model.")
+    weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet")
+    # weight: float = Field(default=1.0, ge=0, description="The weight of the IP-Adapter.")
+    begin_step_percent: float = Field(
+        default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
+    )
+    end_step_percent: float = Field(
+        default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
+    )
+
+
+@invocation_output("ip_adapter_output")
+class IPAdapterOutput(BaseInvocationOutput):
+    # Outputs
+    ip_adapter: IPAdapterField = OutputField(description=FieldDescriptions.ip_adapter, title="IP-Adapter")
+
+
+@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.0.0")
+class IPAdapterInvocation(BaseInvocation):
+    """Collects IP-Adapter info to pass to other nodes."""
+
+    # Inputs
+    image: ImageField = InputField(description="The IP-Adapter image prompt.")
+    ip_adapter_model: IPAdapterModelField = InputField(
+        description="The IP-Adapter model.", title="IP-Adapter Model", input=Input.Direct, ui_order=-1
+    )
+
+    # weight: float = InputField(default=1.0, description="The weight of the IP-Adapter.", ui_type=UIType.Float)
+    weight: Union[float, List[float]] = InputField(
+        default=1, ge=0, description="The weight given to the IP-Adapter", ui_type=UIType.Float, title="Weight"
+    )
+
+    begin_step_percent: float = InputField(
+        default=0, ge=-1, le=2, description="When the IP-Adapter is first applied (% of total steps)"
+    )
+    end_step_percent: float = InputField(
+        default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
+    )
+
+    def invoke(self, context: InvocationContext) -> IPAdapterOutput:
+        # Lookup the CLIP Vision encoder that is intended to be used with the IP-Adapter model.
+        ip_adapter_info = context.services.model_manager.model_info(
+            self.ip_adapter_model.model_name, self.ip_adapter_model.base_model, ModelType.IPAdapter
+        )
+        # HACK(ryand): This is bad for a couple of reasons: 1) we are bypassing the model manager to read the model
+        # directly, and 2) we are reading from disk every time this invocation is called without caching the result.
+        # A better solution would be to store the image encoder model reference in the IP-Adapter model info, but this
+        # is currently messy due to differences between how the model info is generated when installing a model from
+        # disk vs. downloading the model.
+        image_encoder_model_id = get_ip_adapter_image_encoder_model_id(
+            os.path.join(context.services.configuration.get_config().models_path, ip_adapter_info["path"])
+        )
+        image_encoder_model_name = image_encoder_model_id.split("/")[-1].strip()
+        image_encoder_model = CLIPVisionModelField(
+            model_name=image_encoder_model_name,
+            base_model=BaseModelType.Any,
+        )
+        return IPAdapterOutput(
+            ip_adapter=IPAdapterField(
+                image=self.image,
+                ip_adapter_model=self.ip_adapter_model,
+                image_encoder_model=image_encoder_model,
+                weight=self.weight,
+                begin_step_percent=self.begin_step_percent,
+                end_step_percent=self.end_step_percent,
+            ),
+        )

invokeai/app/invocations/latent.py

@@ -1,13 +1,16 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
 from contextlib import ExitStack
+from functools import singledispatchmethod
 from typing import List, Literal, Optional, Union
 
 import einops
 import numpy as np
 import torch
 import torchvision.transforms as T
+from diffusers import AutoencoderKL, AutoencoderTiny
 from diffusers.image_processor import VaeImageProcessor
+from diffusers.models.adapter import FullAdapterXL, T2IAdapter
 from diffusers.models.attention_processor import (
     AttnProcessor2_0,
     LoRAAttnProcessor2_0,
@@ -19,6 +22,7 @@ from diffusers.schedulers import SchedulerMixin as Scheduler
 from pydantic import validator
 from torchvision.transforms.functional import resize as tv_resize
 
+from invokeai.app.invocations.ip_adapter import IPAdapterField
 from invokeai.app.invocations.metadata import CoreMetadata
 from invokeai.app.invocations.primitives import (
     DenoiseMaskField,
@@ -29,18 +33,22 @@ from invokeai.app.invocations.primitives import (
     LatentsOutput,
     build_latents_output,
 )
+from invokeai.app.invocations.t2i_adapter import T2IAdapterField
 from invokeai.app.util.controlnet_utils import prepare_control_image
 from invokeai.app.util.step_callback import stable_diffusion_step_callback
+from invokeai.backend.ip_adapter.ip_adapter import IPAdapter, IPAdapterPlus
 from invokeai.backend.model_management.models import ModelType, SilenceWarnings
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningData, IPAdapterConditioningInfo
 
 from ...backend.model_management.lora import ModelPatcher
 from ...backend.model_management.models import BaseModelType
 from ...backend.model_management.seamless import set_seamless
 from ...backend.stable_diffusion import PipelineIntermediateState
 from ...backend.stable_diffusion.diffusers_pipeline import (
-    ConditioningData,
     ControlNetData,
+    IPAdapterData,
     StableDiffusionGeneratorPipeline,
+    T2IAdapterData,
     image_resized_to_grid_as_tensor,
 )
 from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import PostprocessingSettings
@@ -68,7 +76,6 @@ if choose_torch_device() == torch.device("mps"):
 
 DEFAULT_PRECISION = choose_precision(choose_torch_device())
 
-
 SAMPLER_NAME_VALUES = Literal[tuple(list(SCHEDULER_MAP.keys()))]
 
 
@@ -191,7 +198,7 @@ def get_scheduler(
     title="Denoise Latents",
     tags=["latents", "denoise", "txt2img", "t2i", "t2l", "img2img", "i2i", "l2l"],
     category="latents",
-    version="1.0.0",
+    version="1.3.0",
 )
 class DenoiseLatentsInvocation(BaseInvocation):
     """Denoises noisy latents to decodable images"""
@@ -205,7 +212,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
     noise: Optional[LatentsField] = InputField(description=FieldDescriptions.noise, input=Input.Connection, ui_order=3)
     steps: int = InputField(default=10, gt=0, description=FieldDescriptions.steps)
     cfg_scale: Union[float, List[float]] = InputField(
-        default=7.5, ge=1, description=FieldDescriptions.cfg_scale, ui_type=UIType.Float, title="CFG Scale"
+        default=7.5, ge=1, description=FieldDescriptions.cfg_scale, title="CFG Scale"
     )
     denoising_start: float = InputField(default=0.0, ge=0, le=1, description=FieldDescriptions.denoising_start)
     denoising_end: float = InputField(default=1.0, ge=0, le=1, description=FieldDescriptions.denoising_end)
@@ -215,13 +222,18 @@ class DenoiseLatentsInvocation(BaseInvocation):
     unet: UNetField = InputField(description=FieldDescriptions.unet, input=Input.Connection, title="UNet", ui_order=2)
     control: Union[ControlField, list[ControlField]] = InputField(
         default=None,
-        description=FieldDescriptions.control,
         input=Input.Connection,
         ui_order=5,
     )
+    ip_adapter: Optional[Union[IPAdapterField, list[IPAdapterField]]] = InputField(
+        description=FieldDescriptions.ip_adapter, title="IP-Adapter", default=None, input=Input.Connection, ui_order=6
+    )
+    t2i_adapter: Union[T2IAdapterField, list[T2IAdapterField]] = InputField(
+        description=FieldDescriptions.t2i_adapter, title="T2I-Adapter", default=None, input=Input.Connection, ui_order=7
+    )
     latents: Optional[LatentsField] = InputField(description=FieldDescriptions.latents, input=Input.Connection)
     denoise_mask: Optional[DenoiseMaskField] = InputField(
-        default=None, description=FieldDescriptions.mask, input=Input.Connection, ui_order=6
+        default=None, description=FieldDescriptions.mask, input=Input.Connection, ui_order=8
     )
 
     @validator("cfg_scale")
@@ -323,8 +335,6 @@ class DenoiseLatentsInvocation(BaseInvocation):
     def prep_control_data(
         self,
         context: InvocationContext,
-        # really only need model for dtype and device
-        model: StableDiffusionGeneratorPipeline,
         control_input: Union[ControlField, List[ControlField]],
         latents_shape: List[int],
         exit_stack: ExitStack,
@@ -344,57 +354,205 @@ class DenoiseLatentsInvocation(BaseInvocation):
         else:
             control_list = None
         if control_list is None:
-            control_data = None
-            # from above handling, any control that is not None should now be of type list[ControlField]
-        else:
-            # FIXME: add checks to skip entry if model or image is None
-            #        and if weight is None, populate with default 1.0?
-            control_data = []
-            control_models = []
-            for control_info in control_list:
-                control_model = exit_stack.enter_context(
-                    context.services.model_manager.get_model(
-                        model_name=control_info.control_model.model_name,
-                        model_type=ModelType.ControlNet,
-                        base_model=control_info.control_model.base_model,
-                        context=context,
-                    )
+            return None
+        # After above handling, any control that is not None should now be of type list[ControlField].
+
+        # FIXME: add checks to skip entry if model or image is None
+        #        and if weight is None, populate with default 1.0?
+        controlnet_data = []
+        for control_info in control_list:
+            control_model = exit_stack.enter_context(
+                context.services.model_manager.get_model(
+                    model_name=control_info.control_model.model_name,
+                    model_type=ModelType.ControlNet,
+                    base_model=control_info.control_model.base_model,
+                    context=context,
+                )
+            )
+
+            # control_models.append(control_model)
+            control_image_field = control_info.image
+            input_image = context.services.images.get_pil_image(control_image_field.image_name)
+            # self.image.image_type, self.image.image_name
+            # FIXME: still need to test with different widths, heights, devices, dtypes
+            #        and add in batch_size, num_images_per_prompt?
+            #        and do real check for classifier_free_guidance?
+            # prepare_control_image should return torch.Tensor of shape(batch_size, 3, height, width)
+            control_image = prepare_control_image(
+                image=input_image,
+                do_classifier_free_guidance=do_classifier_free_guidance,
+                width=control_width_resize,
+                height=control_height_resize,
+                # batch_size=batch_size * num_images_per_prompt,
+                # num_images_per_prompt=num_images_per_prompt,
+                device=control_model.device,
+                dtype=control_model.dtype,
+                control_mode=control_info.control_mode,
+                resize_mode=control_info.resize_mode,
+            )
+            control_item = ControlNetData(
+                model=control_model,  # model object
+                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,
+                control_mode=control_info.control_mode,
+                # any resizing needed should currently be happening in prepare_control_image(),
+                #    but adding resize_mode to ControlNetData in case needed in the future
+                resize_mode=control_info.resize_mode,
+            )
+            controlnet_data.append(control_item)
+            # MultiControlNetModel has been refactored out, just need list[ControlNetData]
+
+        return controlnet_data
+
+    def prep_ip_adapter_data(
+        self,
+        context: InvocationContext,
+        ip_adapter: Optional[Union[IPAdapterField, list[IPAdapterField]]],
+        conditioning_data: ConditioningData,
+        exit_stack: ExitStack,
+    ) -> Optional[list[IPAdapterData]]:
+        """If IP-Adapter is enabled, then this function loads the requisite models, and adds the image prompt embeddings
+        to the `conditioning_data` (in-place).
+        """
+        if ip_adapter is None:
+            return None
+
+        # ip_adapter could be a list or a single IPAdapterField. Normalize to a list here.
+        if not isinstance(ip_adapter, list):
+            ip_adapter = [ip_adapter]
+
+        if len(ip_adapter) == 0:
+            return None
+
+        ip_adapter_data_list = []
+        conditioning_data.ip_adapter_conditioning = []
+        for single_ip_adapter in ip_adapter:
+            ip_adapter_model: Union[IPAdapter, IPAdapterPlus] = exit_stack.enter_context(
+                context.services.model_manager.get_model(
+                    model_name=single_ip_adapter.ip_adapter_model.model_name,
+                    model_type=ModelType.IPAdapter,
+                    base_model=single_ip_adapter.ip_adapter_model.base_model,
+                    context=context,
+                )
+            )
+
+            image_encoder_model_info = context.services.model_manager.get_model(
+                model_name=single_ip_adapter.image_encoder_model.model_name,
+                model_type=ModelType.CLIPVision,
+                base_model=single_ip_adapter.image_encoder_model.base_model,
+                context=context,
+            )
+
+            input_image = context.services.images.get_pil_image(single_ip_adapter.image.image_name)
+
+            # TODO(ryand): With some effort, the step of running the CLIP Vision encoder could be done before any other
+            # models are needed in memory. This would help to reduce peak memory utilization in low-memory environments.
+            with image_encoder_model_info as image_encoder_model:
+                # Get image embeddings from CLIP and ImageProjModel.
+                image_prompt_embeds, uncond_image_prompt_embeds = ip_adapter_model.get_image_embeds(
+                    input_image, image_encoder_model
+                )
+                conditioning_data.ip_adapter_conditioning.append(
+                    IPAdapterConditioningInfo(image_prompt_embeds, uncond_image_prompt_embeds)
                 )
 
-                control_models.append(control_model)
-                control_image_field = control_info.image
-                input_image = context.services.images.get_pil_image(control_image_field.image_name)
-                # self.image.image_type, self.image.image_name
-                # FIXME: still need to test with different widths, heights, devices, dtypes
-                #        and add in batch_size, num_images_per_prompt?
-                #        and do real check for classifier_free_guidance?
-                # prepare_control_image should return torch.Tensor of shape(batch_size, 3, height, width)
-                control_image = prepare_control_image(
-                    image=input_image,
-                    do_classifier_free_guidance=do_classifier_free_guidance,
-                    width=control_width_resize,
-                    height=control_height_resize,
-                    # batch_size=batch_size * num_images_per_prompt,
-                    # num_images_per_prompt=num_images_per_prompt,
-                    device=control_model.device,
-                    dtype=control_model.dtype,
-                    control_mode=control_info.control_mode,
-                    resize_mode=control_info.resize_mode,
+            ip_adapter_data_list.append(
+                IPAdapterData(
+                    ip_adapter_model=ip_adapter_model,
+                    weight=single_ip_adapter.weight,
+                    begin_step_percent=single_ip_adapter.begin_step_percent,
+                    end_step_percent=single_ip_adapter.end_step_percent,
                 )
-                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,
-                    control_mode=control_info.control_mode,
-                    # any resizing needed should currently be happening in prepare_control_image(),
-                    #    but adding resize_mode to ControlNetData in case needed in the future
-                    resize_mode=control_info.resize_mode,
+            )
+
+        return ip_adapter_data_list
+
+    def run_t2i_adapters(
+        self,
+        context: InvocationContext,
+        t2i_adapter: Optional[Union[T2IAdapterField, list[T2IAdapterField]]],
+        latents_shape: list[int],
+        do_classifier_free_guidance: bool,
+    ) -> Optional[list[T2IAdapterData]]:
+        if t2i_adapter is None:
+            return None
+
+        # Handle the possibility that t2i_adapter could be a list or a single T2IAdapterField.
+        if isinstance(t2i_adapter, T2IAdapterField):
+            t2i_adapter = [t2i_adapter]
+
+        if len(t2i_adapter) == 0:
+            return None
+
+        t2i_adapter_data = []
+        for t2i_adapter_field in t2i_adapter:
+            t2i_adapter_model_info = context.services.model_manager.get_model(
+                model_name=t2i_adapter_field.t2i_adapter_model.model_name,
+                model_type=ModelType.T2IAdapter,
+                base_model=t2i_adapter_field.t2i_adapter_model.base_model,
+                context=context,
+            )
+            image = context.services.images.get_pil_image(t2i_adapter_field.image.image_name)
+
+            # The max_unet_downscale is the maximum amount that the UNet model downscales the latent image internally.
+            if t2i_adapter_field.t2i_adapter_model.base_model == BaseModelType.StableDiffusion1:
+                max_unet_downscale = 8
+            elif t2i_adapter_field.t2i_adapter_model.base_model == BaseModelType.StableDiffusionXL:
+                max_unet_downscale = 4
+            else:
+                raise ValueError(
+                    f"Unexpected T2I-Adapter base model type: '{t2i_adapter_field.t2i_adapter_model.base_model}'."
                 )
-                control_data.append(control_item)
-                # MultiControlNetModel has been refactored out, just need list[ControlNetData]
-        return control_data
+
+            t2i_adapter_model: T2IAdapter
+            with t2i_adapter_model_info as t2i_adapter_model:
+                total_downscale_factor = t2i_adapter_model.total_downscale_factor
+                if isinstance(t2i_adapter_model.adapter, FullAdapterXL):
+                    # HACK(ryand): Work around a bug in FullAdapterXL. This is being addressed upstream in diffusers by
+                    # this PR: https://github.com/huggingface/diffusers/pull/5134.
+                    total_downscale_factor = total_downscale_factor // 2
+
+                # Resize the T2I-Adapter input image.
+                # We select the resize dimensions so that after the T2I-Adapter's total_downscale_factor is applied, the
+                # result will match the latent image's dimensions after max_unet_downscale is applied.
+                t2i_input_height = latents_shape[2] // max_unet_downscale * total_downscale_factor
+                t2i_input_width = latents_shape[3] // max_unet_downscale * total_downscale_factor
+
+                # Note: We have hard-coded `do_classifier_free_guidance=False`. This is because we only want to prepare
+                # a single image. If CFG is enabled, we will duplicate the resultant tensor after applying the
+                # T2I-Adapter model.
+                #
+                # Note: We re-use the `prepare_control_image(...)` from ControlNet for T2I-Adapter, because it has many
+                # of the same requirements (e.g. preserving binary masks during resize).
+                t2i_image = prepare_control_image(
+                    image=image,
+                    do_classifier_free_guidance=False,
+                    width=t2i_input_width,
+                    height=t2i_input_height,
+                    num_channels=t2i_adapter_model.config.in_channels,
+                    device=t2i_adapter_model.device,
+                    dtype=t2i_adapter_model.dtype,
+                    resize_mode=t2i_adapter_field.resize_mode,
+                )
+
+                adapter_state = t2i_adapter_model(t2i_image)
+
+            if do_classifier_free_guidance:
+                for idx, value in enumerate(adapter_state):
+                    adapter_state[idx] = torch.cat([value] * 2, dim=0)
+
+            t2i_adapter_data.append(
+                T2IAdapterData(
+                    adapter_state=adapter_state,
+                    weight=t2i_adapter_field.weight,
+                    begin_step_percent=t2i_adapter_field.begin_step_percent,
+                    end_step_percent=t2i_adapter_field.end_step_percent,
+                )
+            )
+
+        return t2i_adapter_data
 
     # original idea by https://github.com/AmericanPresidentJimmyCarter
     # TODO: research more for second order schedulers timesteps
@@ -467,6 +625,12 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
             mask, masked_latents = self.prep_inpaint_mask(context, latents)
 
+            # TODO(ryand): I have hard-coded `do_classifier_free_guidance=True` to mirror the behaviour of ControlNets,
+            # below. Investigate whether this is appropriate.
+            t2i_adapter_data = self.run_t2i_adapters(
+                context, self.t2i_adapter, latents.shape, do_classifier_free_guidance=True
+            )
+
             # Get the source node id (we are invoking the prepared node)
             graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
             source_node_id = graph_execution_state.prepared_source_mapping[self.id]
@@ -488,9 +652,12 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 **self.unet.unet.dict(),
                 context=context,
             )
-            with ExitStack() as exit_stack, ModelPatcher.apply_lora_unet(
-                unet_info.context.model, _lora_loader()
-            ), set_seamless(unet_info.context.model, self.unet.seamless_axes), unet_info as unet:
+            with (
+                ExitStack() as exit_stack,
+                ModelPatcher.apply_lora_unet(unet_info.context.model, _lora_loader()),
+                set_seamless(unet_info.context.model, self.unet.seamless_axes),
+                unet_info as unet,
+            ):
                 latents = latents.to(device=unet.device, dtype=unet.dtype)
                 if noise is not None:
                     noise = noise.to(device=unet.device, dtype=unet.dtype)
@@ -509,8 +676,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 pipeline = self.create_pipeline(unet, scheduler)
                 conditioning_data = self.get_conditioning_data(context, scheduler, unet, seed)
 
-                control_data = self.prep_control_data(
-                    model=pipeline,
+                controlnet_data = self.prep_control_data(
                     context=context,
                     control_input=self.control,
                     latents_shape=latents.shape,
@@ -519,6 +685,13 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     exit_stack=exit_stack,
                 )
 
+                ip_adapter_data = self.prep_ip_adapter_data(
+                    context=context,
+                    ip_adapter=self.ip_adapter,
+                    conditioning_data=conditioning_data,
+                    exit_stack=exit_stack,
+                )
+
                 num_inference_steps, timesteps, init_timestep = self.init_scheduler(
                     scheduler,
                     device=unet.device,
@@ -537,7 +710,9 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     masked_latents=masked_latents,
                     num_inference_steps=num_inference_steps,
                     conditioning_data=conditioning_data,
-                    control_data=control_data,  # list[ControlNetData]
+                    control_data=controlnet_data,
+                    ip_adapter_data=ip_adapter_data,
+                    t2i_adapter_data=t2i_adapter_data,
                     callback=step_callback,
                 )
 
@@ -792,8 +967,7 @@ class ImageToLatentsInvocation(BaseInvocation):
             # non_noised_latents_from_image
             image_tensor = image_tensor.to(device=vae.device, dtype=vae.dtype)
             with torch.inference_mode():
-                image_tensor_dist = vae.encode(image_tensor).latent_dist
-                latents = image_tensor_dist.sample().to(dtype=vae.dtype)  # FIXME: uses torch.randn. make reproducible!
+                latents = ImageToLatentsInvocation._encode_to_tensor(vae, image_tensor)
 
             latents = vae.config.scaling_factor * latents
             latents = latents.to(dtype=orig_dtype)
@@ -820,6 +994,18 @@ class ImageToLatentsInvocation(BaseInvocation):
         context.services.latents.save(name, latents)
         return build_latents_output(latents_name=name, latents=latents, seed=None)
 
+    @singledispatchmethod
+    @staticmethod
+    def _encode_to_tensor(vae: AutoencoderKL, image_tensor: torch.FloatTensor) -> torch.FloatTensor:
+        image_tensor_dist = vae.encode(image_tensor).latent_dist
+        latents = image_tensor_dist.sample().to(dtype=vae.dtype)  # FIXME: uses torch.randn. make reproducible!
+        return latents
+
+    @_encode_to_tensor.register
+    @staticmethod
+    def _(vae: AutoencoderTiny, image_tensor: torch.FloatTensor) -> torch.FloatTensor:
+        return vae.encode(image_tensor).latents
+
 
 @invocation("lblend", title="Blend Latents", tags=["latents", "blend"], category="latents", version="1.0.0")
 class BlendLatentsInvocation(BaseInvocation):

invokeai/app/invocations/math.py

@@ -54,17 +54,38 @@ class DivideInvocation(BaseInvocation):
         return IntegerOutput(value=int(self.a / self.b))
 
 
-@invocation("rand_int", title="Random Integer", tags=["math", "random"], category="math", version="1.0.0")
+@invocation(
+    "rand_int",
+    title="Random Integer",
+    tags=["math", "random"],
+    category="math",
+    version="1.0.0",
+    use_cache=False,
+)
 class RandomIntInvocation(BaseInvocation):
     """Outputs a single random integer."""
 
-    low: int = InputField(default=0, description="The inclusive low value")
-    high: int = InputField(default=np.iinfo(np.int32).max, description="The exclusive high value")
+    low: int = InputField(default=0, description=FieldDescriptions.inclusive_low)
+    high: int = InputField(default=np.iinfo(np.int32).max, description=FieldDescriptions.exclusive_high)
 
     def invoke(self, context: InvocationContext) -> IntegerOutput:
         return IntegerOutput(value=np.random.randint(self.low, self.high))
 
 
+@invocation("rand_float", title="Random Float", tags=["math", "float", "random"], category="math", version="1.0.0")
+class RandomFloatInvocation(BaseInvocation):
+    """Outputs a single random float"""
+
+    low: float = InputField(default=0.0, description=FieldDescriptions.inclusive_low)
+    high: float = InputField(default=1.0, description=FieldDescriptions.exclusive_high)
+    decimals: int = InputField(default=2, description=FieldDescriptions.decimal_places)
+
+    def invoke(self, context: InvocationContext) -> FloatOutput:
+        random_float = np.random.uniform(self.low, self.high)
+        rounded_float = round(random_float, self.decimals)
+        return FloatOutput(value=rounded_float)
+
+
 @invocation(
     "float_to_int",
     title="Float To Integer",

invokeai/app/invocations/metadata.py

@@ -12,7 +12,10 @@ from invokeai.app.invocations.baseinvocation import (
     invocation_output,
 )
 from invokeai.app.invocations.controlnet_image_processors import ControlField
+from invokeai.app.invocations.ip_adapter import IPAdapterModelField
 from invokeai.app.invocations.model import LoRAModelField, MainModelField, VAEModelField
+from invokeai.app.invocations.primitives import ImageField
+from invokeai.app.invocations.t2i_adapter import T2IAdapterField
 from invokeai.app.util.model_exclude_null import BaseModelExcludeNull
 
 from ...version import __version__
@@ -25,29 +28,47 @@ class LoRAMetadataField(BaseModelExcludeNull):
     weight: float = Field(description="The weight of the LoRA model")
 
 
+class IPAdapterMetadataField(BaseModelExcludeNull):
+    image: ImageField = Field(description="The IP-Adapter image prompt.")
+    ip_adapter_model: IPAdapterModelField = Field(description="The IP-Adapter model to use.")
+    weight: float = Field(description="The weight of the IP-Adapter model")
+    begin_step_percent: float = Field(
+        default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
+    )
+    end_step_percent: float = Field(
+        default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
+    )
+
+
 class CoreMetadata(BaseModelExcludeNull):
     """Core generation metadata for an image generated in InvokeAI."""
 
     app_version: str = Field(default=__version__, description="The version of InvokeAI used to generate this image")
-    generation_mode: str = Field(
+    generation_mode: Optional[str] = Field(
+        default=None,
         description="The generation mode that output this image",
     )
     created_by: Optional[str] = Field(description="The name of the creator of the image")
-    positive_prompt: str = Field(description="The positive prompt parameter")
-    negative_prompt: str = Field(description="The negative prompt parameter")
-    width: int = Field(description="The width parameter")
-    height: int = Field(description="The height parameter")
-    seed: int = Field(description="The seed used for noise generation")
-    rand_device: str = Field(description="The device used for random number generation")
-    cfg_scale: float = Field(description="The classifier-free guidance scale parameter")
-    steps: int = Field(description="The number of steps used for inference")
-    scheduler: str = Field(description="The scheduler used for inference")
-    clip_skip: int = Field(
+    positive_prompt: Optional[str] = Field(default=None, description="The positive prompt parameter")
+    negative_prompt: Optional[str] = Field(default=None, description="The negative prompt parameter")
+    width: Optional[int] = Field(default=None, description="The width parameter")
+    height: Optional[int] = Field(default=None, description="The height parameter")
+    seed: Optional[int] = Field(default=None, description="The seed used for noise generation")
+    rand_device: Optional[str] = Field(default=None, description="The device used for random number generation")
+    cfg_scale: Optional[float] = Field(default=None, description="The classifier-free guidance scale parameter")
+    steps: Optional[int] = Field(default=None, description="The number of steps used for inference")
+    scheduler: Optional[str] = Field(default=None, description="The scheduler used for inference")
+    clip_skip: Optional[int] = Field(
+        default=None,
         description="The number of skipped CLIP layers",
     )
-    model: MainModelField = Field(description="The main model used for inference")
-    controlnets: list[ControlField] = Field(description="The ControlNets used for inference")
-    loras: list[LoRAMetadataField] = Field(description="The LoRAs used for inference")
+    model: Optional[MainModelField] = Field(default=None, description="The main model used for inference")
+    controlnets: Optional[list[ControlField]] = Field(default=None, description="The ControlNets used for inference")
+    ipAdapters: Optional[list[IPAdapterMetadataField]] = Field(
+        default=None, description="The IP Adapters used for inference"
+    )
+    t2iAdapters: Optional[list[T2IAdapterField]] = Field(default=None, description="The IP Adapters used for inference")
+    loras: Optional[list[LoRAMetadataField]] = Field(default=None, description="The LoRAs used for inference")
     vae: Optional[VAEModelField] = Field(
         default=None,
         description="The VAE used for decoding, if the main model's default was not used",
@@ -104,24 +125,34 @@ class MetadataAccumulatorOutput(BaseInvocationOutput):
 class MetadataAccumulatorInvocation(BaseInvocation):
     """Outputs a Core Metadata Object"""
 
-    generation_mode: str = InputField(
+    generation_mode: Optional[str] = InputField(
+        default=None,
         description="The generation mode that output this image",
     )
-    positive_prompt: str = InputField(description="The positive prompt parameter")
-    negative_prompt: str = InputField(description="The negative prompt parameter")
-    width: int = InputField(description="The width parameter")
-    height: int = InputField(description="The height parameter")
-    seed: int = InputField(description="The seed used for noise generation")
-    rand_device: str = InputField(description="The device used for random number generation")
-    cfg_scale: float = InputField(description="The classifier-free guidance scale parameter")
-    steps: int = InputField(description="The number of steps used for inference")
-    scheduler: str = InputField(description="The scheduler used for inference")
-    clip_skip: int = InputField(
+    positive_prompt: Optional[str] = InputField(default=None, description="The positive prompt parameter")
+    negative_prompt: Optional[str] = InputField(default=None, description="The negative prompt parameter")
+    width: Optional[int] = InputField(default=None, description="The width parameter")
+    height: Optional[int] = InputField(default=None, description="The height parameter")
+    seed: Optional[int] = InputField(default=None, description="The seed used for noise generation")
+    rand_device: Optional[str] = InputField(default=None, description="The device used for random number generation")
+    cfg_scale: Optional[float] = InputField(default=None, description="The classifier-free guidance scale parameter")
+    steps: Optional[int] = InputField(default=None, description="The number of steps used for inference")
+    scheduler: Optional[str] = InputField(default=None, description="The scheduler used for inference")
+    clip_skip: Optional[int] = InputField(
+        default=None,
         description="The number of skipped CLIP layers",
     )
-    model: MainModelField = InputField(description="The main model used for inference")
-    controlnets: list[ControlField] = InputField(description="The ControlNets used for inference")
-    loras: list[LoRAMetadataField] = InputField(description="The LoRAs used for inference")
+    model: Optional[MainModelField] = InputField(default=None, description="The main model used for inference")
+    controlnets: Optional[list[ControlField]] = InputField(
+        default=None, description="The ControlNets used for inference"
+    )
+    ipAdapters: Optional[list[IPAdapterMetadataField]] = InputField(
+        default=None, description="The IP Adapters used for inference"
+    )
+    t2iAdapters: Optional[list[T2IAdapterField]] = InputField(
+        default=None, description="The IP Adapters used for inference"
+    )
+    loras: Optional[list[LoRAMetadataField]] = InputField(default=None, description="The LoRAs used for inference")
     strength: Optional[float] = InputField(
         default=None,
         description="The strength used for latents-to-latents",
@@ -135,6 +166,20 @@ class MetadataAccumulatorInvocation(BaseInvocation):
         description="The VAE used for decoding, if the main model's default was not used",
     )
 
+    # High resolution fix metadata.
+    hrf_width: Optional[int] = InputField(
+        default=None,
+        description="The high resolution fix height and width multipler.",
+    )
+    hrf_height: Optional[int] = InputField(
+        default=None,
+        description="The high resolution fix height and width multipler.",
+    )
+    hrf_strength: Optional[float] = InputField(
+        default=None,
+        description="The high resolution fix img2img strength used in the upscale pass.",
+    )
+
     # SDXL
     positive_style_prompt: Optional[str] = InputField(
         default=None,

invokeai/app/invocations/onnx.py

@@ -95,9 +95,10 @@ class ONNXPromptInvocation(BaseInvocation):
                     print(f'Warn: trigger: "{trigger}" not found')
             if loras or ti_list:
                 text_encoder.release_session()
-            with ONNXModelPatcher.apply_lora_text_encoder(text_encoder, loras), ONNXModelPatcher.apply_ti(
-                orig_tokenizer, text_encoder, ti_list
-            ) as (tokenizer, ti_manager):
+            with (
+                ONNXModelPatcher.apply_lora_text_encoder(text_encoder, loras),
+                ONNXModelPatcher.apply_ti(orig_tokenizer, text_encoder, ti_list) as (tokenizer, ti_manager),
+            ):
                 text_encoder.create_session()
 
                 # copy from
@@ -165,7 +166,6 @@ class ONNXTextToLatentsInvocation(BaseInvocation):
         default=7.5,
         ge=1,
         description=FieldDescriptions.cfg_scale,
-        ui_type=UIType.Float,
     )
     scheduler: SAMPLER_NAME_VALUES = InputField(
         default="euler", description=FieldDescriptions.scheduler, input=Input.Direct, ui_type=UIType.Scheduler
@@ -178,7 +178,6 @@ class ONNXTextToLatentsInvocation(BaseInvocation):
     control: Optional[Union[ControlField, list[ControlField]]] = InputField(
         default=None,
         description=FieldDescriptions.control,
-        ui_type=UIType.Control,
     )
     # seamless:   bool = InputField(default=False, description="Whether or not to generate an image that can tile without seams", )
     # seamless_axes: str = InputField(default="", description="The axes to tile the image on, 'x' and/or 'y'")

invokeai/app/invocations/primitives.py

@@ -226,6 +226,12 @@ class ImageField(BaseModel):
     image_name: str = Field(description="The name of the image")
 
 
+class BoardField(BaseModel):
+    """A board primitive field"""
+
+    board_id: str = Field(description="The id of the board")
+
+
 @invocation_output("image_output")
 class ImageOutput(BaseInvocationOutput):
     """Base class for nodes that output a single image"""

invokeai/app/invocations/prompt.py

@@ -10,7 +10,14 @@ from invokeai.app.invocations.primitives import StringCollectionOutput
 from .baseinvocation import BaseInvocation, InputField, InvocationContext, UIComponent, invocation
 
 
-@invocation("dynamic_prompt", title="Dynamic Prompt", tags=["prompt", "collection"], category="prompt", version="1.0.0")
+@invocation(
+    "dynamic_prompt",
+    title="Dynamic Prompt",
+    tags=["prompt", "collection"],
+    category="prompt",
+    version="1.0.0",
+    use_cache=False,
+)
 class DynamicPromptInvocation(BaseInvocation):
     """Parses a prompt using adieyal/dynamicprompts' random or combinatorial generator"""
 

invokeai/app/invocations/t2i_adapter.py

@@ -0,0 +1,83 @@
+from typing import Union
+
+from pydantic import BaseModel, Field
+
+from invokeai.app.invocations.baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    FieldDescriptions,
+    Input,
+    InputField,
+    InvocationContext,
+    OutputField,
+    UIType,
+    invocation,
+    invocation_output,
+)
+from invokeai.app.invocations.controlnet_image_processors import CONTROLNET_RESIZE_VALUES
+from invokeai.app.invocations.primitives import ImageField
+from invokeai.backend.model_management.models.base import BaseModelType
+
+
+class T2IAdapterModelField(BaseModel):
+    model_name: str = Field(description="Name of the T2I-Adapter model")
+    base_model: BaseModelType = Field(description="Base model")
+
+
+class T2IAdapterField(BaseModel):
+    image: ImageField = Field(description="The T2I-Adapter image prompt.")
+    t2i_adapter_model: T2IAdapterModelField = Field(description="The T2I-Adapter model to use.")
+    weight: Union[float, list[float]] = Field(default=1, description="The weight given to the T2I-Adapter")
+    begin_step_percent: float = Field(
+        default=0, ge=0, le=1, description="When the T2I-Adapter is first applied (% of total steps)"
+    )
+    end_step_percent: float = Field(
+        default=1, ge=0, le=1, description="When the T2I-Adapter is last applied (% of total steps)"
+    )
+    resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
+
+
+@invocation_output("t2i_adapter_output")
+class T2IAdapterOutput(BaseInvocationOutput):
+    t2i_adapter: T2IAdapterField = OutputField(description=FieldDescriptions.t2i_adapter, title="T2I Adapter")
+
+
+@invocation(
+    "t2i_adapter", title="T2I-Adapter", tags=["t2i_adapter", "control"], category="t2i_adapter", version="1.0.0"
+)
+class T2IAdapterInvocation(BaseInvocation):
+    """Collects T2I-Adapter info to pass to other nodes."""
+
+    # Inputs
+    image: ImageField = InputField(description="The IP-Adapter image prompt.")
+    t2i_adapter_model: T2IAdapterModelField = InputField(
+        description="The T2I-Adapter model.",
+        title="T2I-Adapter Model",
+        input=Input.Direct,
+        ui_order=-1,
+    )
+    weight: Union[float, list[float]] = InputField(
+        default=1, ge=0, description="The weight given to the T2I-Adapter", ui_type=UIType.Float, title="Weight"
+    )
+    begin_step_percent: float = InputField(
+        default=0, ge=-1, le=2, description="When the T2I-Adapter is first applied (% of total steps)"
+    )
+    end_step_percent: float = InputField(
+        default=1, ge=0, le=1, description="When the T2I-Adapter is last applied (% of total steps)"
+    )
+    resize_mode: CONTROLNET_RESIZE_VALUES = InputField(
+        default="just_resize",
+        description="The resize mode applied to the T2I-Adapter input image so that it matches the target output size.",
+    )
+
+    def invoke(self, context: InvocationContext) -> T2IAdapterOutput:
+        return T2IAdapterOutput(
+            t2i_adapter=T2IAdapterField(
+                image=self.image,
+                t2i_adapter_model=self.t2i_adapter_model,
+                weight=self.weight,
+                begin_step_percent=self.begin_step_percent,
+                end_step_percent=self.end_step_percent,
+                resize_mode=self.resize_mode,
+            )
+        )

invokeai/app/invocations/upscale.py

@@ -4,12 +4,14 @@ from typing import Literal
 
 import cv2 as cv
 import numpy as np
+import torch
 from basicsr.archs.rrdbnet_arch import RRDBNet
 from PIL import Image
 from realesrgan import RealESRGANer
 
 from invokeai.app.invocations.primitives import ImageField, ImageOutput
 from invokeai.app.models.image import ImageCategory, ResourceOrigin
+from invokeai.backend.util.devices import choose_torch_device
 
 from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
 
@@ -22,13 +24,19 @@ ESRGAN_MODELS = Literal[
     "RealESRGAN_x2plus.pth",
 ]
 
+if choose_torch_device() == torch.device("mps"):
+    from torch import mps
 
-@invocation("esrgan", title="Upscale (RealESRGAN)", tags=["esrgan", "upscale"], category="esrgan", version="1.0.0")
+
+@invocation("esrgan", title="Upscale (RealESRGAN)", tags=["esrgan", "upscale"], category="esrgan", version="1.1.0")
 class ESRGANInvocation(BaseInvocation):
     """Upscales an image using RealESRGAN."""
 
     image: ImageField = InputField(description="The input image")
     model_name: ESRGAN_MODELS = InputField(default="RealESRGAN_x4plus.pth", description="The Real-ESRGAN model to use")
+    tile_size: int = InputField(
+        default=400, ge=0, description="Tile size for tiled ESRGAN upscaling (0=tiling disabled)"
+    )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get_pil_image(self.image.image_name)
@@ -86,9 +94,11 @@ class ESRGANInvocation(BaseInvocation):
             model_path=str(models_path / esrgan_model_path),
             model=rrdbnet_model,
             half=False,
+            tile=self.tile_size,
         )
 
         # prepare image - Real-ESRGAN uses cv2 internally, and cv2 uses BGR vs RGB for PIL
+        # TODO: This strips the alpha... is that okay?
         cv_image = cv.cvtColor(np.array(image.convert("RGB")), cv.COLOR_RGB2BGR)
 
         # We can pass an `outscale` value here, but it just resizes the image by that factor after
@@ -99,6 +109,10 @@ class ESRGANInvocation(BaseInvocation):
         # back to PIL
         pil_image = Image.fromarray(cv.cvtColor(upscaled_image, cv.COLOR_BGR2RGB)).convert("RGBA")
 
+        torch.cuda.empty_cache()
+        if choose_torch_device() == torch.device("mps"):
+            mps.empty_cache()
+
         image_dto = context.services.images.create(
             image=pil_image,
             image_origin=ResourceOrigin.INTERNAL,

invokeai/app/services/board_image_record_storage.py

@@ -53,24 +53,20 @@ class BoardImageRecordStorageBase(ABC):
 
 
 class SqliteBoardImageRecordStorage(BoardImageRecordStorageBase):
-    _filename: str
     _conn: sqlite3.Connection
     _cursor: sqlite3.Cursor
-    _lock: threading.Lock
+    _lock: threading.RLock
 
-    def __init__(self, filename: str) -> None:
+    def __init__(self, conn: sqlite3.Connection, lock: threading.RLock) -> None:
         super().__init__()
-        self._filename = filename
-        self._conn = sqlite3.connect(filename, check_same_thread=False)
+        self._conn = conn
         # Enable row factory to get rows as dictionaries (must be done before making the cursor!)
         self._conn.row_factory = sqlite3.Row
         self._cursor = self._conn.cursor()
-        self._lock = threading.Lock()
+        self._lock = lock
 
         try:
             self._lock.acquire()
-            # Enable foreign keys
-            self._conn.execute("PRAGMA foreign_keys = ON;")
             self._create_tables()
             self._conn.commit()
         finally:

invokeai/app/services/board_record_storage.py

@@ -1,6 +1,5 @@
 import sqlite3
 import threading
-import uuid
 from abc import ABC, abstractmethod
 from typing import Optional, Union, cast
 
@@ -8,6 +7,7 @@ from pydantic import BaseModel, Extra, Field
 
 from invokeai.app.services.image_record_storage import OffsetPaginatedResults
 from invokeai.app.services.models.board_record import BoardRecord, deserialize_board_record
+from invokeai.app.util.misc import uuid_string
 
 
 class BoardChanges(BaseModel, extra=Extra.forbid):
@@ -87,24 +87,20 @@ class BoardRecordStorageBase(ABC):
 
 
 class SqliteBoardRecordStorage(BoardRecordStorageBase):
-    _filename: str
     _conn: sqlite3.Connection
     _cursor: sqlite3.Cursor
-    _lock: threading.Lock
+    _lock: threading.RLock
 
-    def __init__(self, filename: str) -> None:
+    def __init__(self, conn: sqlite3.Connection, lock: threading.RLock) -> None:
         super().__init__()
-        self._filename = filename
-        self._conn = sqlite3.connect(filename, check_same_thread=False)
+        self._conn = conn
         # Enable row factory to get rows as dictionaries (must be done before making the cursor!)
         self._conn.row_factory = sqlite3.Row
         self._cursor = self._conn.cursor()
-        self._lock = threading.Lock()
+        self._lock = lock
 
         try:
             self._lock.acquire()
-            # Enable foreign keys
-            self._conn.execute("PRAGMA foreign_keys = ON;")
             self._create_tables()
             self._conn.commit()
         finally:
@@ -174,7 +170,7 @@ class SqliteBoardRecordStorage(BoardRecordStorageBase):
         board_name: str,
     ) -> BoardRecord:
         try:
-            board_id = str(uuid.uuid4())
+            board_id = uuid_string()
             self._lock.acquire()
             self._cursor.execute(
                 """--sql

invokeai/app/services/config/base.py

@@ -16,7 +16,7 @@ import pydoc
 import sys
 from argparse import ArgumentParser
 from pathlib import Path
-from typing import ClassVar, Dict, List, Literal, Union, get_args, get_origin, get_type_hints
+from typing import ClassVar, Dict, List, Literal, Optional, Union, get_args, get_origin, get_type_hints
 
 from omegaconf import DictConfig, ListConfig, OmegaConf
 from pydantic import BaseSettings
@@ -39,10 +39,10 @@ class InvokeAISettings(BaseSettings):
     read from an omegaconf .yaml file.
     """
 
-    initconf: ClassVar[DictConfig] = None
+    initconf: ClassVar[Optional[DictConfig]] = None
     argparse_groups: ClassVar[Dict] = {}
 
-    def parse_args(self, argv: list = sys.argv[1:]):
+    def parse_args(self, argv: Optional[list] = sys.argv[1:]):
         parser = self.get_parser()
         opt, unknown_opts = parser.parse_known_args(argv)
         if len(unknown_opts) > 0:
@@ -83,7 +83,8 @@ class InvokeAISettings(BaseSettings):
         else:
             settings_stanza = "Uncategorized"
 
-        env_prefix = cls.Config.env_prefix if hasattr(cls.Config, "env_prefix") else settings_stanza.upper()
+        env_prefix = getattr(cls.Config, "env_prefix", None)
+        env_prefix = env_prefix if env_prefix is not None else settings_stanza.upper()
 
         initconf = (
             cls.initconf.get(settings_stanza)
@@ -116,8 +117,8 @@ class InvokeAISettings(BaseSettings):
                 field.default = current_default
 
     @classmethod
-    def cmd_name(self, command_field: str = "type") -> str:
-        hints = get_type_hints(self)
+    def cmd_name(cls, command_field: str = "type") -> str:
+        hints = get_type_hints(cls)
         if command_field in hints:
             return get_args(hints[command_field])[0]
         else:
@@ -133,16 +134,12 @@ class InvokeAISettings(BaseSettings):
         return parser
 
     @classmethod
-    def add_subparser(cls, parser: argparse.ArgumentParser):
-        parser.add_parser(cls.cmd_name(), help=cls.__doc__)
-
-    @classmethod
-    def _excluded(self) -> List[str]:
+    def _excluded(cls) -> List[str]:
         # internal fields that shouldn't be exposed as command line options
         return ["type", "initconf"]
 
     @classmethod
-    def _excluded_from_yaml(self) -> List[str]:
+    def _excluded_from_yaml(cls) -> List[str]:
         # combination of deprecated parameters and internal ones that shouldn't be exposed as invokeai.yaml options
         return [
             "type",

invokeai/app/services/config/invokeai_config.py

@@ -194,8 +194,8 @@ class InvokeAIAppConfig(InvokeAISettings):
     setting environment variables INVOKEAI_<setting>.
     """
 
-    singleton_config: ClassVar[InvokeAIAppConfig] = None
-    singleton_init: ClassVar[Dict] = None
+    singleton_config: ClassVar[Optional[InvokeAIAppConfig]] = None
+    singleton_init: ClassVar[Optional[Dict]] = None
 
     # fmt: off
     type: Literal["InvokeAI"] = "InvokeAI"
@@ -234,29 +234,36 @@ class InvokeAIAppConfig(InvokeAISettings):
     # note - would be better to read the log_format values from logging.py, but this creates circular dependencies issues
     log_format          : Literal['plain', 'color', 'syslog', 'legacy'] = Field(default="color", description='Log format. Use "plain" for text-only, "color" for colorized output, "legacy" for 2.3-style logging and "syslog" for syslog-style', category="Logging")
     log_level           : Literal["debug", "info", "warning", "error", "critical"] = Field(default="info", description="Emit logging messages at this level or  higher", category="Logging")
+    log_sql             : bool = Field(default=False, description="Log SQL queries", category="Logging")
 
     dev_reload          : bool = Field(default=False, description="Automatically reload when Python sources are changed.", category="Development")
 
     version             : bool = Field(default=False, description="Show InvokeAI version and exit", category="Other")
 
     # CACHE
-    ram                 : Union[float, Literal["auto"]] = Field(default=6.0, gt=0, description="Maximum memory amount used by model cache for rapid switching (floating point number or 'auto')", category="Model Cache", )
-    vram                : Union[float, Literal["auto"]] = Field(default=0.25, ge=0, description="Amount of VRAM reserved for model storage (floating point number or 'auto')", category="Model Cache", )
+    ram                 : float = Field(default=7.5, gt=0, description="Maximum memory amount used by model cache for rapid switching (floating point number, GB)", category="Model Cache", )
+    vram                : float = Field(default=0.25, ge=0, description="Amount of VRAM reserved for model storage (floating point number, GB)", category="Model Cache", )
     lazy_offload        : bool = Field(default=True, description="Keep models in VRAM until their space is needed", category="Model Cache", )
 
     # DEVICE
-    device              : Literal[tuple(["auto", "cpu", "cuda", "cuda:1", "mps"])] = Field(default="auto", description="Generation device", category="Device", )
-    precision: Literal[tuple(["auto", "float16", "float32", "autocast"])] = Field(default="auto", description="Floating point precision", category="Device", )
+    device              : Literal["auto", "cpu", "cuda", "cuda:1", "mps"] = Field(default="auto", description="Generation device", category="Device", )
+    precision           : Literal["auto", "float16", "float32", "autocast"] = Field(default="auto", description="Floating point precision", category="Device", )
 
     # GENERATION
     sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", category="Generation", )
-    attention_type      : Literal[tuple(["auto", "normal", "xformers", "sliced", "torch-sdp"])] = Field(default="auto", description="Attention type", category="Generation", )
-    attention_slice_size: Literal[tuple(["auto", "balanced", "max", 1, 2, 3, 4, 5, 6, 7, 8])] = Field(default="auto", description='Slice size, valid when attention_type=="sliced"', category="Generation", )
+    attention_type      : Literal["auto", "normal", "xformers", "sliced", "torch-sdp"] = Field(default="auto", description="Attention type", category="Generation", )
+    attention_slice_size: Literal["auto", "balanced", "max", 1, 2, 3, 4, 5, 6, 7, 8] = Field(default="auto", description='Slice size, valid when attention_type=="sliced"', category="Generation", )
+    force_tiled_decode  : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", category="Generation",)
     force_tiled_decode: bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", category="Generation",)
+    png_compress_level  : int = Field(default=6, description="The compress_level setting of PIL.Image.save(), used for PNG encoding. All settings are lossless. 0 = fastest, largest filesize, 9 = slowest, smallest filesize", category="Generation", )
+
+    # QUEUE
+    max_queue_size      : int = Field(default=10000, gt=0, description="Maximum number of items in the session queue", category="Queue", )
 
     # NODES
     allow_nodes         : Optional[List[str]] = Field(default=None, description="List of nodes to allow. Omit to allow all.", category="Nodes")
     deny_nodes          : Optional[List[str]] = Field(default=None, description="List of nodes to deny. Omit to deny none.", category="Nodes")
+    node_cache_size     : int = Field(default=512, description="How many cached nodes to keep in memory", category="Nodes", )
 
     # DEPRECATED FIELDS - STILL HERE IN ORDER TO OBTAN VALUES FROM PRE-3.1 CONFIG FILES
     always_use_cpu      : bool = Field(default=False, description="If true, use the CPU for rendering even if a GPU is available.", category='Memory/Performance')
@@ -271,8 +278,9 @@ class InvokeAIAppConfig(InvokeAISettings):
 
     class Config:
         validate_assignment = True
+        env_prefix = "INVOKEAI"
 
-    def parse_args(self, argv: List[str] = None, conf: DictConfig = None, clobber=False):
+    def parse_args(self, argv: Optional[list[str]] = None, conf: Optional[DictConfig] = None, clobber=False):
         """
         Update settings with contents of init file, environment, and
         command-line settings.
@@ -283,12 +291,16 @@ class InvokeAIAppConfig(InvokeAISettings):
         # Set the runtime root directory. We parse command-line switches here
         # in order to pick up the --root_dir option.
         super().parse_args(argv)
+        loaded_conf = None
         if conf is None:
             try:
-                conf = OmegaConf.load(self.root_dir / INIT_FILE)
+                loaded_conf = OmegaConf.load(self.root_dir / INIT_FILE)
             except Exception:
                 pass
-        InvokeAISettings.initconf = conf
+        if isinstance(loaded_conf, DictConfig):
+            InvokeAISettings.initconf = loaded_conf
+        else:
+            InvokeAISettings.initconf = conf
 
         # parse args again in order to pick up settings in configuration file
         super().parse_args(argv)
@@ -376,13 +388,6 @@ class InvokeAIAppConfig(InvokeAISettings):
         """
         return self._resolve(self.models_dir)
 
-    @property
-    def autoconvert_path(self) -> Path:
-        """
-        Path to the directory containing models to be imported automatically at startup.
-        """
-        return self._resolve(self.autoconvert_dir) if self.autoconvert_dir else None
-
     # the following methods support legacy calls leftover from the Globals era
     @property
     def full_precision(self) -> bool:
@@ -405,11 +410,11 @@ class InvokeAIAppConfig(InvokeAISettings):
         return True
 
     @property
-    def ram_cache_size(self) -> float:
+    def ram_cache_size(self) -> Union[Literal["auto"], float]:
         return self.max_cache_size or self.ram
 
     @property
-    def vram_cache_size(self) -> float:
+    def vram_cache_size(self) -> Union[Literal["auto"], float]:
         return self.max_vram_cache_size or self.vram
 
     @property

invokeai/app/services/default_graphs.py

@@ -10,57 +10,58 @@ default_text_to_image_graph_id = "539b2af5-2b4d-4d8c-8071-e54a3255fc74"
 
 
 def create_text_to_image() -> LibraryGraph:
+    graph = Graph(
+        nodes={
+            "width": IntegerInvocation(id="width", value=512),
+            "height": IntegerInvocation(id="height", value=512),
+            "seed": IntegerInvocation(id="seed", value=-1),
+            "3": NoiseInvocation(id="3"),
+            "4": CompelInvocation(id="4"),
+            "5": CompelInvocation(id="5"),
+            "6": DenoiseLatentsInvocation(id="6"),
+            "7": LatentsToImageInvocation(id="7"),
+            "8": ImageNSFWBlurInvocation(id="8"),
+        },
+        edges=[
+            Edge(
+                source=EdgeConnection(node_id="width", field="value"),
+                destination=EdgeConnection(node_id="3", field="width"),
+            ),
+            Edge(
+                source=EdgeConnection(node_id="height", field="value"),
+                destination=EdgeConnection(node_id="3", field="height"),
+            ),
+            Edge(
+                source=EdgeConnection(node_id="seed", field="value"),
+                destination=EdgeConnection(node_id="3", field="seed"),
+            ),
+            Edge(
+                source=EdgeConnection(node_id="3", field="noise"),
+                destination=EdgeConnection(node_id="6", field="noise"),
+            ),
+            Edge(
+                source=EdgeConnection(node_id="6", field="latents"),
+                destination=EdgeConnection(node_id="7", field="latents"),
+            ),
+            Edge(
+                source=EdgeConnection(node_id="4", field="conditioning"),
+                destination=EdgeConnection(node_id="6", field="positive_conditioning"),
+            ),
+            Edge(
+                source=EdgeConnection(node_id="5", field="conditioning"),
+                destination=EdgeConnection(node_id="6", field="negative_conditioning"),
+            ),
+            Edge(
+                source=EdgeConnection(node_id="7", field="image"),
+                destination=EdgeConnection(node_id="8", field="image"),
+            ),
+        ],
+    )
     return LibraryGraph(
         id=default_text_to_image_graph_id,
         name="t2i",
         description="Converts text to an image",
-        graph=Graph(
-            nodes={
-                "width": IntegerInvocation(id="width", value=512),
-                "height": IntegerInvocation(id="height", value=512),
-                "seed": IntegerInvocation(id="seed", value=-1),
-                "3": NoiseInvocation(id="3"),
-                "4": CompelInvocation(id="4"),
-                "5": CompelInvocation(id="5"),
-                "6": DenoiseLatentsInvocation(id="6"),
-                "7": LatentsToImageInvocation(id="7"),
-                "8": ImageNSFWBlurInvocation(id="8"),
-            },
-            edges=[
-                Edge(
-                    source=EdgeConnection(node_id="width", field="value"),
-                    destination=EdgeConnection(node_id="3", field="width"),
-                ),
-                Edge(
-                    source=EdgeConnection(node_id="height", field="value"),
-                    destination=EdgeConnection(node_id="3", field="height"),
-                ),
-                Edge(
-                    source=EdgeConnection(node_id="seed", field="value"),
-                    destination=EdgeConnection(node_id="3", field="seed"),
-                ),
-                Edge(
-                    source=EdgeConnection(node_id="3", field="noise"),
-                    destination=EdgeConnection(node_id="6", field="noise"),
-                ),
-                Edge(
-                    source=EdgeConnection(node_id="6", field="latents"),
-                    destination=EdgeConnection(node_id="7", field="latents"),
-                ),
-                Edge(
-                    source=EdgeConnection(node_id="4", field="conditioning"),
-                    destination=EdgeConnection(node_id="6", field="positive_conditioning"),
-                ),
-                Edge(
-                    source=EdgeConnection(node_id="5", field="conditioning"),
-                    destination=EdgeConnection(node_id="6", field="negative_conditioning"),
-                ),
-                Edge(
-                    source=EdgeConnection(node_id="7", field="image"),
-                    destination=EdgeConnection(node_id="8", field="image"),
-                ),
-            ],
-        ),
+        graph=graph,
         exposed_inputs=[
             ExposedNodeInput(node_path="4", field="prompt", alias="positive_prompt"),
             ExposedNodeInput(node_path="5", field="prompt", alias="negative_prompt"),

invokeai/app/services/events.py

@@ -4,21 +4,28 @@ from typing import Any, Optional
 
 from invokeai.app.models.image import ProgressImage
 from invokeai.app.services.model_manager_service import BaseModelType, ModelInfo, ModelType, SubModelType
+from invokeai.app.services.session_queue.session_queue_common import (
+    BatchStatus,
+    EnqueueBatchResult,
+    SessionQueueItem,
+    SessionQueueStatus,
+)
 from invokeai.app.util.misc import get_timestamp
 
 
 class EventServiceBase:
-    session_event: str = "session_event"
+    queue_event: str = "queue_event"
 
     """Basic event bus, to have an empty stand-in when not needed"""
 
     def dispatch(self, event_name: str, payload: Any) -> None:
         pass
 
-    def __emit_session_event(self, event_name: str, payload: dict) -> None:
+    def __emit_queue_event(self, event_name: str, payload: dict) -> None:
+        """Queue events are emitted to a room with queue_id as the room name"""
         payload["timestamp"] = get_timestamp()
         self.dispatch(
-            event_name=EventServiceBase.session_event,
+            event_name=EventServiceBase.queue_event,
             payload=dict(event=event_name, data=payload),
         )
 
@@ -26,6 +33,9 @@ class EventServiceBase:
     # This will make them easier to integrate until we find a schema generator.
     def emit_generator_progress(
         self,
+        queue_id: str,
+        queue_item_id: int,
+        queue_batch_id: str,
         graph_execution_state_id: str,
         node: dict,
         source_node_id: str,
@@ -35,11 +45,14 @@ class EventServiceBase:
         total_steps: int,
     ) -> None:
         """Emitted when there is generation progress"""
-        self.__emit_session_event(
+        self.__emit_queue_event(
             event_name="generator_progress",
             payload=dict(
+                queue_id=queue_id,
+                queue_item_id=queue_item_id,
+                queue_batch_id=queue_batch_id,
                 graph_execution_state_id=graph_execution_state_id,
-                node=node,
+                node_id=node.get("id"),
                 source_node_id=source_node_id,
                 progress_image=progress_image.dict() if progress_image is not None else None,
                 step=step,
@@ -50,15 +63,21 @@ class EventServiceBase:
 
     def emit_invocation_complete(
         self,
+        queue_id: str,
+        queue_item_id: int,
+        queue_batch_id: str,
         graph_execution_state_id: str,
         result: dict,
         node: dict,
         source_node_id: str,
     ) -> None:
         """Emitted when an invocation has completed"""
-        self.__emit_session_event(
+        self.__emit_queue_event(
             event_name="invocation_complete",
             payload=dict(
+                queue_id=queue_id,
+                queue_item_id=queue_item_id,
+                queue_batch_id=queue_batch_id,
                 graph_execution_state_id=graph_execution_state_id,
                 node=node,
                 source_node_id=source_node_id,
@@ -68,6 +87,9 @@ class EventServiceBase:
 
     def emit_invocation_error(
         self,
+        queue_id: str,
+        queue_item_id: int,
+        queue_batch_id: str,
         graph_execution_state_id: str,
         node: dict,
         source_node_id: str,
@@ -75,9 +97,12 @@ class EventServiceBase:
         error: str,
     ) -> None:
         """Emitted when an invocation has completed"""
-        self.__emit_session_event(
+        self.__emit_queue_event(
             event_name="invocation_error",
             payload=dict(
+                queue_id=queue_id,
+                queue_item_id=queue_item_id,
+                queue_batch_id=queue_batch_id,
                 graph_execution_state_id=graph_execution_state_id,
                 node=node,
                 source_node_id=source_node_id,
@@ -86,28 +111,47 @@ class EventServiceBase:
             ),
         )
 
-    def emit_invocation_started(self, graph_execution_state_id: str, node: dict, source_node_id: str) -> None:
+    def emit_invocation_started(
+        self,
+        queue_id: str,
+        queue_item_id: int,
+        queue_batch_id: str,
+        graph_execution_state_id: str,
+        node: dict,
+        source_node_id: str,
+    ) -> None:
         """Emitted when an invocation has started"""
-        self.__emit_session_event(
+        self.__emit_queue_event(
             event_name="invocation_started",
             payload=dict(
+                queue_id=queue_id,
+                queue_item_id=queue_item_id,
+                queue_batch_id=queue_batch_id,
                 graph_execution_state_id=graph_execution_state_id,
                 node=node,
                 source_node_id=source_node_id,
             ),
         )
 
-    def emit_graph_execution_complete(self, graph_execution_state_id: str) -> None:
+    def emit_graph_execution_complete(
+        self, queue_id: str, queue_item_id: int, queue_batch_id: str, graph_execution_state_id: str
+    ) -> None:
         """Emitted when a session has completed all invocations"""
-        self.__emit_session_event(
+        self.__emit_queue_event(
             event_name="graph_execution_state_complete",
             payload=dict(
+                queue_id=queue_id,
+                queue_item_id=queue_item_id,
+                queue_batch_id=queue_batch_id,
                 graph_execution_state_id=graph_execution_state_id,
             ),
         )
 
     def emit_model_load_started(
         self,
+        queue_id: str,
+        queue_item_id: int,
+        queue_batch_id: str,
         graph_execution_state_id: str,
         model_name: str,
         base_model: BaseModelType,
@@ -115,9 +159,12 @@ class EventServiceBase:
         submodel: SubModelType,
     ) -> None:
         """Emitted when a model is requested"""
-        self.__emit_session_event(
+        self.__emit_queue_event(
             event_name="model_load_started",
             payload=dict(
+                queue_id=queue_id,
+                queue_item_id=queue_item_id,
+                queue_batch_id=queue_batch_id,
                 graph_execution_state_id=graph_execution_state_id,
                 model_name=model_name,
                 base_model=base_model,
@@ -128,6 +175,9 @@ class EventServiceBase:
 
     def emit_model_load_completed(
         self,
+        queue_id: str,
+        queue_item_id: int,
+        queue_batch_id: str,
         graph_execution_state_id: str,
         model_name: str,
         base_model: BaseModelType,
@@ -136,9 +186,12 @@ class EventServiceBase:
         model_info: ModelInfo,
     ) -> None:
         """Emitted when a model is correctly loaded (returns model info)"""
-        self.__emit_session_event(
+        self.__emit_queue_event(
             event_name="model_load_completed",
             payload=dict(
+                queue_id=queue_id,
+                queue_item_id=queue_item_id,
+                queue_batch_id=queue_batch_id,
                 graph_execution_state_id=graph_execution_state_id,
                 model_name=model_name,
                 base_model=base_model,
@@ -152,14 +205,20 @@ class EventServiceBase:
 
     def emit_session_retrieval_error(
         self,
+        queue_id: str,
+        queue_item_id: int,
+        queue_batch_id: str,
         graph_execution_state_id: str,
         error_type: str,
         error: str,
     ) -> None:
         """Emitted when session retrieval fails"""
-        self.__emit_session_event(
+        self.__emit_queue_event(
             event_name="session_retrieval_error",
             payload=dict(
+                queue_id=queue_id,
+                queue_item_id=queue_item_id,
+                queue_batch_id=queue_batch_id,
                 graph_execution_state_id=graph_execution_state_id,
                 error_type=error_type,
                 error=error,
@@ -168,18 +227,88 @@ class EventServiceBase:
 
     def emit_invocation_retrieval_error(
         self,
+        queue_id: str,
+        queue_item_id: int,
+        queue_batch_id: str,
         graph_execution_state_id: str,
         node_id: str,
         error_type: str,
         error: str,
     ) -> None:
         """Emitted when invocation retrieval fails"""
-        self.__emit_session_event(
+        self.__emit_queue_event(
             event_name="invocation_retrieval_error",
             payload=dict(
+                queue_id=queue_id,
+                queue_item_id=queue_item_id,
+                queue_batch_id=queue_batch_id,
                 graph_execution_state_id=graph_execution_state_id,
                 node_id=node_id,
                 error_type=error_type,
                 error=error,
             ),
         )
+
+    def emit_session_canceled(
+        self,
+        queue_id: str,
+        queue_item_id: int,
+        queue_batch_id: str,
+        graph_execution_state_id: str,
+    ) -> None:
+        """Emitted when a session is canceled"""
+        self.__emit_queue_event(
+            event_name="session_canceled",
+            payload=dict(
+                queue_id=queue_id,
+                queue_item_id=queue_item_id,
+                queue_batch_id=queue_batch_id,
+                graph_execution_state_id=graph_execution_state_id,
+            ),
+        )
+
+    def emit_queue_item_status_changed(
+        self,
+        session_queue_item: SessionQueueItem,
+        batch_status: BatchStatus,
+        queue_status: SessionQueueStatus,
+    ) -> None:
+        """Emitted when a queue item's status changes"""
+        self.__emit_queue_event(
+            event_name="queue_item_status_changed",
+            payload=dict(
+                queue_id=queue_status.queue_id,
+                queue_item=dict(
+                    queue_id=session_queue_item.queue_id,
+                    item_id=session_queue_item.item_id,
+                    status=session_queue_item.status,
+                    batch_id=session_queue_item.batch_id,
+                    session_id=session_queue_item.session_id,
+                    error=session_queue_item.error,
+                    created_at=str(session_queue_item.created_at) if session_queue_item.created_at else None,
+                    updated_at=str(session_queue_item.updated_at) if session_queue_item.updated_at else None,
+                    started_at=str(session_queue_item.started_at) if session_queue_item.started_at else None,
+                    completed_at=str(session_queue_item.completed_at) if session_queue_item.completed_at else None,
+                ),
+                batch_status=batch_status.dict(),
+                queue_status=queue_status.dict(),
+            ),
+        )
+
+    def emit_batch_enqueued(self, enqueue_result: EnqueueBatchResult) -> None:
+        """Emitted when a batch is enqueued"""
+        self.__emit_queue_event(
+            event_name="batch_enqueued",
+            payload=dict(
+                queue_id=enqueue_result.queue_id,
+                batch_id=enqueue_result.batch.batch_id,
+                enqueued=enqueue_result.enqueued,
+            ),
+        )
+
+    def emit_queue_cleared(self, queue_id: str) -> None:
+        """Emitted when the queue is cleared"""
+        self.__emit_queue_event(
+            event_name="queue_cleared",
+            payload=dict(queue_id=queue_id),
+        )

invokeai/app/services/graph.py

@@ -2,13 +2,14 @@
 
 import copy
 import itertools
-import uuid
 from typing import Annotated, Any, Optional, Union, get_args, get_origin, get_type_hints
 
 import networkx as nx
 from pydantic import BaseModel, root_validator, validator
 from pydantic.fields import Field
 
+from invokeai.app.util.misc import uuid_string
+
 # Importing * is bad karma but needed here for node detection
 from ..invocations import *  # noqa: F401 F403
 from ..invocations.baseinvocation import (
@@ -116,6 +117,10 @@ def are_connection_types_compatible(from_type: Any, to_type: Any) -> bool:
         if from_type is int and to_type is float:
             return True
 
+        # allow int|float -> str, pydantic will cast for us
+        if (from_type is int or from_type is float) and to_type is str:
+            return True
+
         # if not issubclass(from_type, to_type):
         if not is_union_subtype(from_type, to_type):
             return False
@@ -137,19 +142,43 @@ def are_connections_compatible(
     return are_connection_types_compatible(from_node_field, to_node_field)
 
 
-class NodeAlreadyInGraphError(Exception):
+class NodeAlreadyInGraphError(ValueError):
     pass
 
 
-class InvalidEdgeError(Exception):
+class InvalidEdgeError(ValueError):
     pass
 
 
-class NodeNotFoundError(Exception):
+class NodeNotFoundError(ValueError):
     pass
 
 
-class NodeAlreadyExecutedError(Exception):
+class NodeAlreadyExecutedError(ValueError):
+    pass
+
+
+class DuplicateNodeIdError(ValueError):
+    pass
+
+
+class NodeFieldNotFoundError(ValueError):
+    pass
+
+
+class NodeIdMismatchError(ValueError):
+    pass
+
+
+class InvalidSubGraphError(ValueError):
+    pass
+
+
+class CyclicalGraphError(ValueError):
+    pass
+
+
+class UnknownGraphValidationError(ValueError):
     pass
 
 
@@ -227,7 +256,7 @@ InvocationOutputsUnion = Union[BaseInvocationOutput.get_all_subclasses_tuple()]
 
 
 class Graph(BaseModel):
-    id: str = Field(description="The id of this graph", default_factory=lambda: uuid.uuid4().__str__())
+    id: str = Field(description="The id of this graph", default_factory=uuid_string)
     # TODO: use a list (and never use dict in a BaseModel) because pydantic/fastapi hates me
     nodes: dict[str, Annotated[InvocationsUnion, Field(discriminator="type")]] = Field(
         description="The nodes in this graph", default_factory=dict
@@ -307,53 +336,108 @@ class Graph(BaseModel):
         except KeyError:
             pass
 
-    def is_valid(self) -> bool:
-        """Validates the graph."""
+    def validate_self(self) -> None:
+        """
+        Validates the graph.
+
+        Raises an exception if the graph is invalid:
+        - `DuplicateNodeIdError`
+        - `NodeIdMismatchError`
+        - `InvalidSubGraphError`
+        - `NodeNotFoundError`
+        - `NodeFieldNotFoundError`
+        - `CyclicalGraphError`
+        - `InvalidEdgeError`
+        """
+
+        # Validate that all node ids are unique
+        node_ids = [n.id for n in self.nodes.values()]
+        duplicate_node_ids = set([node_id for node_id in node_ids if node_ids.count(node_id) >= 2])
+        if duplicate_node_ids:
+            raise DuplicateNodeIdError(f"Node ids must be unique, found duplicates {duplicate_node_ids}")
+
+        # Validate that all node ids match the keys in the nodes dict
+        for k, v in self.nodes.items():
+            if k != v.id:
+                raise NodeIdMismatchError(f"Node ids must match, got {k} and {v.id}")
 
         # Validate all subgraphs
         for gn in (n for n in self.nodes.values() if isinstance(n, GraphInvocation)):
-            if not gn.graph.is_valid():
-                return False
+            try:
+                gn.graph.validate_self()
+            except Exception as e:
+                raise InvalidSubGraphError(f"Subgraph {gn.id} is invalid") from e
 
-        # Validate all edges reference nodes in the graph
-        node_ids = set([e.source.node_id for e in self.edges] + [e.destination.node_id for e in self.edges])
-        if not all((self.has_node(node_id) for node_id in node_ids)):
-            return False
+        # Validate that all edges match nodes and fields in the graph
+        for edge in self.edges:
+            source_node = self.nodes.get(edge.source.node_id, None)
+            if source_node is None:
+                raise NodeNotFoundError(f"Edge source node {edge.source.node_id} does not exist in the graph")
+
+            destination_node = self.nodes.get(edge.destination.node_id, None)
+            if destination_node is None:
+                raise NodeNotFoundError(f"Edge destination node {edge.destination.node_id} does not exist in the graph")
+
+            # output fields are not on the node object directly, they are on the output type
+            if edge.source.field not in source_node.get_output_type().__fields__:
+                raise NodeFieldNotFoundError(
+                    f"Edge source field {edge.source.field} does not exist in node {edge.source.node_id}"
+                )
+
+            # input fields are on the node
+            if edge.destination.field not in destination_node.__fields__:
+                raise NodeFieldNotFoundError(
+                    f"Edge destination field {edge.destination.field} does not exist in node {edge.destination.node_id}"
+                )
 
         # Validate there are no cycles
         g = self.nx_graph_flat()
         if not nx.is_directed_acyclic_graph(g):
-            return False
+            raise CyclicalGraphError("Graph contains cycles")
 
         # Validate all edge connections are valid
-        if not all(
-            (
-                are_connections_compatible(
-                    self.get_node(e.source.node_id),
-                    e.source.field,
-                    self.get_node(e.destination.node_id),
-                    e.destination.field,
+        for e in self.edges:
+            if not are_connections_compatible(
+                self.get_node(e.source.node_id),
+                e.source.field,
+                self.get_node(e.destination.node_id),
+                e.destination.field,
+            ):
+                raise InvalidEdgeError(
+                    f"Invalid edge from {e.source.node_id}.{e.source.field} to {e.destination.node_id}.{e.destination.field}"
                 )
-                for e in self.edges
-            )
+
+        # Validate all iterators & collectors
+        # TODO: may need to validate all iterators & collectors in subgraphs so edge connections in parent graphs will be available
+        for n in self.nodes.values():
+            if isinstance(n, IterateInvocation) and not self._is_iterator_connection_valid(n.id):
+                raise InvalidEdgeError(f"Invalid iterator node {n.id}")
+            if isinstance(n, CollectInvocation) and not self._is_collector_connection_valid(n.id):
+                raise InvalidEdgeError(f"Invalid collector node {n.id}")
+
+        return None
+
+    def is_valid(self) -> bool:
+        """
+        Checks if the graph is valid.
+
+        Raises `UnknownGraphValidationError` if there is a problem validating the graph (not a validation error).
+        """
+        try:
+            self.validate_self()
+            return True
+        except (
+            DuplicateNodeIdError,
+            NodeIdMismatchError,
+            InvalidSubGraphError,
+            NodeNotFoundError,
+            NodeFieldNotFoundError,
+            CyclicalGraphError,
+            InvalidEdgeError,
         ):
             return False
-
-        # Validate all iterators
-        # TODO: may need to validate all iterators in subgraphs so edge connections in parent graphs will be available
-        if not all(
-            (self._is_iterator_connection_valid(n.id) for n in self.nodes.values() if isinstance(n, IterateInvocation))
-        ):
-            return False
-
-        # Validate all collectors
-        # TODO: may need to validate all collectors in subgraphs so edge connections in parent graphs will be available
-        if not all(
-            (self._is_collector_connection_valid(n.id) for n in self.nodes.values() if isinstance(n, CollectInvocation))
-        ):
-            return False
-
-        return True
+        except Exception as e:
+            raise UnknownGraphValidationError(f"Problem validating graph {e}") from e
 
     def _validate_edge(self, edge: Edge):
         """Validates that a new edge doesn't create a cycle in the graph"""
@@ -697,8 +781,7 @@ class Graph(BaseModel):
 class GraphExecutionState(BaseModel):
     """Tracks the state of a graph execution"""
 
-    id: str = Field(description="The id of the execution state", default_factory=lambda: uuid.uuid4().__str__())
-
+    id: str = Field(description="The id of the execution state", default_factory=uuid_string)
     # TODO: Store a reference to the graph instead of the actual graph?
     graph: Graph = Field(description="The graph being executed")
 
@@ -735,6 +818,12 @@ class GraphExecutionState(BaseModel):
         default_factory=dict,
     )
 
+    @validator("graph")
+    def graph_is_valid(cls, v: Graph):
+        """Validates that the graph is valid"""
+        v.validate_self()
+        return v
+
     class Config:
         schema_extra = {
             "required": [
@@ -847,7 +936,7 @@ class GraphExecutionState(BaseModel):
             new_node = copy.deepcopy(node)
 
             # Create the node id (use a random uuid)
-            new_node.id = str(uuid.uuid4())
+            new_node.id = uuid_string()
 
             # Set the iteration index for iteration invocations
             if isinstance(new_node, IterateInvocation):
@@ -1082,7 +1171,7 @@ class ExposedNodeOutput(BaseModel):
 
 
 class LibraryGraph(BaseModel):
-    id: str = Field(description="The unique identifier for this library graph", default_factory=uuid.uuid4)
+    id: str = Field(description="The unique identifier for this library graph", default_factory=uuid_string)
     graph: Graph = Field(description="The graph")
     name: str = Field(description="The name of the graph")
     description: str = Field(description="The description of the graph")

invokeai/app/services/image_file_storage.py

@@ -9,6 +9,7 @@ from PIL import Image, PngImagePlugin
 from PIL.Image import Image as PILImageType
 from send2trash import send2trash
 
+from invokeai.app.services.config.invokeai_config import InvokeAIAppConfig
 from invokeai.app.util.thumbnails import get_thumbnail_name, make_thumbnail
 
 
@@ -79,6 +80,7 @@ class DiskImageFileStorage(ImageFileStorageBase):
     __cache_ids: Queue  # TODO: this is an incredibly naive cache
     __cache: Dict[Path, PILImageType]
     __max_cache_size: int
+    __compress_level: int
 
     def __init__(self, output_folder: Union[str, Path]):
         self.__cache = dict()
@@ -87,7 +89,7 @@ class DiskImageFileStorage(ImageFileStorageBase):
 
         self.__output_folder: Path = output_folder if isinstance(output_folder, Path) else Path(output_folder)
         self.__thumbnails_folder = self.__output_folder / "thumbnails"
-
+        self.__compress_level = InvokeAIAppConfig.get_config().png_compress_level
         # Validate required output folders at launch
         self.__validate_storage_folders()
 
@@ -134,7 +136,7 @@ class DiskImageFileStorage(ImageFileStorageBase):
                 if original_workflow is not None:
                     pnginfo.add_text("invokeai_workflow", original_workflow)
 
-            image.save(image_path, "PNG", pnginfo=pnginfo)
+            image.save(image_path, "PNG", pnginfo=pnginfo, compress_level=self.__compress_level)
 
             thumbnail_name = get_thumbnail_name(image_name)
             thumbnail_path = self.get_path(thumbnail_name, thumbnail=True)

invokeai/app/services/image_record_storage.py

@@ -148,24 +148,20 @@ class ImageRecordStorageBase(ABC):
 
 
 class SqliteImageRecordStorage(ImageRecordStorageBase):
-    _filename: str
     _conn: sqlite3.Connection
     _cursor: sqlite3.Cursor
-    _lock: threading.Lock
+    _lock: threading.RLock
 
-    def __init__(self, filename: str) -> None:
+    def __init__(self, conn: sqlite3.Connection, lock: threading.RLock) -> None:
         super().__init__()
-        self._filename = filename
-        self._conn = sqlite3.connect(filename, check_same_thread=False)
+        self._conn = conn
         # Enable row factory to get rows as dictionaries (must be done before making the cursor!)
         self._conn.row_factory = sqlite3.Row
         self._cursor = self._conn.cursor()
-        self._lock = threading.Lock()
+        self._lock = lock
 
         try:
             self._lock.acquire()
-            # Enable foreign keys
-            self._conn.execute("PRAGMA foreign_keys = ON;")
             self._create_tables()
             self._conn.commit()
         finally:
@@ -588,7 +584,7 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
                 FROM images
                 JOIN board_images ON images.image_name = board_images.image_name
                 WHERE board_images.board_id = ?
-                ORDER BY images.created_at DESC
+                ORDER BY images.starred DESC, images.created_at DESC
                 LIMIT 1;
                 """,
                 (board_id,),

invokeai/app/services/images.py

@@ -1,6 +1,6 @@
 from abc import ABC, abstractmethod
 from logging import Logger
-from typing import TYPE_CHECKING, Optional
+from typing import TYPE_CHECKING, Callable, Optional
 
 from PIL.Image import Image as PILImageType
 
@@ -38,6 +38,29 @@ if TYPE_CHECKING:
 class ImageServiceABC(ABC):
     """High-level service for image management."""
 
+    _on_changed_callbacks: list[Callable[[ImageDTO], None]]
+    _on_deleted_callbacks: list[Callable[[str], None]]
+
+    def __init__(self) -> None:
+        self._on_changed_callbacks = list()
+        self._on_deleted_callbacks = list()
+
+    def on_changed(self, on_changed: Callable[[ImageDTO], None]) -> None:
+        """Register a callback for when an image is changed"""
+        self._on_changed_callbacks.append(on_changed)
+
+    def on_deleted(self, on_deleted: Callable[[str], None]) -> None:
+        """Register a callback for when an image is deleted"""
+        self._on_deleted_callbacks.append(on_deleted)
+
+    def _on_changed(self, item: ImageDTO) -> None:
+        for callback in self._on_changed_callbacks:
+            callback(item)
+
+    def _on_deleted(self, item_id: str) -> None:
+        for callback in self._on_deleted_callbacks:
+            callback(item_id)
+
     @abstractmethod
     def create(
         self,
@@ -161,6 +184,7 @@ class ImageService(ImageServiceABC):
     _services: ImageServiceDependencies
 
     def __init__(self, services: ImageServiceDependencies):
+        super().__init__()
         self._services = services
 
     def create(
@@ -217,6 +241,7 @@ class ImageService(ImageServiceABC):
             self._services.image_files.save(image_name=image_name, image=image, metadata=metadata, workflow=workflow)
             image_dto = self.get_dto(image_name)
 
+            self._on_changed(image_dto)
             return image_dto
         except ImageRecordSaveException:
             self._services.logger.error("Failed to save image record")
@@ -235,7 +260,9 @@ class ImageService(ImageServiceABC):
     ) -> ImageDTO:
         try:
             self._services.image_records.update(image_name, changes)
-            return self.get_dto(image_name)
+            image_dto = self.get_dto(image_name)
+            self._on_changed(image_dto)
+            return image_dto
         except ImageRecordSaveException:
             self._services.logger.error("Failed to update image record")
             raise
@@ -374,6 +401,7 @@ class ImageService(ImageServiceABC):
         try:
             self._services.image_files.delete(image_name)
             self._services.image_records.delete(image_name)
+            self._on_deleted(image_name)
         except ImageRecordDeleteException:
             self._services.logger.error("Failed to delete image record")
             raise
@@ -390,6 +418,8 @@ class ImageService(ImageServiceABC):
             for image_name in image_names:
                 self._services.image_files.delete(image_name)
             self._services.image_records.delete_many(image_names)
+            for image_name in image_names:
+                self._on_deleted(image_name)
         except ImageRecordDeleteException:
             self._services.logger.error("Failed to delete image records")
             raise
@@ -406,6 +436,7 @@ class ImageService(ImageServiceABC):
             count = len(image_names)
             for image_name in image_names:
                 self._services.image_files.delete(image_name)
+                self._on_deleted(image_name)
             return count
         except ImageRecordDeleteException:
             self._services.logger.error("Failed to delete image records")

invokeai/app/services/invocation_cache/invocation_cache_base.py

@@ -0,0 +1,62 @@
+from abc import ABC, abstractmethod
+from typing import Optional, Union
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput
+from invokeai.app.services.invocation_cache.invocation_cache_common import InvocationCacheStatus
+
+
+class InvocationCacheBase(ABC):
+    """
+    Base class for invocation caches.
+    When an invocation is executed, it is hashed and its output stored in the cache.
+    When new invocations are executed, if they are flagged with `use_cache`, they
+    will attempt to pull their value from the cache before executing.
+
+    Implementations should register for the `on_deleted` event of the `images` and `latents`
+    services, and delete any cached outputs that reference the deleted image or latent.
+
+    See the memory implementation for an example.
+
+    Implementations should respect the `node_cache_size` configuration value, and skip all
+    cache logic if the value is set to 0.
+    """
+
+    @abstractmethod
+    def get(self, key: Union[int, str]) -> Optional[BaseInvocationOutput]:
+        """Retrieves an invocation output from the cache"""
+        pass
+
+    @abstractmethod
+    def save(self, key: Union[int, str], invocation_output: BaseInvocationOutput) -> None:
+        """Stores an invocation output in the cache"""
+        pass
+
+    @abstractmethod
+    def delete(self, key: Union[int, str]) -> None:
+        """Deletes an invocation output from the cache"""
+        pass
+
+    @abstractmethod
+    def clear(self) -> None:
+        """Clears the cache"""
+        pass
+
+    @abstractmethod
+    def create_key(self, invocation: BaseInvocation) -> int:
+        """Gets the key for the invocation's cache item"""
+        pass
+
+    @abstractmethod
+    def disable(self) -> None:
+        """Disables the cache, overriding the max cache size"""
+        pass
+
+    @abstractmethod
+    def enable(self) -> None:
+        """Enables the cache, letting the the max cache size take effect"""
+        pass
+
+    @abstractmethod
+    def get_status(self) -> InvocationCacheStatus:
+        """Returns the status of the cache"""
+        pass

invokeai/app/services/invocation_cache/invocation_cache_common.py

@@ -0,0 +1,9 @@
+from pydantic import BaseModel, Field
+
+
+class InvocationCacheStatus(BaseModel):
+    size: int = Field(description="The current size of the invocation cache")
+    hits: int = Field(description="The number of cache hits")
+    misses: int = Field(description="The number of cache misses")
+    enabled: bool = Field(description="Whether the invocation cache is enabled")
+    max_size: int = Field(description="The maximum size of the invocation cache")

invokeai/app/services/invocation_cache/invocation_cache_memory.py

@@ -0,0 +1,126 @@
+from collections import OrderedDict
+from dataclasses import dataclass, field
+from threading import Lock
+from typing import Optional, Union
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput
+from invokeai.app.services.invocation_cache.invocation_cache_base import InvocationCacheBase
+from invokeai.app.services.invocation_cache.invocation_cache_common import InvocationCacheStatus
+from invokeai.app.services.invoker import Invoker
+
+
+@dataclass(order=True)
+class CachedItem:
+    invocation_output: BaseInvocationOutput = field(compare=False)
+    invocation_output_json: str = field(compare=False)
+
+
+class MemoryInvocationCache(InvocationCacheBase):
+    _cache: OrderedDict[Union[int, str], CachedItem]
+    _max_cache_size: int
+    _disabled: bool
+    _hits: int
+    _misses: int
+    _invoker: Invoker
+    _lock: Lock
+
+    def __init__(self, max_cache_size: int = 0) -> None:
+        self._cache = OrderedDict()
+        self._max_cache_size = max_cache_size
+        self._disabled = False
+        self._hits = 0
+        self._misses = 0
+        self._lock = Lock()
+
+    def start(self, invoker: Invoker) -> None:
+        self._invoker = invoker
+        if self._max_cache_size == 0:
+            return
+        self._invoker.services.images.on_deleted(self._delete_by_match)
+        self._invoker.services.latents.on_deleted(self._delete_by_match)
+
+    def get(self, key: Union[int, str]) -> Optional[BaseInvocationOutput]:
+        with self._lock:
+            if self._max_cache_size == 0 or self._disabled:
+                return None
+            item = self._cache.get(key, None)
+            if item is not None:
+                self._hits += 1
+                self._cache.move_to_end(key)
+                return item.invocation_output
+            self._misses += 1
+            return None
+
+    def save(self, key: Union[int, str], invocation_output: BaseInvocationOutput) -> None:
+        with self._lock:
+            if self._max_cache_size == 0 or self._disabled or key in self._cache:
+                return
+            # If the cache is full, we need to remove the least used
+            number_to_delete = len(self._cache) + 1 - self._max_cache_size
+            self._delete_oldest_access(number_to_delete)
+            self._cache[key] = CachedItem(invocation_output, invocation_output.json())
+
+    def _delete_oldest_access(self, number_to_delete: int) -> None:
+        number_to_delete = min(number_to_delete, len(self._cache))
+        for _ in range(number_to_delete):
+            self._cache.popitem(last=False)
+
+    def _delete(self, key: Union[int, str]) -> None:
+        if self._max_cache_size == 0:
+            return
+        if key in self._cache:
+            del self._cache[key]
+
+    def delete(self, key: Union[int, str]) -> None:
+        with self._lock:
+            return self._delete(key)
+
+    def clear(self, *args, **kwargs) -> None:
+        with self._lock:
+            if self._max_cache_size == 0:
+                return
+            self._cache.clear()
+            self._misses = 0
+            self._hits = 0
+
+    @staticmethod
+    def create_key(invocation: BaseInvocation) -> int:
+        return hash(invocation.json(exclude={"id"}))
+
+    def disable(self) -> None:
+        with self._lock:
+            if self._max_cache_size == 0:
+                return
+            self._disabled = True
+
+    def enable(self) -> None:
+        with self._lock:
+            if self._max_cache_size == 0:
+                return
+            self._disabled = False
+
+    def get_status(self) -> InvocationCacheStatus:
+        with self._lock:
+            return InvocationCacheStatus(
+                hits=self._hits,
+                misses=self._misses,
+                enabled=not self._disabled and self._max_cache_size > 0,
+                size=len(self._cache),
+                max_size=self._max_cache_size,
+            )
+
+    def _delete_by_match(self, to_match: str) -> None:
+        with self._lock:
+            if self._max_cache_size == 0:
+                return
+            keys_to_delete = set()
+            for key, cached_item in self._cache.items():
+                if to_match in cached_item.invocation_output_json:
+                    keys_to_delete.add(key)
+            if not keys_to_delete:
+                return
+            for key in keys_to_delete:
+                self._delete(key)
+            self._invoker.services.logger.debug(
+                f"Deleted {len(keys_to_delete)} cached invocation outputs for {to_match}"
+            )

invokeai/app/services/invocation_queue.py

@@ -11,6 +11,13 @@ from pydantic import BaseModel, Field
 class InvocationQueueItem(BaseModel):
     graph_execution_state_id: str = Field(description="The ID of the graph execution state")
     invocation_id: str = Field(description="The ID of the node being invoked")
+    session_queue_id: str = Field(description="The ID of the session queue from which this invocation queue item came")
+    session_queue_item_id: int = Field(
+        description="The ID of session queue item from which this invocation queue item came"
+    )
+    session_queue_batch_id: str = Field(
+        description="The ID of the session batch from which this invocation queue item came"
+    )
     invoke_all: bool = Field(default=False)
     timestamp: float = Field(default_factory=time.time)
 

invokeai/app/services/invocation_services.py

@@ -12,12 +12,15 @@ if TYPE_CHECKING:
     from invokeai.app.services.events import EventServiceBase
     from invokeai.app.services.graph import GraphExecutionState, LibraryGraph
     from invokeai.app.services.images import ImageServiceABC
+    from invokeai.app.services.invocation_cache.invocation_cache_base import InvocationCacheBase
     from invokeai.app.services.invocation_queue import InvocationQueueABC
     from invokeai.app.services.invocation_stats import InvocationStatsServiceBase
     from invokeai.app.services.invoker import InvocationProcessorABC
     from invokeai.app.services.item_storage import ItemStorageABC
     from invokeai.app.services.latent_storage import LatentsStorageBase
     from invokeai.app.services.model_manager_service import ModelManagerServiceBase
+    from invokeai.app.services.session_processor.session_processor_base import SessionProcessorBase
+    from invokeai.app.services.session_queue.session_queue_base import SessionQueueBase
 
 
 class InvocationServices:
@@ -28,8 +31,8 @@ class InvocationServices:
     boards: "BoardServiceABC"
     configuration: "InvokeAIAppConfig"
     events: "EventServiceBase"
-    graph_execution_manager: "ItemStorageABC"["GraphExecutionState"]
-    graph_library: "ItemStorageABC"["LibraryGraph"]
+    graph_execution_manager: "ItemStorageABC[GraphExecutionState]"
+    graph_library: "ItemStorageABC[LibraryGraph]"
     images: "ImageServiceABC"
     latents: "LatentsStorageBase"
     logger: "Logger"
@@ -37,6 +40,9 @@ class InvocationServices:
     processor: "InvocationProcessorABC"
     performance_statistics: "InvocationStatsServiceBase"
     queue: "InvocationQueueABC"
+    session_queue: "SessionQueueBase"
+    session_processor: "SessionProcessorBase"
+    invocation_cache: "InvocationCacheBase"
 
     def __init__(
         self,
@@ -44,8 +50,8 @@ class InvocationServices:
         boards: "BoardServiceABC",
         configuration: "InvokeAIAppConfig",
         events: "EventServiceBase",
-        graph_execution_manager: "ItemStorageABC"["GraphExecutionState"],
-        graph_library: "ItemStorageABC"["LibraryGraph"],
+        graph_execution_manager: "ItemStorageABC[GraphExecutionState]",
+        graph_library: "ItemStorageABC[LibraryGraph]",
         images: "ImageServiceABC",
         latents: "LatentsStorageBase",
         logger: "Logger",
@@ -53,10 +59,12 @@ class InvocationServices:
         processor: "InvocationProcessorABC",
         performance_statistics: "InvocationStatsServiceBase",
         queue: "InvocationQueueABC",
+        session_queue: "SessionQueueBase",
+        session_processor: "SessionProcessorBase",
+        invocation_cache: "InvocationCacheBase",
     ):
         self.board_images = board_images
         self.boards = boards
-        self.boards = boards
         self.configuration = configuration
         self.events = events
         self.graph_execution_manager = graph_execution_manager
@@ -68,3 +76,6 @@ class InvocationServices:
         self.processor = processor
         self.performance_statistics = performance_statistics
         self.queue = queue
+        self.session_queue = session_queue
+        self.session_processor = session_processor
+        self.invocation_cache = invocation_cache

invokeai/app/services/invoker.py

@@ -17,7 +17,14 @@ class Invoker:
         self.services = services
         self._start()
 
-    def invoke(self, graph_execution_state: GraphExecutionState, invoke_all: bool = False) -> Optional[str]:
+    def invoke(
+        self,
+        session_queue_id: str,
+        session_queue_item_id: int,
+        session_queue_batch_id: str,
+        graph_execution_state: GraphExecutionState,
+        invoke_all: bool = False,
+    ) -> Optional[str]:
         """Determines the next node to invoke and enqueues it, preparing if needed.
         Returns the id of the queued node, or `None` if there are no nodes left to enqueue."""
 
@@ -32,7 +39,9 @@ class Invoker:
         # Queue the invocation
         self.services.queue.put(
             InvocationQueueItem(
-                # session_id    = session.id,
+                session_queue_id=session_queue_id,
+                session_queue_item_id=session_queue_item_id,
+                session_queue_batch_id=session_queue_batch_id,
                 graph_execution_state_id=graph_execution_state.id,
                 invocation_id=invocation.id,
                 invoke_all=invoke_all,

invokeai/app/services/latent_storage.py

@@ -3,7 +3,7 @@
 from abc import ABC, abstractmethod
 from pathlib import Path
 from queue import Queue
-from typing import Dict, Optional, Union
+from typing import Callable, Dict, Optional, Union
 
 import torch
 
@@ -11,6 +11,13 @@ import torch
 class LatentsStorageBase(ABC):
     """Responsible for storing and retrieving latents."""
 
+    _on_changed_callbacks: list[Callable[[torch.Tensor], None]]
+    _on_deleted_callbacks: list[Callable[[str], None]]
+
+    def __init__(self) -> None:
+        self._on_changed_callbacks = list()
+        self._on_deleted_callbacks = list()
+
     @abstractmethod
     def get(self, name: str) -> torch.Tensor:
         pass
@@ -23,6 +30,22 @@ class LatentsStorageBase(ABC):
     def delete(self, name: str) -> None:
         pass
 
+    def on_changed(self, on_changed: Callable[[torch.Tensor], None]) -> None:
+        """Register a callback for when an item is changed"""
+        self._on_changed_callbacks.append(on_changed)
+
+    def on_deleted(self, on_deleted: Callable[[str], None]) -> None:
+        """Register a callback for when an item is deleted"""
+        self._on_deleted_callbacks.append(on_deleted)
+
+    def _on_changed(self, item: torch.Tensor) -> None:
+        for callback in self._on_changed_callbacks:
+            callback(item)
+
+    def _on_deleted(self, item_id: str) -> None:
+        for callback in self._on_deleted_callbacks:
+            callback(item_id)
+
 
 class ForwardCacheLatentsStorage(LatentsStorageBase):
     """Caches the latest N latents in memory, writing-thorugh to and reading from underlying storage"""
@@ -33,6 +56,7 @@ class ForwardCacheLatentsStorage(LatentsStorageBase):
     __underlying_storage: LatentsStorageBase
 
     def __init__(self, underlying_storage: LatentsStorageBase, max_cache_size: int = 20):
+        super().__init__()
         self.__underlying_storage = underlying_storage
         self.__cache = dict()
         self.__cache_ids = Queue()
@@ -50,11 +74,13 @@ class ForwardCacheLatentsStorage(LatentsStorageBase):
     def save(self, name: str, data: torch.Tensor) -> None:
         self.__underlying_storage.save(name, data)
         self.__set_cache(name, data)
+        self._on_changed(data)
 
     def delete(self, name: str) -> None:
         self.__underlying_storage.delete(name)
         if name in self.__cache:
             del self.__cache[name]
+        self._on_deleted(name)
 
     def __get_cache(self, name: str) -> Optional[torch.Tensor]:
         return None if name not in self.__cache else self.__cache[name]

invokeai/app/services/model_manager_service.py

@@ -525,7 +525,7 @@ class ModelManagerService(ModelManagerServiceBase):
 
     def _emit_load_event(
         self,
-        context,
+        context: InvocationContext,
         model_name: str,
         base_model: BaseModelType,
         model_type: ModelType,
@@ -537,6 +537,9 @@ class ModelManagerService(ModelManagerServiceBase):
 
         if model_info:
             context.services.events.emit_model_load_completed(
+                queue_id=context.queue_id,
+                queue_item_id=context.queue_item_id,
+                queue_batch_id=context.queue_batch_id,
                 graph_execution_state_id=context.graph_execution_state_id,
                 model_name=model_name,
                 base_model=base_model,
@@ -546,6 +549,9 @@ class ModelManagerService(ModelManagerServiceBase):
             )
         else:
             context.services.events.emit_model_load_started(
+                queue_id=context.queue_id,
+                queue_item_id=context.queue_item_id,
+                queue_batch_id=context.queue_batch_id,
                 graph_execution_state_id=context.graph_execution_state_id,
                 model_name=model_name,
                 base_model=base_model,

invokeai/app/services/processor.py

@@ -1,6 +1,7 @@
 import time
 import traceback
 from threading import BoundedSemaphore, Event, Thread
+from typing import Optional
 
 import invokeai.backend.util.logging as logger
 
@@ -37,10 +38,11 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
         try:
             self.__threadLimit.acquire()
             statistics: InvocationStatsServiceBase = self.__invoker.services.performance_statistics
+            queue_item: Optional[InvocationQueueItem] = None
 
             while not stop_event.is_set():
                 try:
-                    queue_item: InvocationQueueItem = self.__invoker.services.queue.get()
+                    queue_item = self.__invoker.services.queue.get()
                 except Exception as e:
                     self.__invoker.services.logger.error("Exception while getting from queue:\n%s" % e)
 
@@ -48,7 +50,6 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                     # do not hammer the queue
                     time.sleep(0.5)
                     continue
-
                 try:
                     graph_execution_state = self.__invoker.services.graph_execution_manager.get(
                         queue_item.graph_execution_state_id
@@ -56,6 +57,9 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                 except Exception as e:
                     self.__invoker.services.logger.error("Exception while retrieving session:\n%s" % e)
                     self.__invoker.services.events.emit_session_retrieval_error(
+                        queue_batch_id=queue_item.session_queue_batch_id,
+                        queue_item_id=queue_item.session_queue_item_id,
+                        queue_id=queue_item.session_queue_id,
                         graph_execution_state_id=queue_item.graph_execution_state_id,
                         error_type=e.__class__.__name__,
                         error=traceback.format_exc(),
@@ -67,6 +71,9 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                 except Exception as e:
                     self.__invoker.services.logger.error("Exception while retrieving invocation:\n%s" % e)
                     self.__invoker.services.events.emit_invocation_retrieval_error(
+                        queue_batch_id=queue_item.session_queue_batch_id,
+                        queue_item_id=queue_item.session_queue_item_id,
+                        queue_id=queue_item.session_queue_id,
                         graph_execution_state_id=queue_item.graph_execution_state_id,
                         node_id=queue_item.invocation_id,
                         error_type=e.__class__.__name__,
@@ -79,6 +86,9 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
 
                 # Send starting event
                 self.__invoker.services.events.emit_invocation_started(
+                    queue_batch_id=queue_item.session_queue_batch_id,
+                    queue_item_id=queue_item.session_queue_item_id,
+                    queue_id=queue_item.session_queue_id,
                     graph_execution_state_id=graph_execution_state.id,
                     node=invocation.dict(),
                     source_node_id=source_node_id,
@@ -89,13 +99,17 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                     graph_id = graph_execution_state.id
                     model_manager = self.__invoker.services.model_manager
                     with statistics.collect_stats(invocation, graph_id, model_manager):
-                        # use the internal invoke_internal(), which wraps the node's invoke() method in
-                        # this accomodates nodes which require a value, but get it only from a
-                        # connection
+                        # use the internal invoke_internal(), which wraps the node's invoke() method,
+                        # which handles a few things:
+                        # - nodes that require a value, but get it only from a connection
+                        # - referencing the invocation cache instead of executing the node
                         outputs = invocation.invoke_internal(
                             InvocationContext(
                                 services=self.__invoker.services,
                                 graph_execution_state_id=graph_execution_state.id,
+                                queue_item_id=queue_item.session_queue_item_id,
+                                queue_id=queue_item.session_queue_id,
+                                queue_batch_id=queue_item.session_queue_batch_id,
                             )
                         )
 
@@ -111,6 +125,9 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
 
                         # Send complete event
                         self.__invoker.services.events.emit_invocation_complete(
+                            queue_batch_id=queue_item.session_queue_batch_id,
+                            queue_item_id=queue_item.session_queue_item_id,
+                            queue_id=queue_item.session_queue_id,
                             graph_execution_state_id=graph_execution_state.id,
                             node=invocation.dict(),
                             source_node_id=source_node_id,
@@ -138,6 +155,9 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                     self.__invoker.services.logger.error("Error while invoking:\n%s" % e)
                     # Send error event
                     self.__invoker.services.events.emit_invocation_error(
+                        queue_batch_id=queue_item.session_queue_batch_id,
+                        queue_item_id=queue_item.session_queue_item_id,
+                        queue_id=queue_item.session_queue_id,
                         graph_execution_state_id=graph_execution_state.id,
                         node=invocation.dict(),
                         source_node_id=source_node_id,
@@ -155,10 +175,19 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                 is_complete = graph_execution_state.is_complete()
                 if queue_item.invoke_all and not is_complete:
                     try:
-                        self.__invoker.invoke(graph_execution_state, invoke_all=True)
+                        self.__invoker.invoke(
+                            session_queue_batch_id=queue_item.session_queue_batch_id,
+                            session_queue_item_id=queue_item.session_queue_item_id,
+                            session_queue_id=queue_item.session_queue_id,
+                            graph_execution_state=graph_execution_state,
+                            invoke_all=True,
+                        )
                     except Exception as e:
                         self.__invoker.services.logger.error("Error while invoking:\n%s" % e)
                         self.__invoker.services.events.emit_invocation_error(
+                            queue_batch_id=queue_item.session_queue_batch_id,
+                            queue_item_id=queue_item.session_queue_item_id,
+                            queue_id=queue_item.session_queue_id,
                             graph_execution_state_id=graph_execution_state.id,
                             node=invocation.dict(),
                             source_node_id=source_node_id,
@@ -166,7 +195,12 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                             error=traceback.format_exc(),
                         )
                 elif is_complete:
-                    self.__invoker.services.events.emit_graph_execution_complete(graph_execution_state.id)
+                    self.__invoker.services.events.emit_graph_execution_complete(
+                        queue_batch_id=queue_item.session_queue_batch_id,
+                        queue_item_id=queue_item.session_queue_item_id,
+                        queue_id=queue_item.session_queue_id,
+                        graph_execution_state_id=graph_execution_state.id,
+                    )
 
         except KeyboardInterrupt:
             pass  # Log something? KeyboardInterrupt is probably not going to be seen by the processor

invokeai/app/services/resource_name.py

@@ -1,7 +1,8 @@
-import uuid
 from abc import ABC, abstractmethod
 from enum import Enum, EnumMeta
 
+from invokeai.app.util.misc import uuid_string
+
 
 class ResourceType(str, Enum, metaclass=EnumMeta):
     """Enum for resource types."""
@@ -25,6 +26,6 @@ class SimpleNameService(NameServiceBase):
 
     # TODO: Add customizable naming schemes
     def create_image_name(self) -> str:
-        uuid_str = str(uuid.uuid4())
+        uuid_str = uuid_string()
         filename = f"{uuid_str}.png"
         return filename

invokeai/app/services/session_processor/session_processor_base.py

@@ -0,0 +1,28 @@
+from abc import ABC, abstractmethod
+
+from invokeai.app.services.session_processor.session_processor_common import SessionProcessorStatus
+
+
+class SessionProcessorBase(ABC):
+    """
+    Base class for session processor.
+
+    The session processor is responsible for executing sessions. It runs a simple polling loop,
+    checking the session queue for new sessions to execute. It must coordinate with the
+    invocation queue to ensure only one session is executing at a time.
+    """
+
+    @abstractmethod
+    def resume(self) -> SessionProcessorStatus:
+        """Starts or resumes the session processor"""
+        pass
+
+    @abstractmethod
+    def pause(self) -> SessionProcessorStatus:
+        """Pauses the session processor"""
+        pass
+
+    @abstractmethod
+    def get_status(self) -> SessionProcessorStatus:
+        """Gets the status of the session processor"""
+        pass

invokeai/app/services/session_processor/session_processor_common.py

@@ -0,0 +1,6 @@
+from pydantic import BaseModel, Field
+
+
+class SessionProcessorStatus(BaseModel):
+    is_started: bool = Field(description="Whether the session processor is started")
+    is_processing: bool = Field(description="Whether a session is being processed")

invokeai/app/services/session_processor/session_processor_default.py

@@ -0,0 +1,140 @@
+import traceback
+from threading import BoundedSemaphore
+from threading import Event as ThreadEvent
+from threading import Thread
+from typing import Optional
+
+from fastapi_events.handlers.local import local_handler
+from fastapi_events.typing import Event as FastAPIEvent
+
+from invokeai.app.services.events import EventServiceBase
+from invokeai.app.services.session_queue.session_queue_common import SessionQueueItem
+
+from ..invoker import Invoker
+from .session_processor_base import SessionProcessorBase
+from .session_processor_common import SessionProcessorStatus
+
+POLLING_INTERVAL = 1
+THREAD_LIMIT = 1
+
+
+class DefaultSessionProcessor(SessionProcessorBase):
+    def start(self, invoker: Invoker) -> None:
+        self.__invoker: Invoker = invoker
+        self.__queue_item: Optional[SessionQueueItem] = None
+
+        self.__resume_event = ThreadEvent()
+        self.__stop_event = ThreadEvent()
+        self.__poll_now_event = ThreadEvent()
+
+        local_handler.register(event_name=EventServiceBase.queue_event, _func=self._on_queue_event)
+
+        self.__threadLimit = BoundedSemaphore(THREAD_LIMIT)
+        self.__thread = Thread(
+            name="session_processor",
+            target=self.__process,
+            kwargs=dict(
+                stop_event=self.__stop_event, poll_now_event=self.__poll_now_event, resume_event=self.__resume_event
+            ),
+        )
+        self.__thread.start()
+
+    def stop(self, *args, **kwargs) -> None:
+        self.__stop_event.set()
+
+    def _poll_now(self) -> None:
+        self.__poll_now_event.set()
+
+    async def _on_queue_event(self, event: FastAPIEvent) -> None:
+        event_name = event[1]["event"]
+
+        # This was a match statement, but match is not supported on python 3.9
+        if event_name in [
+            "graph_execution_state_complete",
+            "invocation_error",
+            "session_retrieval_error",
+            "invocation_retrieval_error",
+        ]:
+            self.__queue_item = None
+            self._poll_now()
+        elif (
+            event_name == "session_canceled"
+            and self.__queue_item is not None
+            and self.__queue_item.session_id == event[1]["data"]["graph_execution_state_id"]
+        ):
+            self.__queue_item = None
+            self._poll_now()
+        elif event_name == "batch_enqueued":
+            self._poll_now()
+        elif event_name == "queue_cleared":
+            self.__queue_item = None
+            self._poll_now()
+
+    def resume(self) -> SessionProcessorStatus:
+        if not self.__resume_event.is_set():
+            self.__resume_event.set()
+        return self.get_status()
+
+    def pause(self) -> SessionProcessorStatus:
+        if self.__resume_event.is_set():
+            self.__resume_event.clear()
+        return self.get_status()
+
+    def get_status(self) -> SessionProcessorStatus:
+        return SessionProcessorStatus(
+            is_started=self.__resume_event.is_set(),
+            is_processing=self.__queue_item is not None,
+        )
+
+    def __process(
+        self,
+        stop_event: ThreadEvent,
+        poll_now_event: ThreadEvent,
+        resume_event: ThreadEvent,
+    ):
+        try:
+            stop_event.clear()
+            resume_event.set()
+            self.__threadLimit.acquire()
+            queue_item: Optional[SessionQueueItem] = None
+            self.__invoker.services.logger
+            while not stop_event.is_set():
+                poll_now_event.clear()
+                try:
+                    # do not dequeue if there is already a session running
+                    if self.__queue_item is None and resume_event.is_set():
+                        queue_item = self.__invoker.services.session_queue.dequeue()
+
+                        if queue_item is not None:
+                            self.__invoker.services.logger.debug(f"Executing queue item {queue_item.item_id}")
+                            self.__queue_item = queue_item
+                            self.__invoker.services.graph_execution_manager.set(queue_item.session)
+                            self.__invoker.invoke(
+                                session_queue_batch_id=queue_item.batch_id,
+                                session_queue_id=queue_item.queue_id,
+                                session_queue_item_id=queue_item.item_id,
+                                graph_execution_state=queue_item.session,
+                                invoke_all=True,
+                            )
+                            queue_item = None
+
+                    if queue_item is None:
+                        self.__invoker.services.logger.debug("Waiting for next polling interval or event")
+                        poll_now_event.wait(POLLING_INTERVAL)
+                        continue
+                except Exception as e:
+                    self.__invoker.services.logger.error(f"Error in session processor: {e}")
+                    if queue_item is not None:
+                        self.__invoker.services.session_queue.cancel_queue_item(
+                            queue_item.item_id, error=traceback.format_exc()
+                        )
+                    poll_now_event.wait(POLLING_INTERVAL)
+                    continue
+        except Exception as e:
+            self.__invoker.services.logger.error(f"Fatal Error in session processor: {e}")
+            pass
+        finally:
+            stop_event.clear()
+            poll_now_event.clear()
+            self.__queue_item = None
+            self.__threadLimit.release()

invokeai/app/services/session_queue/session_queue_base.py

@@ -0,0 +1,112 @@
+from abc import ABC, abstractmethod
+from typing import Optional
+
+from invokeai.app.services.graph import Graph
+from invokeai.app.services.session_queue.session_queue_common import (
+    QUEUE_ITEM_STATUS,
+    Batch,
+    BatchStatus,
+    CancelByBatchIDsResult,
+    CancelByQueueIDResult,
+    ClearResult,
+    EnqueueBatchResult,
+    EnqueueGraphResult,
+    IsEmptyResult,
+    IsFullResult,
+    PruneResult,
+    SessionQueueItem,
+    SessionQueueItemDTO,
+    SessionQueueStatus,
+)
+from invokeai.app.services.shared.models import CursorPaginatedResults
+
+
+class SessionQueueBase(ABC):
+    """Base class for session queue"""
+
+    @abstractmethod
+    def dequeue(self) -> Optional[SessionQueueItem]:
+        """Dequeues the next session queue item."""
+        pass
+
+    @abstractmethod
+    def enqueue_graph(self, queue_id: str, graph: Graph, prepend: bool) -> EnqueueGraphResult:
+        """Enqueues a single graph for execution."""
+        pass
+
+    @abstractmethod
+    def enqueue_batch(self, queue_id: str, batch: Batch, prepend: bool) -> EnqueueBatchResult:
+        """Enqueues all permutations of a batch for execution."""
+        pass
+
+    @abstractmethod
+    def get_current(self, queue_id: str) -> Optional[SessionQueueItem]:
+        """Gets the currently-executing session queue item"""
+        pass
+
+    @abstractmethod
+    def get_next(self, queue_id: str) -> Optional[SessionQueueItem]:
+        """Gets the next session queue item (does not dequeue it)"""
+        pass
+
+    @abstractmethod
+    def clear(self, queue_id: str) -> ClearResult:
+        """Deletes all session queue items"""
+        pass
+
+    @abstractmethod
+    def prune(self, queue_id: str) -> PruneResult:
+        """Deletes all completed and errored session queue items"""
+        pass
+
+    @abstractmethod
+    def is_empty(self, queue_id: str) -> IsEmptyResult:
+        """Checks if the queue is empty"""
+        pass
+
+    @abstractmethod
+    def is_full(self, queue_id: str) -> IsFullResult:
+        """Checks if the queue is empty"""
+        pass
+
+    @abstractmethod
+    def get_queue_status(self, queue_id: str) -> SessionQueueStatus:
+        """Gets the status of the queue"""
+        pass
+
+    @abstractmethod
+    def get_batch_status(self, queue_id: str, batch_id: str) -> BatchStatus:
+        """Gets the status of a batch"""
+        pass
+
+    @abstractmethod
+    def cancel_queue_item(self, item_id: int, error: Optional[str] = None) -> SessionQueueItem:
+        """Cancels a session queue item"""
+        pass
+
+    @abstractmethod
+    def cancel_by_batch_ids(self, queue_id: str, batch_ids: list[str]) -> CancelByBatchIDsResult:
+        """Cancels all queue items with matching batch IDs"""
+        pass
+
+    @abstractmethod
+    def cancel_by_queue_id(self, queue_id: str) -> CancelByQueueIDResult:
+        """Cancels all queue items with matching queue ID"""
+        pass
+
+    @abstractmethod
+    def list_queue_items(
+        self,
+        queue_id: str,
+        limit: int,
+        priority: int,
+        cursor: Optional[int] = None,
+        status: Optional[QUEUE_ITEM_STATUS] = None,
+    ) -> CursorPaginatedResults[SessionQueueItemDTO]:
+        """Gets a page of session queue items"""
+        pass
+
+    @abstractmethod
+    def get_queue_item(self, item_id: int) -> SessionQueueItem:
+        """Gets a session queue item by ID"""
+        pass

invokeai/app/services/session_queue/session_queue_common.py

@@ -0,0 +1,423 @@
+import datetime
+import json
+from itertools import chain, product
+from typing import Generator, Iterable, Literal, NamedTuple, Optional, TypeAlias, Union, cast
+
+from pydantic import BaseModel, Field, StrictStr, parse_raw_as, root_validator, validator
+from pydantic.json import pydantic_encoder
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation
+from invokeai.app.services.graph import Graph, GraphExecutionState, NodeNotFoundError
+from invokeai.app.util.misc import uuid_string
+
+# region Errors
+
+
+class BatchZippedLengthError(ValueError):
+    """Raise when a batch has items of different lengths."""
+
+
+class BatchItemsTypeError(TypeError):
+    """Raise when a batch has items of different types."""
+
+
+class BatchDuplicateNodeFieldError(ValueError):
+    """Raise when a batch has duplicate node_path and field_name."""
+
+
+class TooManySessionsError(ValueError):
+    """Raise when too many sessions are requested."""
+
+
+class SessionQueueItemNotFoundError(ValueError):
+    """Raise when a queue item is not found."""
+
+
+# endregion
+
+
+# region Batch
+
+BatchDataType = Union[
+    StrictStr,
+    float,
+    int,
+]
+
+
+class NodeFieldValue(BaseModel):
+    node_path: str = Field(description="The node into which this batch data item will be substituted.")
+    field_name: str = Field(description="The field into which this batch data item will be substituted.")
+    value: BatchDataType = Field(description="The value to substitute into the node/field.")
+
+
+class BatchDatum(BaseModel):
+    node_path: str = Field(description="The node into which this batch data collection will be substituted.")
+    field_name: str = Field(description="The field into which this batch data collection will be substituted.")
+    items: list[BatchDataType] = Field(
+        default_factory=list, description="The list of items to substitute into the node/field."
+    )
+
+
+BatchDataCollection: TypeAlias = list[list[BatchDatum]]
+
+
+class Batch(BaseModel):
+    batch_id: str = Field(default_factory=uuid_string, description="The ID of the batch")
+    data: Optional[BatchDataCollection] = Field(default=None, description="The batch data collection.")
+    graph: Graph = Field(description="The graph to initialize the session with")
+    runs: int = Field(
+        default=1, ge=1, description="Int stating how many times to iterate through all possible batch indices"
+    )
+
+    @validator("data")
+    def validate_lengths(cls, v: Optional[BatchDataCollection]):
+        if v is None:
+            return v
+        for batch_data_list in v:
+            first_item_length = len(batch_data_list[0].items) if batch_data_list and batch_data_list[0].items else 0
+            for i in batch_data_list:
+                if len(i.items) != first_item_length:
+                    raise BatchZippedLengthError("Zipped batch items must all have the same length")
+        return v
+
+    @validator("data")
+    def validate_types(cls, v: Optional[BatchDataCollection]):
+        if v is None:
+            return v
+        for batch_data_list in v:
+            for datum in batch_data_list:
+                # Get the type of the first item in the list
+                first_item_type = type(datum.items[0]) if datum.items else None
+                for item in datum.items:
+                    if type(item) is not first_item_type:
+                        raise BatchItemsTypeError("All items in a batch must have the same type")
+        return v
+
+    @validator("data")
+    def validate_unique_field_mappings(cls, v: Optional[BatchDataCollection]):
+        if v is None:
+            return v
+        paths: set[tuple[str, str]] = set()
+        for batch_data_list in v:
+            for datum in batch_data_list:
+                pair = (datum.node_path, datum.field_name)
+                if pair in paths:
+                    raise BatchDuplicateNodeFieldError("Each batch data must have unique node_id and field_name")
+                paths.add(pair)
+        return v
+
+    @root_validator(skip_on_failure=True)
+    def validate_batch_nodes_and_edges(cls, values):
+        batch_data_collection = cast(Optional[BatchDataCollection], values["data"])
+        if batch_data_collection is None:
+            return values
+        graph = cast(Graph, values["graph"])
+        for batch_data_list in batch_data_collection:
+            for batch_data in batch_data_list:
+                try:
+                    node = cast(BaseInvocation, graph.get_node(batch_data.node_path))
+                except NodeNotFoundError:
+                    raise NodeNotFoundError(f"Node {batch_data.node_path} not found in graph")
+                if batch_data.field_name not in node.__fields__:
+                    raise NodeNotFoundError(f"Field {batch_data.field_name} not found in node {batch_data.node_path}")
+        return values
+
+    @validator("graph")
+    def validate_graph(cls, v: Graph):
+        v.validate_self()
+        return v
+
+    class Config:
+        schema_extra = {
+            "required": [
+                "graph",
+                "runs",
+            ]
+        }
+
+
+# endregion Batch
+
+
+# region Queue Items
+
+DEFAULT_QUEUE_ID = "default"
+
+QUEUE_ITEM_STATUS = Literal["pending", "in_progress", "completed", "failed", "canceled"]
+
+
+def get_field_values(queue_item_dict: dict) -> Optional[list[NodeFieldValue]]:
+    field_values_raw = queue_item_dict.get("field_values", None)
+    return parse_raw_as(list[NodeFieldValue], field_values_raw) if field_values_raw is not None else None
+
+
+def get_session(queue_item_dict: dict) -> GraphExecutionState:
+    session_raw = queue_item_dict.get("session", "{}")
+    return parse_raw_as(GraphExecutionState, session_raw)
+
+
+class SessionQueueItemWithoutGraph(BaseModel):
+    """Session queue item without the full graph. Used for serialization."""
+
+    item_id: int = Field(description="The identifier of the session queue item")
+    status: QUEUE_ITEM_STATUS = Field(default="pending", description="The status of this queue item")
+    priority: int = Field(default=0, description="The priority of this queue item")
+    batch_id: str = Field(description="The ID of the batch associated with this queue item")
+    session_id: str = Field(
+        description="The ID of the session associated with this queue item. The session doesn't exist in graph_executions until the queue item is executed."
+    )
+    error: Optional[str] = Field(default=None, description="The error message if this queue item errored")
+    created_at: Union[datetime.datetime, str] = Field(description="When this queue item was created")
+    updated_at: Union[datetime.datetime, str] = Field(description="When this queue item was updated")
+    started_at: Optional[Union[datetime.datetime, str]] = Field(description="When this queue item was started")
+    completed_at: Optional[Union[datetime.datetime, str]] = Field(description="When this queue item was completed")
+    queue_id: str = Field(description="The id of the queue with which this item is associated")
+    field_values: Optional[list[NodeFieldValue]] = Field(
+        default=None, description="The field values that were used for this queue item"
+    )
+
+    @classmethod
+    def from_dict(cls, queue_item_dict: dict) -> "SessionQueueItemDTO":
+        # must parse these manually
+        queue_item_dict["field_values"] = get_field_values(queue_item_dict)
+        return SessionQueueItemDTO(**queue_item_dict)
+
+    class Config:
+        schema_extra = {
+            "required": [
+                "item_id",
+                "status",
+                "batch_id",
+                "queue_id",
+                "session_id",
+                "priority",
+                "session_id",
+                "created_at",
+                "updated_at",
+            ]
+        }
+
+
+class SessionQueueItemDTO(SessionQueueItemWithoutGraph):
+    pass
+
+
+class SessionQueueItem(SessionQueueItemWithoutGraph):
+    session: GraphExecutionState = Field(description="The fully-populated session to be executed")
+
+    @classmethod
+    def from_dict(cls, queue_item_dict: dict) -> "SessionQueueItem":
+        # must parse these manually
+        queue_item_dict["field_values"] = get_field_values(queue_item_dict)
+        queue_item_dict["session"] = get_session(queue_item_dict)
+        return SessionQueueItem(**queue_item_dict)
+
+    class Config:
+        schema_extra = {
+            "required": [
+                "item_id",
+                "status",
+                "batch_id",
+                "queue_id",
+                "session_id",
+                "session",
+                "priority",
+                "session_id",
+                "created_at",
+                "updated_at",
+            ]
+        }
+
+
+# endregion Queue Items
+
+# region Query Results
+
+
+class SessionQueueStatus(BaseModel):
+    queue_id: str = Field(..., description="The ID of the queue")
+    item_id: Optional[int] = Field(description="The current queue item id")
+    batch_id: Optional[str] = Field(description="The current queue item's batch id")
+    session_id: Optional[str] = Field(description="The current queue item's session id")
+    pending: int = Field(..., description="Number of queue items with status 'pending'")
+    in_progress: int = Field(..., description="Number of queue items with status 'in_progress'")
+    completed: int = Field(..., description="Number of queue items with status 'complete'")
+    failed: int = Field(..., description="Number of queue items with status 'error'")
+    canceled: int = Field(..., description="Number of queue items with status 'canceled'")
+    total: int = Field(..., description="Total number of queue items")
+
+
+class BatchStatus(BaseModel):
+    queue_id: str = Field(..., description="The ID of the queue")
+    batch_id: str = Field(..., description="The ID of the batch")
+    pending: int = Field(..., description="Number of queue items with status 'pending'")
+    in_progress: int = Field(..., description="Number of queue items with status 'in_progress'")
+    completed: int = Field(..., description="Number of queue items with status 'complete'")
+    failed: int = Field(..., description="Number of queue items with status 'error'")
+    canceled: int = Field(..., description="Number of queue items with status 'canceled'")
+    total: int = Field(..., description="Total number of queue items")
+
+
+class EnqueueBatchResult(BaseModel):
+    queue_id: str = Field(description="The ID of the queue")
+    enqueued: int = Field(description="The total number of queue items enqueued")
+    requested: int = Field(description="The total number of queue items requested to be enqueued")
+    batch: Batch = Field(description="The batch that was enqueued")
+    priority: int = Field(description="The priority of the enqueued batch")
+
+
+class EnqueueGraphResult(BaseModel):
+    enqueued: int = Field(description="The total number of queue items enqueued")
+    requested: int = Field(description="The total number of queue items requested to be enqueued")
+    batch: Batch = Field(description="The batch that was enqueued")
+    priority: int = Field(description="The priority of the enqueued batch")
+    queue_item: SessionQueueItemDTO = Field(description="The queue item that was enqueued")
+
+
+class ClearResult(BaseModel):
+    """Result of clearing the session queue"""
+
+    deleted: int = Field(..., description="Number of queue items deleted")
+
+
+class PruneResult(ClearResult):
+    """Result of pruning the session queue"""
+
+    pass
+
+
+class CancelByBatchIDsResult(BaseModel):
+    """Result of canceling by list of batch ids"""
+
+    canceled: int = Field(..., description="Number of queue items canceled")
+
+
+class CancelByQueueIDResult(CancelByBatchIDsResult):
+    """Result of canceling by queue id"""
+
+    pass
+
+
+class IsEmptyResult(BaseModel):
+    """Result of checking if the session queue is empty"""
+
+    is_empty: bool = Field(..., description="Whether the session queue is empty")
+
+
+class IsFullResult(BaseModel):
+    """Result of checking if the session queue is full"""
+
+    is_full: bool = Field(..., description="Whether the session queue is full")
+
+
+# endregion Query Results
+
+
+# region Util
+
+
+def populate_graph(graph: Graph, node_field_values: Iterable[NodeFieldValue]) -> Graph:
+    """
+    Populates the given graph with the given batch data items.
+    """
+    graph_clone = graph.copy(deep=True)
+    for item in node_field_values:
+        node = graph_clone.get_node(item.node_path)
+        if node is None:
+            continue
+        setattr(node, item.field_name, item.value)
+        graph_clone.update_node(item.node_path, node)
+    return graph_clone
+
+
+def create_session_nfv_tuples(
+    batch: Batch, maximum: int
+) -> Generator[tuple[GraphExecutionState, list[NodeFieldValue]], None, None]:
+    """
+    Create all graph permutations from the given batch data and graph. Yields tuples
+    of the form (graph, batch_data_items) where batch_data_items is the list of BatchDataItems
+    that was applied to the graph.
+    """
+
+    # TODO: Should this be a class method on Batch?
+
+    data: list[list[tuple[NodeFieldValue]]] = []
+    batch_data_collection = batch.data if batch.data is not None else []
+    for batch_datum_list in batch_data_collection:
+        # each batch_datum_list needs to be convered to NodeFieldValues and then zipped
+
+        node_field_values_to_zip: list[list[NodeFieldValue]] = []
+        for batch_datum in batch_datum_list:
+            node_field_values = [
+                NodeFieldValue(node_path=batch_datum.node_path, field_name=batch_datum.field_name, value=item)
+                for item in batch_datum.items
+            ]
+            node_field_values_to_zip.append(node_field_values)
+        data.append(list(zip(*node_field_values_to_zip)))
+
+    # create generator to yield session,nfv tuples
+    count = 0
+    for _ in range(batch.runs):
+        for d in product(*data):
+            if count >= maximum:
+                return
+            flat_node_field_values = list(chain.from_iterable(d))
+            graph = populate_graph(batch.graph, flat_node_field_values)
+            yield (GraphExecutionState(graph=graph), flat_node_field_values)
+            count += 1
+
+
+def calc_session_count(batch: Batch) -> int:
+    """
+    Calculates the number of sessions that would be created by the batch, without incurring
+    the overhead of actually generating them. Adapted from `create_sessions().
+    """
+    # TODO: Should this be a class method on Batch?
+    if not batch.data:
+        return batch.runs
+    data = []
+    for batch_datum_list in batch.data:
+        to_zip = []
+        for batch_datum in batch_datum_list:
+            batch_data_items = range(len(batch_datum.items))
+            to_zip.append(batch_data_items)
+        data.append(list(zip(*to_zip)))
+    data_product = list(product(*data))
+    return len(data_product) * batch.runs
+
+
+class SessionQueueValueToInsert(NamedTuple):
+    """A tuple of values to insert into the session_queue table"""
+
+    queue_id: str  # queue_id
+    session: str  # session json
+    session_id: str  # session_id
+    batch_id: str  # batch_id
+    field_values: Optional[str]  # field_values json
+    priority: int  # priority
+
+
+ValuesToInsert: TypeAlias = list[SessionQueueValueToInsert]
+
+
+def prepare_values_to_insert(queue_id: str, batch: Batch, priority: int, max_new_queue_items: int) -> ValuesToInsert:
+    values_to_insert: ValuesToInsert = []
+    for session, field_values in create_session_nfv_tuples(batch, max_new_queue_items):
+        # sessions must have unique id
+        session.id = uuid_string()
+        values_to_insert.append(
+            SessionQueueValueToInsert(
+                queue_id,  # queue_id
+                session.json(),  # session (json)
+                session.id,  # session_id
+                batch.batch_id,  # batch_id
+                # must use pydantic_encoder bc field_values is a list of models
+                json.dumps(field_values, default=pydantic_encoder) if field_values else None,  # field_values (json)
+                priority,  # priority
+            )
+        )
+    return values_to_insert
+
+
+# endregion Util

invokeai/app/services/session_queue/session_queue_sqlite.py

@@ -0,0 +1,835 @@
+import sqlite3
+import threading
+from typing import Optional, Union, cast
+
+from fastapi_events.handlers.local import local_handler
+from fastapi_events.typing import Event as FastAPIEvent
+
+from invokeai.app.services.events import EventServiceBase
+from invokeai.app.services.graph import Graph
+from invokeai.app.services.invoker import Invoker
+from invokeai.app.services.session_queue.session_queue_base import SessionQueueBase
+from invokeai.app.services.session_queue.session_queue_common import (
+    DEFAULT_QUEUE_ID,
+    QUEUE_ITEM_STATUS,
+    Batch,
+    BatchStatus,
+    CancelByBatchIDsResult,
+    CancelByQueueIDResult,
+    ClearResult,
+    EnqueueBatchResult,
+    EnqueueGraphResult,
+    IsEmptyResult,
+    IsFullResult,
+    PruneResult,
+    SessionQueueItem,
+    SessionQueueItemDTO,
+    SessionQueueItemNotFoundError,
+    SessionQueueStatus,
+    calc_session_count,
+    prepare_values_to_insert,
+)
+from invokeai.app.services.shared.models import CursorPaginatedResults
+
+
+class SqliteSessionQueue(SessionQueueBase):
+    __invoker: Invoker
+    __conn: sqlite3.Connection
+    __cursor: sqlite3.Cursor
+    __lock: threading.RLock
+
+    def start(self, invoker: Invoker) -> None:
+        self.__invoker = invoker
+        self._set_in_progress_to_canceled()
+        prune_result = self.prune(DEFAULT_QUEUE_ID)
+        local_handler.register(event_name=EventServiceBase.queue_event, _func=self._on_session_event)
+        self.__invoker.services.logger.info(f"Pruned {prune_result.deleted} finished queue items")
+
+    def __init__(self, conn: sqlite3.Connection, lock: threading.RLock) -> None:
+        super().__init__()
+        self.__conn = conn
+        # Enable row factory to get rows as dictionaries (must be done before making the cursor!)
+        self.__conn.row_factory = sqlite3.Row
+        self.__cursor = self.__conn.cursor()
+        self.__lock = lock
+        self._create_tables()
+
+    def _match_event_name(self, event: FastAPIEvent, match_in: list[str]) -> bool:
+        return event[1]["event"] in match_in
+
+    async def _on_session_event(self, event: FastAPIEvent) -> FastAPIEvent:
+        event_name = event[1]["event"]
+
+        # This was a match statement, but match is not supported on python 3.9
+        if event_name == "graph_execution_state_complete":
+            await self._handle_complete_event(event)
+        elif event_name in ["invocation_error", "session_retrieval_error", "invocation_retrieval_error"]:
+            await self._handle_error_event(event)
+        elif event_name == "session_canceled":
+            await self._handle_cancel_event(event)
+        return event
+
+    async def _handle_complete_event(self, event: FastAPIEvent) -> None:
+        try:
+            item_id = event[1]["data"]["queue_item_id"]
+            # When a queue item has an error, we get an error event, then a completed event.
+            # Mark the queue item completed only if it isn't already marked completed, e.g.
+            # by a previously-handled error event.
+            queue_item = self.get_queue_item(item_id)
+            if queue_item.status not in ["completed", "failed", "canceled"]:
+                queue_item = self._set_queue_item_status(item_id=queue_item.item_id, status="completed")
+        except SessionQueueItemNotFoundError:
+            return
+
+    async def _handle_error_event(self, event: FastAPIEvent) -> None:
+        try:
+            item_id = event[1]["data"]["queue_item_id"]
+            error = event[1]["data"]["error"]
+            queue_item = self.get_queue_item(item_id)
+            # always set to failed if have an error, even if previously the item was marked completed or canceled
+            queue_item = self._set_queue_item_status(item_id=queue_item.item_id, status="failed", error=error)
+        except SessionQueueItemNotFoundError:
+            return
+
+    async def _handle_cancel_event(self, event: FastAPIEvent) -> None:
+        try:
+            item_id = event[1]["data"]["queue_item_id"]
+            queue_item = self.get_queue_item(item_id)
+            if queue_item.status not in ["completed", "failed", "canceled"]:
+                queue_item = self._set_queue_item_status(item_id=queue_item.item_id, status="canceled")
+        except SessionQueueItemNotFoundError:
+            return
+
+    def _create_tables(self) -> None:
+        """Creates the session queue tables, indicies, and triggers"""
+        try:
+            self.__lock.acquire()
+            self.__cursor.execute(
+                """--sql
+                CREATE TABLE IF NOT EXISTS session_queue (
+                    item_id INTEGER PRIMARY KEY AUTOINCREMENT, -- used for ordering, cursor pagination
+                    batch_id TEXT NOT NULL, -- identifier of the batch this queue item belongs to
+                    queue_id TEXT NOT NULL, -- identifier of the queue this queue item belongs to
+                    session_id TEXT NOT NULL UNIQUE, -- duplicated data from the session column, for ease of access
+                    field_values TEXT, -- NULL if no values are associated with this queue item
+                    session TEXT NOT NULL, -- the session to be executed
+                    status TEXT NOT NULL DEFAULT 'pending', -- the status of the queue item, one of 'pending', 'in_progress', 'completed', 'failed', 'canceled'
+                    priority INTEGER NOT NULL DEFAULT 0, -- the priority, higher is more important
+                    error TEXT, -- any errors associated with this queue item
+                    created_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
+                    updated_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')), -- updated via trigger
+                    started_at DATETIME, -- updated via trigger
+                    completed_at DATETIME -- updated via trigger, completed items are cleaned up on application startup
+                    -- Ideally this is a FK, but graph_executions uses INSERT OR REPLACE, and REPLACE triggers the ON DELETE CASCADE...
+                    -- FOREIGN KEY (session_id) REFERENCES graph_executions (id) ON DELETE CASCADE
+                );
+                """
+            )
+
+            self.__cursor.execute(
+                """--sql
+                CREATE UNIQUE INDEX IF NOT EXISTS idx_session_queue_item_id ON session_queue(item_id);
+                """
+            )
+
+            self.__cursor.execute(
+                """--sql
+                CREATE UNIQUE INDEX IF NOT EXISTS idx_session_queue_session_id ON session_queue(session_id);
+                """
+            )
+
+            self.__cursor.execute(
+                """--sql
+                CREATE INDEX IF NOT EXISTS idx_session_queue_batch_id ON session_queue(batch_id);
+                """
+            )
+
+            self.__cursor.execute(
+                """--sql
+                CREATE INDEX IF NOT EXISTS idx_session_queue_created_priority ON session_queue(priority);
+                """
+            )
+
+            self.__cursor.execute(
+                """--sql
+                CREATE INDEX IF NOT EXISTS idx_session_queue_created_status ON session_queue(status);
+                """
+            )
+
+            self.__cursor.execute(
+                """--sql
+                CREATE TRIGGER IF NOT EXISTS tg_session_queue_completed_at
+                AFTER UPDATE OF status ON session_queue
+                FOR EACH ROW
+                WHEN
+                  NEW.status = 'completed'
+                  OR NEW.status = 'failed'
+                  OR NEW.status = 'canceled'
+                BEGIN
+                  UPDATE session_queue
+                  SET completed_at = STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')
+                  WHERE item_id = NEW.item_id;
+                END;
+                """
+            )
+
+            self.__cursor.execute(
+                """--sql
+                CREATE TRIGGER IF NOT EXISTS tg_session_queue_started_at
+                AFTER UPDATE OF status ON session_queue
+                FOR EACH ROW
+                WHEN
+                  NEW.status = 'in_progress'
+                BEGIN
+                  UPDATE session_queue
+                  SET started_at = STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')
+                  WHERE item_id = NEW.item_id;
+                END;
+                """
+            )
+
+            self.__cursor.execute(
+                """--sql
+                CREATE TRIGGER IF NOT EXISTS tg_session_queue_updated_at
+                AFTER UPDATE
+                ON session_queue FOR EACH ROW
+                BEGIN
+                    UPDATE session_queue
+                    SET updated_at = STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')
+                    WHERE item_id = old.item_id;
+                END;
+                """
+            )
+
+            self.__conn.commit()
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+
+    def _set_in_progress_to_canceled(self) -> None:
+        """
+        Sets all in_progress queue items to canceled. Run on app startup, not associated with any queue.
+        This is necessary because the invoker may have been killed while processing a queue item.
+        """
+        try:
+            self.__lock.acquire()
+            self.__cursor.execute(
+                """--sql
+                UPDATE session_queue
+                SET status = 'canceled'
+                WHERE status = 'in_progress';
+                """
+            )
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+
+    def _get_current_queue_size(self, queue_id: str) -> int:
+        """Gets the current number of pending queue items"""
+        self.__cursor.execute(
+            """--sql
+            SELECT count(*)
+            FROM session_queue
+            WHERE
+              queue_id = ?
+              AND status = 'pending'
+            """,
+            (queue_id,),
+        )
+        return cast(int, self.__cursor.fetchone()[0])
+
+    def _get_highest_priority(self, queue_id: str) -> int:
+        """Gets the highest priority value in the queue"""
+        self.__cursor.execute(
+            """--sql
+            SELECT MAX(priority)
+            FROM session_queue
+            WHERE
+              queue_id = ?
+              AND status = 'pending'
+            """,
+            (queue_id,),
+        )
+        return cast(Union[int, None], self.__cursor.fetchone()[0]) or 0
+
+    def enqueue_graph(self, queue_id: str, graph: Graph, prepend: bool) -> EnqueueGraphResult:
+        enqueue_result = self.enqueue_batch(queue_id=queue_id, batch=Batch(graph=graph), prepend=prepend)
+        try:
+            self.__lock.acquire()
+            self.__cursor.execute(
+                """--sql
+                SELECT *
+                FROM session_queue
+                WHERE queue_id = ?
+                AND batch_id = ?
+                """,
+                (queue_id, enqueue_result.batch.batch_id),
+            )
+            result = cast(Union[sqlite3.Row, None], self.__cursor.fetchone())
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        if result is None:
+            raise SessionQueueItemNotFoundError(f"No queue item with batch id {enqueue_result.batch.batch_id}")
+        return EnqueueGraphResult(
+            **enqueue_result.dict(),
+            queue_item=SessionQueueItemDTO.from_dict(dict(result)),
+        )
+
+    def enqueue_batch(self, queue_id: str, batch: Batch, prepend: bool) -> EnqueueBatchResult:
+        try:
+            self.__lock.acquire()
+
+            # TODO: how does this work in a multi-user scenario?
+            current_queue_size = self._get_current_queue_size(queue_id)
+            max_queue_size = self.__invoker.services.configuration.get_config().max_queue_size
+            max_new_queue_items = max_queue_size - current_queue_size
+
+            priority = 0
+            if prepend:
+                priority = self._get_highest_priority(queue_id) + 1
+
+            requested_count = calc_session_count(batch)
+            values_to_insert = prepare_values_to_insert(
+                queue_id=queue_id,
+                batch=batch,
+                priority=priority,
+                max_new_queue_items=max_new_queue_items,
+            )
+            enqueued_count = len(values_to_insert)
+
+            if requested_count > enqueued_count:
+                values_to_insert = values_to_insert[:max_new_queue_items]
+
+            self.__cursor.executemany(
+                """--sql
+                INSERT INTO session_queue (queue_id, session, session_id, batch_id, field_values, priority)
+                VALUES (?, ?, ?, ?, ?, ?)
+                """,
+                values_to_insert,
+            )
+            self.__conn.commit()
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        enqueue_result = EnqueueBatchResult(
+            queue_id=queue_id,
+            requested=requested_count,
+            enqueued=enqueued_count,
+            batch=batch,
+            priority=priority,
+        )
+        self.__invoker.services.events.emit_batch_enqueued(enqueue_result)
+        return enqueue_result
+
+    def dequeue(self) -> Optional[SessionQueueItem]:
+        try:
+            self.__lock.acquire()
+            self.__cursor.execute(
+                """--sql
+                SELECT *
+                FROM session_queue
+                WHERE status = 'pending'
+                ORDER BY
+                  priority DESC,
+                  item_id ASC
+                LIMIT 1
+                """
+            )
+            result = cast(Union[sqlite3.Row, None], self.__cursor.fetchone())
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        if result is None:
+            return None
+        queue_item = SessionQueueItem.from_dict(dict(result))
+        queue_item = self._set_queue_item_status(item_id=queue_item.item_id, status="in_progress")
+        return queue_item
+
+    def get_next(self, queue_id: str) -> Optional[SessionQueueItem]:
+        try:
+            self.__lock.acquire()
+            self.__cursor.execute(
+                """--sql
+                SELECT *
+                FROM session_queue
+                WHERE
+                  queue_id = ?
+                  AND status = 'pending'
+                ORDER BY
+                  priority DESC,
+                  created_at ASC
+                LIMIT 1
+                """,
+                (queue_id,),
+            )
+            result = cast(Union[sqlite3.Row, None], self.__cursor.fetchone())
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        if result is None:
+            return None
+        return SessionQueueItem.from_dict(dict(result))
+
+    def get_current(self, queue_id: str) -> Optional[SessionQueueItem]:
+        try:
+            self.__lock.acquire()
+            self.__cursor.execute(
+                """--sql
+                SELECT *
+                FROM session_queue
+                WHERE
+                  queue_id = ?
+                  AND status = 'in_progress'
+                LIMIT 1
+                """,
+                (queue_id,),
+            )
+            result = cast(Union[sqlite3.Row, None], self.__cursor.fetchone())
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        if result is None:
+            return None
+        return SessionQueueItem.from_dict(dict(result))
+
+    def _set_queue_item_status(
+        self, item_id: int, status: QUEUE_ITEM_STATUS, error: Optional[str] = None
+    ) -> SessionQueueItem:
+        try:
+            self.__lock.acquire()
+            self.__cursor.execute(
+                """--sql
+                UPDATE session_queue
+                SET status = ?, error = ?
+                WHERE item_id = ?
+                """,
+                (status, error, item_id),
+            )
+            self.__conn.commit()
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        queue_item = self.get_queue_item(item_id)
+        batch_status = self.get_batch_status(queue_id=queue_item.queue_id, batch_id=queue_item.batch_id)
+        queue_status = self.get_queue_status(queue_id=queue_item.queue_id)
+        self.__invoker.services.events.emit_queue_item_status_changed(
+            session_queue_item=queue_item,
+            batch_status=batch_status,
+            queue_status=queue_status,
+        )
+        return queue_item
+
+    def is_empty(self, queue_id: str) -> IsEmptyResult:
+        try:
+            self.__lock.acquire()
+            self.__cursor.execute(
+                """--sql
+                SELECT count(*)
+                FROM session_queue
+                WHERE queue_id = ?
+                """,
+                (queue_id,),
+            )
+            is_empty = cast(int, self.__cursor.fetchone()[0]) == 0
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        return IsEmptyResult(is_empty=is_empty)
+
+    def is_full(self, queue_id: str) -> IsFullResult:
+        try:
+            self.__lock.acquire()
+            self.__cursor.execute(
+                """--sql
+                SELECT count(*)
+                FROM session_queue
+                WHERE queue_id = ?
+                """,
+                (queue_id,),
+            )
+            max_queue_size = self.__invoker.services.configuration.max_queue_size
+            is_full = cast(int, self.__cursor.fetchone()[0]) >= max_queue_size
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        return IsFullResult(is_full=is_full)
+
+    def delete_queue_item(self, item_id: int) -> SessionQueueItem:
+        queue_item = self.get_queue_item(item_id=item_id)
+        try:
+            self.__lock.acquire()
+            self.__cursor.execute(
+                """--sql
+                DELETE FROM session_queue
+                WHERE
+                  item_id = ?
+                """,
+                (item_id,),
+            )
+            self.__conn.commit()
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        return queue_item
+
+    def clear(self, queue_id: str) -> ClearResult:
+        try:
+            self.__lock.acquire()
+            self.__cursor.execute(
+                """--sql
+                SELECT COUNT(*)
+                FROM session_queue
+                WHERE queue_id = ?
+                """,
+                (queue_id,),
+            )
+            count = self.__cursor.fetchone()[0]
+            self.__cursor.execute(
+                """--sql
+                DELETE
+                FROM session_queue
+                WHERE queue_id = ?
+                """,
+                (queue_id,),
+            )
+            self.__conn.commit()
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        self.__invoker.services.events.emit_queue_cleared(queue_id)
+        return ClearResult(deleted=count)
+
+    def prune(self, queue_id: str) -> PruneResult:
+        try:
+            where = """--sql
+                WHERE
+                  queue_id = ?
+                  AND (
+                    status = 'completed'
+                    OR status = 'failed'
+                    OR status = 'canceled'
+                  )
+                """
+            self.__lock.acquire()
+            self.__cursor.execute(
+                f"""--sql
+                SELECT COUNT(*)
+                FROM session_queue
+                {where};
+                """,
+                (queue_id,),
+            )
+            count = self.__cursor.fetchone()[0]
+            self.__cursor.execute(
+                f"""--sql
+                DELETE
+                FROM session_queue
+                {where};
+                """,
+                (queue_id,),
+            )
+            self.__conn.commit()
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        return PruneResult(deleted=count)
+
+    def cancel_queue_item(self, item_id: int, error: Optional[str] = None) -> SessionQueueItem:
+        queue_item = self.get_queue_item(item_id)
+        if queue_item.status not in ["canceled", "failed", "completed"]:
+            status = "failed" if error is not None else "canceled"
+            queue_item = self._set_queue_item_status(item_id=item_id, status=status, error=error)
+            self.__invoker.services.queue.cancel(queue_item.session_id)
+            self.__invoker.services.events.emit_session_canceled(
+                queue_item_id=queue_item.item_id,
+                queue_id=queue_item.queue_id,
+                queue_batch_id=queue_item.batch_id,
+                graph_execution_state_id=queue_item.session_id,
+            )
+        return queue_item
+
+    def cancel_by_batch_ids(self, queue_id: str, batch_ids: list[str]) -> CancelByBatchIDsResult:
+        try:
+            current_queue_item = self.get_current(queue_id)
+            self.__lock.acquire()
+            placeholders = ", ".join(["?" for _ in batch_ids])
+            where = f"""--sql
+                WHERE
+                  queue_id == ?
+                  AND batch_id IN ({placeholders})
+                  AND status != 'canceled'
+                  AND status != 'completed'
+                  AND status != 'failed'
+                """
+            params = [queue_id] + batch_ids
+            self.__cursor.execute(
+                f"""--sql
+                SELECT COUNT(*)
+                FROM session_queue
+                {where};
+                """,
+                tuple(params),
+            )
+            count = self.__cursor.fetchone()[0]
+            self.__cursor.execute(
+                f"""--sql
+                UPDATE session_queue
+                SET status = 'canceled'
+                {where};
+                """,
+                tuple(params),
+            )
+            self.__conn.commit()
+            if current_queue_item is not None and current_queue_item.batch_id in batch_ids:
+                self.__invoker.services.queue.cancel(current_queue_item.session_id)
+                self.__invoker.services.events.emit_session_canceled(
+                    queue_item_id=current_queue_item.item_id,
+                    queue_id=current_queue_item.queue_id,
+                    queue_batch_id=current_queue_item.batch_id,
+                    graph_execution_state_id=current_queue_item.session_id,
+                )
+                batch_status = self.get_batch_status(queue_id=queue_id, batch_id=current_queue_item.batch_id)
+                queue_status = self.get_queue_status(queue_id=queue_id)
+                self.__invoker.services.events.emit_queue_item_status_changed(
+                    session_queue_item=current_queue_item,
+                    batch_status=batch_status,
+                    queue_status=queue_status,
+                )
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        return CancelByBatchIDsResult(canceled=count)
+
+    def cancel_by_queue_id(self, queue_id: str) -> CancelByQueueIDResult:
+        try:
+            current_queue_item = self.get_current(queue_id)
+            self.__lock.acquire()
+            where = """--sql
+                WHERE
+                  queue_id is ?
+                  AND status != 'canceled'
+                  AND status != 'completed'
+                  AND status != 'failed'
+                """
+            params = [queue_id]
+            self.__cursor.execute(
+                f"""--sql
+                SELECT COUNT(*)
+                FROM session_queue
+                {where};
+                """,
+                tuple(params),
+            )
+            count = self.__cursor.fetchone()[0]
+            self.__cursor.execute(
+                f"""--sql
+                UPDATE session_queue
+                SET status = 'canceled'
+                {where};
+                """,
+                tuple(params),
+            )
+            self.__conn.commit()
+            if current_queue_item is not None and current_queue_item.queue_id == queue_id:
+                self.__invoker.services.queue.cancel(current_queue_item.session_id)
+                self.__invoker.services.events.emit_session_canceled(
+                    queue_item_id=current_queue_item.item_id,
+                    queue_id=current_queue_item.queue_id,
+                    queue_batch_id=current_queue_item.batch_id,
+                    graph_execution_state_id=current_queue_item.session_id,
+                )
+                batch_status = self.get_batch_status(queue_id=queue_id, batch_id=current_queue_item.batch_id)
+                queue_status = self.get_queue_status(queue_id=queue_id)
+                self.__invoker.services.events.emit_queue_item_status_changed(
+                    session_queue_item=current_queue_item,
+                    batch_status=batch_status,
+                    queue_status=queue_status,
+                )
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        return CancelByQueueIDResult(canceled=count)
+
+    def get_queue_item(self, item_id: int) -> SessionQueueItem:
+        try:
+            self.__lock.acquire()
+            self.__cursor.execute(
+                """--sql
+                SELECT * FROM session_queue
+                WHERE
+                  item_id = ?
+                """,
+                (item_id,),
+            )
+            result = cast(Union[sqlite3.Row, None], self.__cursor.fetchone())
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        if result is None:
+            raise SessionQueueItemNotFoundError(f"No queue item with id {item_id}")
+        return SessionQueueItem.from_dict(dict(result))
+
+    def list_queue_items(
+        self,
+        queue_id: str,
+        limit: int,
+        priority: int,
+        cursor: Optional[int] = None,
+        status: Optional[QUEUE_ITEM_STATUS] = None,
+    ) -> CursorPaginatedResults[SessionQueueItemDTO]:
+        try:
+            item_id = cursor
+            self.__lock.acquire()
+            query = """--sql
+                SELECT item_id,
+                    status,
+                    priority,
+                    field_values,
+                    error,
+                    created_at,
+                    updated_at,
+                    completed_at,
+                    started_at,
+                    session_id,
+                    batch_id,
+                    queue_id
+                FROM session_queue
+                WHERE queue_id = ?
+            """
+            params: list[Union[str, int]] = [queue_id]
+
+            if status is not None:
+                query += """--sql
+                    AND status = ?
+                    """
+                params.append(status)
+
+            if item_id is not None:
+                query += """--sql
+                    AND (priority < ?) OR (priority = ? AND item_id > ?)
+                    """
+                params.extend([priority, priority, item_id])
+
+            query += """--sql
+                ORDER BY
+                  priority DESC,
+                  item_id ASC
+                LIMIT ?
+                """
+            params.append(limit + 1)
+            self.__cursor.execute(query, params)
+            results = cast(list[sqlite3.Row], self.__cursor.fetchall())
+            items = [SessionQueueItemDTO.from_dict(dict(result)) for result in results]
+            has_more = False
+            if len(items) > limit:
+                # remove the extra item
+                items.pop()
+                has_more = True
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        return CursorPaginatedResults(items=items, limit=limit, has_more=has_more)
+
+    def get_queue_status(self, queue_id: str) -> SessionQueueStatus:
+        try:
+            self.__lock.acquire()
+            self.__cursor.execute(
+                """--sql
+                SELECT status, count(*)
+                FROM session_queue
+                WHERE queue_id = ?
+                GROUP BY status
+                """,
+                (queue_id,),
+            )
+            counts_result = cast(list[sqlite3.Row], self.__cursor.fetchall())
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+
+        current_item = self.get_current(queue_id=queue_id)
+        total = sum(row[1] for row in counts_result)
+        counts: dict[str, int] = {row[0]: row[1] for row in counts_result}
+        return SessionQueueStatus(
+            queue_id=queue_id,
+            item_id=current_item.item_id if current_item else None,
+            session_id=current_item.session_id if current_item else None,
+            batch_id=current_item.batch_id if current_item else None,
+            pending=counts.get("pending", 0),
+            in_progress=counts.get("in_progress", 0),
+            completed=counts.get("completed", 0),
+            failed=counts.get("failed", 0),
+            canceled=counts.get("canceled", 0),
+            total=total,
+        )
+
+    def get_batch_status(self, queue_id: str, batch_id: str) -> BatchStatus:
+        try:
+            self.__lock.acquire()
+            self.__cursor.execute(
+                """--sql
+                SELECT status, count(*)
+                FROM session_queue
+                WHERE
+                  queue_id = ?
+                  AND batch_id = ?
+                GROUP BY status
+                """,
+                (queue_id, batch_id),
+            )
+            result = cast(list[sqlite3.Row], self.__cursor.fetchall())
+            total = sum(row[1] for row in result)
+            counts: dict[str, int] = {row[0]: row[1] for row in result}
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+
+        return BatchStatus(
+            batch_id=batch_id,
+            queue_id=queue_id,
+            pending=counts.get("pending", 0),
+            in_progress=counts.get("in_progress", 0),
+            completed=counts.get("completed", 0),
+            failed=counts.get("failed", 0),
+            canceled=counts.get("canceled", 0),
+            total=total,
+        )

invokeai/app/services/shared/models.py

@@ -0,0 +1,14 @@
+from typing import Generic, TypeVar
+
+from pydantic import BaseModel, Field
+from pydantic.generics import GenericModel
+
+GenericBaseModel = TypeVar("GenericBaseModel", bound=BaseModel)
+
+
+class CursorPaginatedResults(GenericModel, Generic[GenericBaseModel]):
+    """Cursor-paginated results"""
+
+    limit: int = Field(..., description="Limit of items to get")
+    has_more: bool = Field(..., description="Whether there are more items available")
+    items: list[GenericBaseModel] = Field(..., description="Items")

invokeai/app/services/sqlite.py

@@ -1,5 +1,5 @@
 import sqlite3
-from threading import Lock
+import threading
 from typing import Generic, Optional, TypeVar, get_args
 
 from pydantic import BaseModel, parse_raw_as
@@ -12,23 +12,19 @@ sqlite_memory = ":memory:"
 
 
 class SqliteItemStorage(ItemStorageABC, Generic[T]):
-    _filename: str
     _table_name: str
     _conn: sqlite3.Connection
     _cursor: sqlite3.Cursor
     _id_field: str
-    _lock: Lock
+    _lock: threading.RLock
 
-    def __init__(self, filename: str, table_name: str, id_field: str = "id"):
+    def __init__(self, conn: sqlite3.Connection, table_name: str, lock: threading.RLock, id_field: str = "id"):
         super().__init__()
 
-        self._filename = filename
         self._table_name = table_name
         self._id_field = id_field  # TODO: validate that T has this field
-        self._lock = Lock()
-        self._conn = sqlite3.connect(
-            self._filename, check_same_thread=False
-        )  # TODO: figure out a better threading solution
+        self._lock = lock
+        self._conn = conn
         self._cursor = self._conn.cursor()
 
         self._create_table()
@@ -49,8 +45,7 @@ class SqliteItemStorage(ItemStorageABC, Generic[T]):
 
     def _parse_item(self, item: str) -> T:
         item_type = get_args(self.__orig_class__)[0]
-        parsed = parse_raw_as(item_type, item)
-        return parsed
+        return parse_raw_as(item_type, item)
 
     def set(self, item: T):
         try:

invokeai/app/services/thread.py

@@ -0,0 +1,3 @@
+import threading
+
+lock = threading.RLock()

invokeai/app/util/controlnet_utils.py

@@ -265,22 +265,41 @@ def np_img_resize(np_img: np.ndarray, resize_mode: str, h: int, w: int, device:
 
 
 def prepare_control_image(
-    # image used to be Union[PIL.Image.Image, List[PIL.Image.Image], torch.Tensor, List[torch.Tensor]]
-    # but now should be able to assume that image is a single PIL.Image, which simplifies things
     image: Image,
-    # FIXME: need to fix hardwiring of width and height, change to basing on latents dimensions?
-    # latents_to_match_resolution, # TorchTensor of shape (batch_size, 3, height, width)
-    width=512,  # should be 8 * latent.shape[3]
-    height=512,  # should be 8 * latent height[2]
-    # batch_size=1, # currently no batching
-    # num_images_per_prompt=1, # currently only single image
+    width: int,
+    height: int,
+    num_channels: int = 3,
     device="cuda",
     dtype=torch.float16,
     do_classifier_free_guidance=True,
     control_mode="balanced",
     resize_mode="just_resize_simple",
 ):
-    # FIXME: implement "crop_resize_simple" and "fill_resize_simple", or pull them out
+    """Pre-process images for ControlNets or T2I-Adapters.
+
+    Args:
+        image (Image): The PIL image to pre-process.
+        width (int): The target width in pixels.
+        height (int): The target height in pixels.
+        num_channels (int, optional): The target number of image channels. This is achieved by converting the input
+            image to RGB, then naively taking the first `num_channels` channels. The primary use case is converting a
+            RGB image to a single-channel grayscale image. Raises if `num_channels` cannot be achieved. Defaults to 3.
+        device (str, optional): The target device for the output image. Defaults to "cuda".
+        dtype (_type_, optional): The dtype for the output image. Defaults to torch.float16.
+        do_classifier_free_guidance (bool, optional): If True, repeat the output image along the batch dimension.
+            Defaults to True.
+        control_mode (str, optional): Defaults to "balanced".
+        resize_mode (str, optional): Defaults to "just_resize_simple".
+
+    Raises:
+        NotImplementedError: If resize_mode == "crop_resize_simple".
+        NotImplementedError: If resize_mode == "fill_resize_simple".
+        ValueError: If `resize_mode` is not recognized.
+        ValueError: If `num_channels` is out of range.
+
+    Returns:
+        torch.Tensor: The pre-processed input tensor.
+    """
     if (
         resize_mode == "just_resize_simple"
         or resize_mode == "crop_resize_simple"
@@ -289,10 +308,10 @@ def prepare_control_image(
         image = image.convert("RGB")
         if resize_mode == "just_resize_simple":
             image = image.resize((width, height), resample=PIL_INTERPOLATION["lanczos"])
-        elif resize_mode == "crop_resize_simple":  # not yet implemented
-            pass
-        elif resize_mode == "fill_resize_simple":  # not yet implemented
-            pass
+        elif resize_mode == "crop_resize_simple":
+            raise NotImplementedError(f"prepare_control_image is not implemented for resize_mode='{resize_mode}'.")
+        elif resize_mode == "fill_resize_simple":
+            raise NotImplementedError(f"prepare_control_image is not implemented for resize_mode='{resize_mode}'.")
         nimage = np.array(image)
         nimage = nimage[None, :]
         nimage = np.concatenate([nimage], axis=0)
@@ -313,9 +332,11 @@ def prepare_control_image(
             device=device,
         )
     else:
-        pass
-        print("ERROR: invalid resize_mode ==> ", resize_mode)
-        exit(1)
+        raise ValueError(f"Unsupported resize_mode: '{resize_mode}'.")
+
+    if timage.shape[1] < num_channels or num_channels <= 0:
+        raise ValueError(f"Cannot achieve the target of num_channels={num_channels}.")
+    timage = timage[:, :num_channels, :, :]
 
     timage = timage.to(device=device, dtype=dtype)
     cfg_injection = control_mode == "more_control" or control_mode == "unbalanced"

invokeai/app/util/misc.py

@@ -1,4 +1,5 @@
 import datetime
+import uuid
 
 import numpy as np
 
@@ -21,3 +22,8 @@ SEED_MAX = np.iinfo(np.uint32).max
 def get_random_seed():
     rng = np.random.default_rng(seed=None)
     return int(rng.integers(0, SEED_MAX))
+
+
+def uuid_string():
+    res = uuid.uuid4()
+    return str(res)

invokeai/app/util/step_callback.py

@@ -110,6 +110,9 @@ def stable_diffusion_step_callback(
     dataURL = image_to_dataURL(image, image_format="JPEG")
 
     context.services.events.emit_generator_progress(
+        queue_id=context.queue_id,
+        queue_item_id=context.queue_item_id,
+        queue_batch_id=context.queue_batch_id,
         graph_execution_state_id=context.graph_execution_state_id,
         node=node,
         source_node_id=source_node_id,

invokeai/assets/fonts/inter/LICENSE.txt

@@ -0,0 +1,94 @@
+Copyright (c) 2016-2020 The Inter Project Authors.
+"Inter" is trademark of Rasmus Andersson.
+https://github.com/rsms/inter
+
+This Font Software is licensed under the SIL Open Font License, Version 1.1.
+This license is copied below, and is also available with a FAQ at:
+http://scripts.sil.org/OFL
+
+-----------------------------------------------------------
+SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007
+-----------------------------------------------------------
+
+PREAMBLE
+The goals of the Open Font License (OFL) are to stimulate worldwide
+development of collaborative font projects, to support the font creation
+efforts of academic and linguistic communities, and to provide a free and
+open framework in which fonts may be shared and improved in partnership
+with others.
+
+The OFL allows the licensed fonts to be used, studied, modified and
+redistributed freely as long as they are not sold by themselves. The
+fonts, including any derivative works, can be bundled, embedded,
+redistributed and/or sold with any software provided that any reserved
+names are not used by derivative works. The fonts and derivatives,
+however, cannot be released under any other type of license. The
+requirement for fonts to remain under this license does not apply
+to any document created using the fonts or their derivatives.
+
+DEFINITIONS
+"Font Software" refers to the set of files released by the Copyright
+Holder(s) under this license and clearly marked as such. This may
+include source files, build scripts and documentation.
+
+"Reserved Font Name" refers to any names specified as such after the
+copyright statement(s).
+
+"Original Version" refers to the collection of Font Software components as
+distributed by the Copyright Holder(s).
+
+"Modified Version" refers to any derivative made by adding to, deleting,
+or substituting -- in part or in whole -- any of the components of the
+Original Version, by changing formats or by porting the Font Software to a
+new environment.
+
+"Author" refers to any designer, engineer, programmer, technical
+writer or other person who contributed to the Font Software.
+
+PERMISSION AND CONDITIONS
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of the Font Software, to use, study, copy, merge, embed, modify,
+redistribute, and sell modified and unmodified copies of the Font
+Software, subject to the following conditions:
+
+1) Neither the Font Software nor any of its individual components,
+in Original or Modified Versions, may be sold by itself.
+
+2) Original or Modified Versions of the Font Software may be bundled,
+redistributed and/or sold with any software, provided that each copy
+contains the above copyright notice and this license. These can be
+included either as stand-alone text files, human-readable headers or
+in the appropriate machine-readable metadata fields within text or
+binary files as long as those fields can be easily viewed by the user.
+
+3) No Modified Version of the Font Software may use the Reserved Font
+Name(s) unless explicit written permission is granted by the corresponding
+Copyright Holder. This restriction only applies to the primary font name as
+presented to the users.
+
+4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font
+Software shall not be used to promote, endorse or advertise any
+Modified Version, except to acknowledge the contribution(s) of the
+Copyright Holder(s) and the Author(s) or with their explicit written
+permission.
+
+5) The Font Software, modified or unmodified, in part or in whole,
+must be distributed entirely under this license, and must not be
+distributed under any other license. The requirement for fonts to
+remain under this license does not apply to any document created
+using the Font Software.
+
+TERMINATION
+This license becomes null and void if any of the above conditions are
+not met.
+
+DISCLAIMER
+THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT
+OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE
+COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL
+DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM
+OTHER DEALINGS IN THE FONT SOFTWARE.

invokeai/backend/image_util/invoke_metadata.py

@@ -0,0 +1,46 @@
+# Copyright (c) 2023 Lincoln D. Stein and the InvokeAI Development Team
+
+"""Very simple functions to fetch and print metadata from InvokeAI-generated images."""
+
+import json
+import sys
+from pathlib import Path
+from typing import Any, Dict
+
+from PIL import Image
+
+
+def get_invokeai_metadata(image_path: Path) -> Dict[str, Any]:
+    """
+    Retrieve "invokeai_metadata" field from png image.
+
+    :param image_path: Path to the image to read metadata from.
+    May raise:
+      OSError -- image path not found
+      KeyError -- image doesn't contain the metadata field
+    """
+    image: Image = Image.open(image_path)
+    return json.loads(image.text["invokeai_metadata"])
+
+
+def print_invokeai_metadata(image_path: Path):
+    """Pretty-print the metadata."""
+    try:
+        metadata = get_invokeai_metadata(image_path)
+        print(f"{image_path}:\n{json.dumps(metadata, sort_keys=True, indent=4)}")
+    except OSError:
+        print(f"{image_path}:\nNo file found.")
+    except KeyError:
+        print(f"{image_path}:\nNo metadata found.")
+    print()
+
+
+def main():
+    """Run the command-line utility."""
+    image_paths = sys.argv[1:]
+    if not image_paths:
+        print(f"Usage: {Path(sys.argv[0]).name} image1 image2 image3 ...")
+        print("\nPretty-print InvokeAI image metadata from the listed png files.")
+        sys.exit(-1)
+    for img in image_paths:
+        print_invokeai_metadata(img)

invokeai/backend/install/invokeai_configure.py

@@ -70,7 +70,6 @@ def get_literal_fields(field) -> list[Any]:
 config = InvokeAIAppConfig.get_config()
 
 Model_dir = "models"
-
 Default_config_file = config.model_conf_path
 SD_Configs = config.legacy_conf_path
 
@@ -93,7 +92,7 @@ INIT_FILE_PREAMBLE = """# InvokeAI initialization file
 # or renaming it and then running invokeai-configure again.
 """
 
-logger = InvokeAILogger.getLogger()
+logger = InvokeAILogger.get_logger()
 
 
 class DummyWidgetValue(Enum):
@@ -458,7 +457,7 @@ Use cursor arrows to make a checkbox selection, and space to toggle.
         )
         self.add_widget_intelligent(
             npyscreen.TitleFixedText,
-            name="Model RAM cache size (GB). Make this at least large enough to hold a single full model.",
+            name="Model RAM cache size (GB). Make this at least large enough to hold a single full model (2GB for SD-1, 6GB for SDXL).",
             begin_entry_at=0,
             editable=False,
             color="CONTROL",
@@ -651,8 +650,19 @@ def edit_opts(program_opts: Namespace, invokeai_opts: Namespace) -> argparse.Nam
     return editApp.new_opts()
 
 
+def default_ramcache() -> float:
+    """Run a heuristic for the default RAM cache based on installed RAM."""
+
+    # Note that on my 64 GB machine, psutil.virtual_memory().total gives 62 GB,
+    # So we adjust everthing down a bit.
+    return (
+        15.0 if MAX_RAM >= 60 else 7.5 if MAX_RAM >= 30 else 4 if MAX_RAM >= 14 else 2.1
+    )  # 2.1 is just large enough for sd 1.5 ;-)
+
+
 def default_startup_options(init_file: Path) -> Namespace:
     opts = InvokeAIAppConfig.get_config()
+    opts.ram = opts.ram or default_ramcache()
     return opts
 
 
@@ -894,7 +904,7 @@ def main():
     if opt.full_precision:
         invoke_args.extend(["--precision", "float32"])
     config.parse_args(invoke_args)
-    logger = InvokeAILogger().getLogger(config=config)
+    logger = InvokeAILogger().get_logger(config=config)
 
     errors = set()
 

invokeai/backend/install/model_install_backend.py

@@ -2,6 +2,7 @@
 Utility (backend) functions used by model_install.py
 """
 import os
+import re
 import shutil
 import warnings
 from dataclasses import dataclass, field
@@ -30,7 +31,7 @@ warnings.filterwarnings("ignore")
 
 # --------------------------globals-----------------------
 config = InvokeAIAppConfig.get_config()
-logger = InvokeAILogger.getLogger(name="InvokeAI")
+logger = InvokeAILogger.get_logger(name="InvokeAI")
 
 # the initial "configs" dir is now bundled in the `invokeai.configs` package
 Dataset_path = Path(configs.__path__[0]) / "INITIAL_MODELS.yaml"
@@ -47,8 +48,14 @@ Config_preamble = """
 
 LEGACY_CONFIGS = {
     BaseModelType.StableDiffusion1: {
-        ModelVariantType.Normal: "v1-inference.yaml",
-        ModelVariantType.Inpaint: "v1-inpainting-inference.yaml",
+        ModelVariantType.Normal: {
+            SchedulerPredictionType.Epsilon: "v1-inference.yaml",
+            SchedulerPredictionType.VPrediction: "v1-inference-v.yaml",
+        },
+        ModelVariantType.Inpaint: {
+            SchedulerPredictionType.Epsilon: "v1-inpainting-inference.yaml",
+            SchedulerPredictionType.VPrediction: "v1-inpainting-inference-v.yaml",
+        },
     },
     BaseModelType.StableDiffusion2: {
         ModelVariantType.Normal: {
@@ -69,14 +76,6 @@ LEGACY_CONFIGS = {
 }
 
 
-@dataclass
-class ModelInstallList:
-    """Class for listing models to be installed/removed"""
-
-    install_models: List[str] = field(default_factory=list)
-    remove_models: List[str] = field(default_factory=list)
-
-
 @dataclass
 class InstallSelections:
     install_models: List[str] = field(default_factory=list)
@@ -90,10 +89,12 @@ class ModelLoadInfo:
     base_type: BaseModelType
     path: Optional[Path] = None
     repo_id: Optional[str] = None
+    subfolder: Optional[str] = None
     description: str = ""
     installed: bool = False
     recommended: bool = False
     default: bool = False
+    requires: Optional[List[str]] = field(default_factory=list)
 
 
 class ModelInstall(object):
@@ -127,12 +128,13 @@ class ModelInstall(object):
             value["name"] = name
             value["base_type"] = base
             value["model_type"] = model_type
-            model_dict[key] = ModelLoadInfo(**value)
+            model_info = ModelLoadInfo(**value)
+            if model_info.subfolder and model_info.repo_id:
+                model_info.repo_id += f":{model_info.subfolder}"
+            model_dict[key] = model_info
 
         # supplement with entries in models.yaml
         installed_models = [x for x in self.mgr.list_models()]
-        # suppresses autoloaded models
-        # installed_models = [x for x in self.mgr.list_models() if not self._is_autoloaded(x)]
 
         for md in installed_models:
             base = md["base_model"]
@@ -164,9 +166,12 @@ class ModelInstall(object):
 
     def list_models(self, model_type):
         installed = self.mgr.list_models(model_type=model_type)
+        print()
         print(f"Installed models of type `{model_type}`:")
+        print(f"{'Model Key':50} Model Path")
         for i in installed:
-            print(f"{i['model_name']}\t{i['base_model']}\t{i['path']}")
+            print(f"{'/'.join([i['base_model'],i['model_type'],i['model_name']]):50} {i['path']}")
+        print()
 
     # logic here a little reversed to maintain backward compatibility
     def starter_models(self, all_models: bool = False) -> Set[str]:
@@ -204,6 +209,8 @@ class ModelInstall(object):
             job += 1
 
         # add requested models
+        self._remove_installed(selections.install_models)
+        self._add_required_models(selections.install_models)
         for path in selections.install_models:
             logger.info(f"Installing {path} [{job}/{jobs}]")
             try:
@@ -263,6 +270,26 @@ class ModelInstall(object):
 
         return models_installed
 
+    def _remove_installed(self, model_list: List[str]):
+        all_models = self.all_models()
+        for path in model_list:
+            key = self.reverse_paths.get(path)
+            if key and all_models[key].installed:
+                logger.warning(f"{path} already installed. Skipping.")
+                model_list.remove(path)
+
+    def _add_required_models(self, model_list: List[str]):
+        additional_models = []
+        all_models = self.all_models()
+        for path in model_list:
+            if not (key := self.reverse_paths.get(path)):
+                continue
+            for requirement in all_models[key].requires:
+                requirement_key = self.reverse_paths.get(requirement)
+                if not all_models[requirement_key].installed:
+                    additional_models.append(requirement)
+        model_list.extend(additional_models)
+
     # 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) -> AddModelResult:
@@ -286,7 +313,7 @@ class ModelInstall(object):
             location = download_with_resume(url, Path(staging))
             if not location:
                 logger.error(f"Unable to download {url}. Skipping.")
-            info = ModelProbe().heuristic_probe(location)
+            info = ModelProbe().heuristic_probe(location, self.prediction_helper)
             dest = self.config.models_path / info.base_type.value / info.model_type.value / location.name
             dest.parent.mkdir(parents=True, exist_ok=True)
             models_path = shutil.move(location, dest)
@@ -295,36 +322,63 @@ class ModelInstall(object):
         return self._install_path(Path(models_path), info)
 
     def _install_repo(self, repo_id: str) -> AddModelResult:
+        # hack to recover models stored in subfolders --
+        # Required to get the "v2" model of monster-labs/control_v1p_sd15_qrcode_monster
+        subfolder = None
+        if match := re.match(r"^([^/]+/[^/]+):(\w+)$", repo_id):
+            repo_id = match.group(1)
+            subfolder = match.group(2)
+
         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]
+        if subfolder:
+            files = [x for x in files if x.startswith(f"{subfolder}/")]
+        prefix = f"{subfolder}/" if subfolder else ""
+
         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
-            elif "unet/model.onnx" in files:
+            if f"{prefix}model_index.json" in files:
+                location = self._download_hf_pipeline(repo_id, staging, subfolder=subfolder)  # pipeline
+            elif f"{prefix}unet/model.onnx" in files:
                 location = self._download_hf_model(repo_id, files, staging)
             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
+                    if f"{prefix}pytorch_lora_weights.{suffix}" in files:
+                        location = self._download_hf_model(
+                            repo_id, ["pytorch_lora_weights.bin"], staging, subfolder=subfolder
+                        )  # LoRA
                         break
                     elif (
-                        self.config.precision == "float16" and f"diffusion_pytorch_model.fp16.{suffix}" in files
+                        self.config.precision == "float16" and f"{prefix}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)
+                        location = self._download_hf_model(repo_id, files, staging, subfolder=subfolder)
                         break
-                    elif f"diffusion_pytorch_model.{suffix}" in files:
+                    elif f"{prefix}diffusion_pytorch_model.{suffix}" in files:
                         files = ["config.json", f"diffusion_pytorch_model.{suffix}"]
-                        location = self._download_hf_model(repo_id, files, staging)
+                        location = self._download_hf_model(repo_id, files, staging, subfolder=subfolder)
                         break
-                    elif f"learned_embeds.{suffix}" in files:
-                        location = self._download_hf_model(repo_id, [f"learned_embeds.{suffix}"], staging)
+                    elif f"{prefix}learned_embeds.{suffix}" in files:
+                        location = self._download_hf_model(
+                            repo_id, [f"learned_embeds.{suffix}"], staging, subfolder=subfolder
+                        )
+                        break
+                    elif (
+                        f"{prefix}image_encoder.txt" in files and f"{prefix}ip_adapter.{suffix}" in files
+                    ):  # IP-Adapter
+                        files = ["image_encoder.txt", f"ip_adapter.{suffix}"]
+                        location = self._download_hf_model(repo_id, files, staging, subfolder=subfolder)
+                        break
+                    elif f"{prefix}model.{suffix}" in files and f"{prefix}config.json" in files:
+                        # This elif-condition is pretty fragile, but it is intended to handle CLIP Vision models hosted
+                        # by InvokeAI for use with IP-Adapters.
+                        files = ["config.json", f"model.{suffix}"]
+                        location = self._download_hf_model(repo_id, files, staging, subfolder=subfolder)
                         break
             if not location:
                 logger.warning(f"Could not determine type of repo {repo_id}. Skipping install.")
@@ -383,7 +437,7 @@ class ModelInstall(object):
                     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:
+                    elif info.base_type in [BaseModelType.StableDiffusion1, BaseModelType.StableDiffusion2]:
                         legacy_conf = Path(
                             self.config.legacy_conf_dir,
                             LEGACY_CONFIGS[info.base_type][info.variant_type][info.prediction_type],
@@ -411,9 +465,9 @@ class ModelInstall(object):
         else:
             return path
 
-    def _download_hf_pipeline(self, repo_id: str, staging: Path) -> Path:
+    def _download_hf_pipeline(self, repo_id: str, staging: Path, subfolder: str = None) -> Path:
         """
-        This retrieves a StableDiffusion model from cache or remote and then
+        Retrieve a StableDiffusion model from cache or remote and then
         does a save_pretrained() to the indicated staging area.
         """
         _, name = repo_id.split("/")
@@ -428,6 +482,7 @@ class ModelInstall(object):
                     variant=variant,
                     torch_dtype=precision,
                     safety_checker=None,
+                    subfolder=subfolder,
                 )
             except Exception as e:  # most errors are due to fp16 not being present. Fix this to catch other errors
                 if "fp16" not in str(e):
@@ -442,7 +497,7 @@ class ModelInstall(object):
         model.save_pretrained(staging / name, safe_serialization=True)
         return staging / name
 
-    def _download_hf_model(self, repo_id: str, files: List[str], staging: Path) -> Path:
+    def _download_hf_model(self, repo_id: str, files: List[str], staging: Path, subfolder: None) -> Path:
         _, name = repo_id.split("/")
         location = staging / name
         paths = list()
@@ -453,7 +508,7 @@ class ModelInstall(object):
                 model_dir=location / filePath.parent,
                 model_name=filePath.name,
                 access_token=self.access_token,
-                subfolder=filePath.parent,
+                subfolder=filePath.parent / subfolder if subfolder else filePath.parent,
             )
             if p:
                 paths.append(p)
@@ -482,7 +537,7 @@ def yes_or_no(prompt: str, default_yes=True):
 
 # ---------------------------------------------
 def hf_download_from_pretrained(model_class: object, model_name: str, destination: Path, **kwargs):
-    logger = InvokeAILogger.getLogger("InvokeAI")
+    logger = InvokeAILogger.get_logger("InvokeAI")
     logger.addFilter(lambda x: "fp16 is not a valid" not in x.getMessage())
 
     model = model_class.from_pretrained(
@@ -534,14 +589,17 @@ def hf_download_with_resume(
         logger.info(f"{model_name}: Downloading...")
 
     try:
-        with open(model_dest, open_mode) as file, tqdm(
-            desc=model_name,
-            initial=exist_size,
-            total=total + exist_size,
-            unit="iB",
-            unit_scale=True,
-            unit_divisor=1000,
-        ) as bar:
+        with (
+            open(model_dest, open_mode) as file,
+            tqdm(
+                desc=model_name,
+                initial=exist_size,
+                total=total + exist_size,
+                unit="iB",
+                unit_scale=True,
+                unit_divisor=1000,
+            ) as bar,
+        ):
             for data in resp.iter_content(chunk_size=1024):
                 size = file.write(data)
                 bar.update(size)

invokeai/backend/ip_adapter/README.md

@@ -0,0 +1,45 @@
+# IP-Adapter Model Formats
+
+The official IP-Adapter models are released here: [h94/IP-Adapter](https://huggingface.co/h94/IP-Adapter)
+
+This official model repo does not integrate well with InvokeAI's current approach to model management, so we have defined a new file structure for IP-Adapter models. The InvokeAI format is described below.
+
+## CLIP Vision Models
+
+CLIP Vision models are organized in `diffusers`` format. The expected directory structure is:
+
+```bash
+ip_adapter_sd_image_encoder/
+├── config.json
+└── model.safetensors
+```
+
+## IP-Adapter Models
+
+IP-Adapter models are stored in a directory containing two files
+- `image_encoder.txt`: A text file containing the model identifier for the CLIP Vision encoder that is intended to be used with this IP-Adapter model.
+- `ip_adapter.bin`: The IP-Adapter weights.
+
+Sample directory structure:
+```bash
+ip_adapter_sd15/
+├── image_encoder.txt
+└── ip_adapter.bin
+```
+
+### Why save the weights in a .safetensors file?
+
+The weights in `ip_adapter.bin` are stored in a nested dict, which is not supported by `safetensors`. This could be solved by splitting `ip_adapter.bin` into multiple files, but for now we have decided to maintain consistency with the checkpoint structure used in the official [h94/IP-Adapter](https://huggingface.co/h94/IP-Adapter) repo.
+
+## InvokeAI Hosted IP-Adapters
+
+Image Encoders:
+- [InvokeAI/ip_adapter_sd_image_encoder](https://huggingface.co/InvokeAI/ip_adapter_sd_image_encoder)
+- [InvokeAI/ip_adapter_sdxl_image_encoder](https://huggingface.co/InvokeAI/ip_adapter_sdxl_image_encoder)
+
+IP-Adapters:
+- [InvokeAI/ip_adapter_sd15](https://huggingface.co/InvokeAI/ip_adapter_sd15)
+- [InvokeAI/ip_adapter_plus_sd15](https://huggingface.co/InvokeAI/ip_adapter_plus_sd15)
+- [InvokeAI/ip_adapter_plus_face_sd15](https://huggingface.co/InvokeAI/ip_adapter_plus_face_sd15)
+- [InvokeAI/ip_adapter_sdxl](https://huggingface.co/InvokeAI/ip_adapter_sdxl)
+- [InvokeAI/ip_adapter_sdxl_vit_h](https://huggingface.co/InvokeAI/ip_adapter_sdxl_vit_h)

invokeai/backend/ip_adapter/attention_processor.py

@@ -0,0 +1,165 @@
+# copied from https://github.com/tencent-ailab/IP-Adapter (Apache License 2.0)
+#   and modified as needed
+
+# tencent-ailab comment:
+# modified from https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from diffusers.models.attention_processor import AttnProcessor2_0 as DiffusersAttnProcessor2_0
+
+from invokeai.backend.ip_adapter.ip_attention_weights import IPAttentionProcessorWeights
+
+
+# Create a version of AttnProcessor2_0 that is a sub-class of nn.Module. This is required for IP-Adapter state_dict
+# loading.
+class AttnProcessor2_0(DiffusersAttnProcessor2_0, nn.Module):
+    def __init__(self):
+        DiffusersAttnProcessor2_0.__init__(self)
+        nn.Module.__init__(self)
+
+    def __call__(
+        self,
+        attn,
+        hidden_states,
+        encoder_hidden_states=None,
+        attention_mask=None,
+        temb=None,
+        ip_adapter_image_prompt_embeds=None,
+    ):
+        """Re-definition of DiffusersAttnProcessor2_0.__call__(...) that accepts and ignores the
+        ip_adapter_image_prompt_embeds parameter.
+        """
+        return DiffusersAttnProcessor2_0.__call__(
+            self, attn, hidden_states, encoder_hidden_states, attention_mask, temb
+        )
+
+
+class IPAttnProcessor2_0(torch.nn.Module):
+    r"""
+    Attention processor for IP-Adapater for PyTorch 2.0.
+    Args:
+        hidden_size (`int`):
+            The hidden size of the attention layer.
+        cross_attention_dim (`int`):
+            The number of channels in the `encoder_hidden_states`.
+        scale (`float`, defaults to 1.0):
+            the weight scale of image prompt.
+    """
+
+    def __init__(self, weights: list[IPAttentionProcessorWeights], scales: list[float]):
+        super().__init__()
+
+        if not hasattr(F, "scaled_dot_product_attention"):
+            raise ImportError("AttnProcessor2_0 requires PyTorch 2.0, to use it, please upgrade PyTorch to 2.0.")
+
+        assert len(weights) == len(scales)
+
+        self._weights = weights
+        self._scales = scales
+
+    def __call__(
+        self,
+        attn,
+        hidden_states,
+        encoder_hidden_states=None,
+        attention_mask=None,
+        temb=None,
+        ip_adapter_image_prompt_embeds=None,
+    ):
+        residual = hidden_states
+
+        if attn.spatial_norm is not None:
+            hidden_states = attn.spatial_norm(hidden_states, temb)
+
+        input_ndim = hidden_states.ndim
+
+        if input_ndim == 4:
+            batch_size, channel, height, width = hidden_states.shape
+            hidden_states = hidden_states.view(batch_size, channel, height * width).transpose(1, 2)
+
+        batch_size, sequence_length, _ = (
+            hidden_states.shape if encoder_hidden_states is None else encoder_hidden_states.shape
+        )
+
+        if attention_mask is not None:
+            attention_mask = attn.prepare_attention_mask(attention_mask, sequence_length, batch_size)
+            # scaled_dot_product_attention expects attention_mask shape to be
+            # (batch, heads, source_length, target_length)
+            attention_mask = attention_mask.view(batch_size, attn.heads, -1, attention_mask.shape[-1])
+
+        if attn.group_norm is not None:
+            hidden_states = attn.group_norm(hidden_states.transpose(1, 2)).transpose(1, 2)
+
+        query = attn.to_q(hidden_states)
+
+        if encoder_hidden_states is None:
+            encoder_hidden_states = hidden_states
+        elif attn.norm_cross:
+            encoder_hidden_states = attn.norm_encoder_hidden_states(encoder_hidden_states)
+
+        key = attn.to_k(encoder_hidden_states)
+        value = attn.to_v(encoder_hidden_states)
+
+        inner_dim = key.shape[-1]
+        head_dim = inner_dim // attn.heads
+
+        query = query.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+
+        key = key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+        value = value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+
+        # the output of sdp = (batch, num_heads, seq_len, head_dim)
+        # TODO: add support for attn.scale when we move to Torch 2.1
+        hidden_states = F.scaled_dot_product_attention(
+            query, key, value, attn_mask=attention_mask, dropout_p=0.0, is_causal=False
+        )
+
+        hidden_states = hidden_states.transpose(1, 2).reshape(batch_size, -1, attn.heads * head_dim)
+        hidden_states = hidden_states.to(query.dtype)
+
+        if encoder_hidden_states is not None:
+            # If encoder_hidden_states is not None, then we are doing cross-attention, not self-attention. In this case,
+            # we will apply IP-Adapter conditioning. We validate the inputs for IP-Adapter conditioning here.
+            assert ip_adapter_image_prompt_embeds is not None
+            assert len(ip_adapter_image_prompt_embeds) == len(self._weights)
+
+            for ipa_embed, ipa_weights, scale in zip(ip_adapter_image_prompt_embeds, self._weights, self._scales):
+                # The batch dimensions should match.
+                assert ipa_embed.shape[0] == encoder_hidden_states.shape[0]
+                # The channel dimensions should match.
+                assert ipa_embed.shape[2] == encoder_hidden_states.shape[2]
+
+                ip_hidden_states = ipa_embed
+
+                ip_key = ipa_weights.to_k_ip(ip_hidden_states)
+                ip_value = ipa_weights.to_v_ip(ip_hidden_states)
+
+                ip_key = ip_key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+                ip_value = ip_value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+
+                # The output of sdpa has shape: (batch, num_heads, seq_len, head_dim)
+                # TODO: add support for attn.scale when we move to Torch 2.1
+                ip_hidden_states = F.scaled_dot_product_attention(
+                    query, ip_key, ip_value, attn_mask=None, dropout_p=0.0, is_causal=False
+                )
+
+                ip_hidden_states = ip_hidden_states.transpose(1, 2).reshape(batch_size, -1, attn.heads * head_dim)
+                ip_hidden_states = ip_hidden_states.to(query.dtype)
+
+                hidden_states = hidden_states + scale * ip_hidden_states
+
+        # linear proj
+        hidden_states = attn.to_out[0](hidden_states)
+        # dropout
+        hidden_states = attn.to_out[1](hidden_states)
+
+        if input_ndim == 4:
+            hidden_states = hidden_states.transpose(-1, -2).reshape(batch_size, channel, height, width)
+
+        if attn.residual_connection:
+            hidden_states = hidden_states + residual
+
+        hidden_states = hidden_states / attn.rescale_output_factor
+
+        return hidden_states

invokeai/backend/ip_adapter/ip_adapter.py

@@ -0,0 +1,167 @@
+# copied from https://github.com/tencent-ailab/IP-Adapter (Apache License 2.0)
+#   and modified as needed
+
+from typing import Optional, Union
+
+import torch
+from PIL import Image
+from transformers import CLIPImageProcessor, CLIPVisionModelWithProjection
+
+from invokeai.backend.ip_adapter.ip_attention_weights import IPAttentionWeights
+from invokeai.backend.model_management.models.base import calc_model_size_by_data
+
+from .resampler import Resampler
+
+
+class ImageProjModel(torch.nn.Module):
+    """Image Projection Model"""
+
+    def __init__(self, cross_attention_dim=1024, clip_embeddings_dim=1024, clip_extra_context_tokens=4):
+        super().__init__()
+
+        self.cross_attention_dim = cross_attention_dim
+        self.clip_extra_context_tokens = clip_extra_context_tokens
+        self.proj = torch.nn.Linear(clip_embeddings_dim, self.clip_extra_context_tokens * cross_attention_dim)
+        self.norm = torch.nn.LayerNorm(cross_attention_dim)
+
+    @classmethod
+    def from_state_dict(cls, state_dict: dict[torch.Tensor], clip_extra_context_tokens=4):
+        """Initialize an ImageProjModel from a state_dict.
+
+        The cross_attention_dim and clip_embeddings_dim are inferred from the shape of the tensors in the state_dict.
+
+        Args:
+            state_dict (dict[torch.Tensor]): The state_dict of model weights.
+            clip_extra_context_tokens (int, optional): Defaults to 4.
+
+        Returns:
+            ImageProjModel
+        """
+        cross_attention_dim = state_dict["norm.weight"].shape[0]
+        clip_embeddings_dim = state_dict["proj.weight"].shape[-1]
+
+        model = cls(cross_attention_dim, clip_embeddings_dim, clip_extra_context_tokens)
+
+        model.load_state_dict(state_dict)
+        return model
+
+    def forward(self, image_embeds):
+        embeds = image_embeds
+        clip_extra_context_tokens = self.proj(embeds).reshape(
+            -1, self.clip_extra_context_tokens, self.cross_attention_dim
+        )
+        clip_extra_context_tokens = self.norm(clip_extra_context_tokens)
+        return clip_extra_context_tokens
+
+
+class IPAdapter:
+    """IP-Adapter: https://arxiv.org/pdf/2308.06721.pdf"""
+
+    def __init__(
+        self,
+        state_dict: dict[str, torch.Tensor],
+        device: torch.device,
+        dtype: torch.dtype = torch.float16,
+        num_tokens: int = 4,
+    ):
+        self.device = device
+        self.dtype = dtype
+
+        self._num_tokens = num_tokens
+
+        self._clip_image_processor = CLIPImageProcessor()
+
+        self._image_proj_model = self._init_image_proj_model(state_dict["image_proj"])
+
+        self.attn_weights = IPAttentionWeights.from_state_dict(state_dict["ip_adapter"]).to(
+            self.device, dtype=self.dtype
+        )
+
+    def to(self, device: torch.device, dtype: Optional[torch.dtype] = None):
+        self.device = device
+        if dtype is not None:
+            self.dtype = dtype
+
+        self._image_proj_model.to(device=self.device, dtype=self.dtype)
+        self.attn_weights.to(device=self.device, dtype=self.dtype)
+
+    def calc_size(self):
+        return calc_model_size_by_data(self._image_proj_model) + calc_model_size_by_data(self.attn_weights)
+
+    def _init_image_proj_model(self, state_dict):
+        return ImageProjModel.from_state_dict(state_dict, self._num_tokens).to(self.device, dtype=self.dtype)
+
+    @torch.inference_mode()
+    def get_image_embeds(self, pil_image, image_encoder: CLIPVisionModelWithProjection):
+        if isinstance(pil_image, Image.Image):
+            pil_image = [pil_image]
+        clip_image = self._clip_image_processor(images=pil_image, return_tensors="pt").pixel_values
+        clip_image_embeds = image_encoder(clip_image.to(self.device, dtype=self.dtype)).image_embeds
+        image_prompt_embeds = self._image_proj_model(clip_image_embeds)
+        uncond_image_prompt_embeds = self._image_proj_model(torch.zeros_like(clip_image_embeds))
+        return image_prompt_embeds, uncond_image_prompt_embeds
+
+
+class IPAdapterPlus(IPAdapter):
+    """IP-Adapter with fine-grained features"""
+
+    def _init_image_proj_model(self, state_dict):
+        return Resampler.from_state_dict(
+            state_dict=state_dict,
+            depth=4,
+            dim_head=64,
+            heads=12,
+            num_queries=self._num_tokens,
+            ff_mult=4,
+        ).to(self.device, dtype=self.dtype)
+
+    @torch.inference_mode()
+    def get_image_embeds(self, pil_image, image_encoder: CLIPVisionModelWithProjection):
+        if isinstance(pil_image, Image.Image):
+            pil_image = [pil_image]
+        clip_image = self._clip_image_processor(images=pil_image, return_tensors="pt").pixel_values
+        clip_image = clip_image.to(self.device, dtype=self.dtype)
+        clip_image_embeds = image_encoder(clip_image, output_hidden_states=True).hidden_states[-2]
+        image_prompt_embeds = self._image_proj_model(clip_image_embeds)
+        uncond_clip_image_embeds = image_encoder(torch.zeros_like(clip_image), output_hidden_states=True).hidden_states[
+            -2
+        ]
+        uncond_image_prompt_embeds = self._image_proj_model(uncond_clip_image_embeds)
+        return image_prompt_embeds, uncond_image_prompt_embeds
+
+
+class IPAdapterPlusXL(IPAdapterPlus):
+    """IP-Adapter Plus for SDXL."""
+
+    def _init_image_proj_model(self, state_dict):
+        return Resampler.from_state_dict(
+            state_dict=state_dict,
+            depth=4,
+            dim_head=64,
+            heads=20,
+            num_queries=self._num_tokens,
+            ff_mult=4,
+        ).to(self.device, dtype=self.dtype)
+
+
+def build_ip_adapter(
+    ip_adapter_ckpt_path: str, device: torch.device, dtype: torch.dtype = torch.float16
+) -> Union[IPAdapter, IPAdapterPlus]:
+    state_dict = torch.load(ip_adapter_ckpt_path, map_location="cpu")
+
+    # Determine if the state_dict is from an IPAdapter or IPAdapterPlus based on the image_proj weights that it
+    # contains.
+    is_plus = "proj.weight" not in state_dict["image_proj"]
+
+    if is_plus:
+        cross_attention_dim = state_dict["ip_adapter"]["1.to_k_ip.weight"].shape[-1]
+        if cross_attention_dim == 768:
+            # SD1 IP-Adapter Plus
+            return IPAdapterPlus(state_dict, device=device, dtype=dtype)
+        elif cross_attention_dim == 2048:
+            # SDXL IP-Adapter Plus
+            return IPAdapterPlusXL(state_dict, device=device, dtype=dtype)
+        else:
+            raise Exception(f"Unsupported IP-Adapter Plus cross-attention dimension: {cross_attention_dim}.")
+    else:
+        return IPAdapter(state_dict, device=device, dtype=dtype)

invokeai/backend/ip_adapter/ip_attention_weights.py

@@ -0,0 +1,46 @@
+import torch
+
+
+class IPAttentionProcessorWeights(torch.nn.Module):
+    """The IP-Adapter weights for a single attention processor.
+
+    This class is a torch.nn.Module sub-class to facilitate loading from a state_dict. It does not have a forward(...)
+    method.
+    """
+
+    def __init__(self, in_dim: int, out_dim: int):
+        super().__init__()
+        self.to_k_ip = torch.nn.Linear(in_dim, out_dim, bias=False)
+        self.to_v_ip = torch.nn.Linear(in_dim, out_dim, bias=False)
+
+
+class IPAttentionWeights(torch.nn.Module):
+    """A collection of all the `IPAttentionProcessorWeights` objects for an IP-Adapter model.
+
+    This class is a torch.nn.Module sub-class so that it inherits the `.to(...)` functionality. It does not have a
+    forward(...) method.
+    """
+
+    def __init__(self, weights: torch.nn.ModuleDict):
+        super().__init__()
+        self._weights = weights
+
+    def get_attention_processor_weights(self, idx: int) -> IPAttentionProcessorWeights:
+        """Get the `IPAttentionProcessorWeights` for the idx'th attention processor."""
+        # Cast to int first, because we expect the key to represent an int. Then cast back to str, because
+        # `torch.nn.ModuleDict` only supports str keys.
+        return self._weights[str(int(idx))]
+
+    @classmethod
+    def from_state_dict(cls, state_dict: dict[str, torch.Tensor]):
+        attn_proc_weights: dict[str, IPAttentionProcessorWeights] = {}
+
+        for tensor_name, tensor in state_dict.items():
+            if "to_k_ip.weight" in tensor_name:
+                index = str(int(tensor_name.split(".")[0]))
+                attn_proc_weights[index] = IPAttentionProcessorWeights(tensor.shape[1], tensor.shape[0])
+
+        attn_proc_weights_module = torch.nn.ModuleDict(attn_proc_weights)
+        attn_proc_weights_module.load_state_dict(state_dict)
+
+        return cls(attn_proc_weights_module)

invokeai/backend/ip_adapter/resampler.py

@@ -0,0 +1,158 @@
+# copied from https://github.com/tencent-ailab/IP-Adapter (Apache License 2.0)
+
+# tencent ailab comment: modified from
+# https://github.com/mlfoundations/open_flamingo/blob/main/open_flamingo/src/helpers.py
+import math
+
+import torch
+import torch.nn as nn
+
+
+# FFN
+def FeedForward(dim, mult=4):
+    inner_dim = int(dim * mult)
+    return nn.Sequential(
+        nn.LayerNorm(dim),
+        nn.Linear(dim, inner_dim, bias=False),
+        nn.GELU(),
+        nn.Linear(inner_dim, dim, bias=False),
+    )
+
+
+def reshape_tensor(x, heads):
+    bs, length, width = x.shape
+    # (bs, length, width) --> (bs, length, n_heads, dim_per_head)
+    x = x.view(bs, length, heads, -1)
+    # (bs, length, n_heads, dim_per_head) --> (bs, n_heads, length, dim_per_head)
+    x = x.transpose(1, 2)
+    # (bs, n_heads, length, dim_per_head) --> (bs*n_heads, length, dim_per_head)
+    x = x.reshape(bs, heads, length, -1)
+    return x
+
+
+class PerceiverAttention(nn.Module):
+    def __init__(self, *, dim, dim_head=64, heads=8):
+        super().__init__()
+        self.scale = dim_head**-0.5
+        self.dim_head = dim_head
+        self.heads = heads
+        inner_dim = dim_head * heads
+
+        self.norm1 = nn.LayerNorm(dim)
+        self.norm2 = nn.LayerNorm(dim)
+
+        self.to_q = nn.Linear(dim, inner_dim, bias=False)
+        self.to_kv = nn.Linear(dim, inner_dim * 2, bias=False)
+        self.to_out = nn.Linear(inner_dim, dim, bias=False)
+
+    def forward(self, x, latents):
+        """
+        Args:
+            x (torch.Tensor): image features
+                shape (b, n1, D)
+            latent (torch.Tensor): latent features
+                shape (b, n2, D)
+        """
+        x = self.norm1(x)
+        latents = self.norm2(latents)
+
+        b, l, _ = latents.shape
+
+        q = self.to_q(latents)
+        kv_input = torch.cat((x, latents), dim=-2)
+        k, v = self.to_kv(kv_input).chunk(2, dim=-1)
+
+        q = reshape_tensor(q, self.heads)
+        k = reshape_tensor(k, self.heads)
+        v = reshape_tensor(v, self.heads)
+
+        # attention
+        scale = 1 / math.sqrt(math.sqrt(self.dim_head))
+        weight = (q * scale) @ (k * scale).transpose(-2, -1)  # More stable with f16 than dividing afterwards
+        weight = torch.softmax(weight.float(), dim=-1).type(weight.dtype)
+        out = weight @ v
+
+        out = out.permute(0, 2, 1, 3).reshape(b, l, -1)
+
+        return self.to_out(out)
+
+
+class Resampler(nn.Module):
+    def __init__(
+        self,
+        dim=1024,
+        depth=8,
+        dim_head=64,
+        heads=16,
+        num_queries=8,
+        embedding_dim=768,
+        output_dim=1024,
+        ff_mult=4,
+    ):
+        super().__init__()
+
+        self.latents = nn.Parameter(torch.randn(1, num_queries, dim) / dim**0.5)
+
+        self.proj_in = nn.Linear(embedding_dim, dim)
+
+        self.proj_out = nn.Linear(dim, output_dim)
+        self.norm_out = nn.LayerNorm(output_dim)
+
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(
+                nn.ModuleList(
+                    [
+                        PerceiverAttention(dim=dim, dim_head=dim_head, heads=heads),
+                        FeedForward(dim=dim, mult=ff_mult),
+                    ]
+                )
+            )
+
+    @classmethod
+    def from_state_dict(cls, state_dict: dict[torch.Tensor], depth=8, dim_head=64, heads=16, num_queries=8, ff_mult=4):
+        """A convenience function that initializes a Resampler from a state_dict.
+
+        Some of the shape parameters are inferred from the state_dict (e.g. dim, embedding_dim, etc.). At the time of
+        writing, we did not have a need for inferring ALL of the shape parameters from the state_dict, but this would be
+        possible if needed in the future.
+
+        Args:
+            state_dict (dict[torch.Tensor]): The state_dict to load.
+            depth (int, optional):
+            dim_head (int, optional):
+            heads (int, optional):
+            ff_mult (int, optional):
+
+        Returns:
+            Resampler
+        """
+        dim = state_dict["latents"].shape[2]
+        num_queries = state_dict["latents"].shape[1]
+        embedding_dim = state_dict["proj_in.weight"].shape[-1]
+        output_dim = state_dict["norm_out.weight"].shape[0]
+
+        model = cls(
+            dim=dim,
+            depth=depth,
+            dim_head=dim_head,
+            heads=heads,
+            num_queries=num_queries,
+            embedding_dim=embedding_dim,
+            output_dim=output_dim,
+            ff_mult=ff_mult,
+        )
+        model.load_state_dict(state_dict)
+        return model
+
+    def forward(self, x):
+        latents = self.latents.repeat(x.size(0), 1, 1)
+
+        x = self.proj_in(x)
+
+        for attn, ff in self.layers:
+            latents = attn(x, latents) + latents
+            latents = ff(latents) + latents
+
+        latents = self.proj_out(latents)
+        return self.norm_out(latents)

invokeai/backend/ip_adapter/unet_patcher.py

@@ -0,0 +1,53 @@
+from contextlib import contextmanager
+
+from diffusers.models import UNet2DConditionModel
+
+from invokeai.backend.ip_adapter.attention_processor import AttnProcessor2_0, IPAttnProcessor2_0
+from invokeai.backend.ip_adapter.ip_adapter import IPAdapter
+
+
+class UNetPatcher:
+    """A class that contains multiple IP-Adapters and can apply them to a UNet."""
+
+    def __init__(self, ip_adapters: list[IPAdapter]):
+        self._ip_adapters = ip_adapters
+        self._scales = [1.0] * len(self._ip_adapters)
+
+    def set_scale(self, idx: int, value: float):
+        self._scales[idx] = value
+
+    def _prepare_attention_processors(self, unet: UNet2DConditionModel):
+        """Prepare a dict of attention processors that can be injected into a unet, and load the IP-Adapter attention
+        weights into them.
+
+        Note that the `unet` param is only used to determine attention block dimensions and naming.
+        """
+        # Construct a dict of attention processors based on the UNet's architecture.
+        attn_procs = {}
+        for idx, name in enumerate(unet.attn_processors.keys()):
+            if name.endswith("attn1.processor"):
+                attn_procs[name] = AttnProcessor2_0()
+            else:
+                # Collect the weights from each IP Adapter for the idx'th attention processor.
+                attn_procs[name] = IPAttnProcessor2_0(
+                    [ip_adapter.attn_weights.get_attention_processor_weights(idx) for ip_adapter in self._ip_adapters],
+                    self._scales,
+                )
+        return attn_procs
+
+    @contextmanager
+    def apply_ip_adapter_attention(self, unet: UNet2DConditionModel):
+        """A context manager that patches `unet` with IP-Adapter attention processors."""
+
+        attn_procs = self._prepare_attention_processors(unet)
+
+        orig_attn_processors = unet.attn_processors
+
+        try:
+            # Note to future devs: set_attn_processor(...) does something slightly unexpected - it pops elements from the
+            # passed dict. So, if you wanted to keep the dict for future use, you'd have to make a moderately-shallow copy
+            # of it. E.g. `attn_procs_copy = {k: v for k, v in attn_procs.items()}`.
+            unet.set_attn_processor(attn_procs)
+            yield None
+        finally:
+            unet.set_attn_processor(orig_attn_processors)

invokeai/backend/model_management/README.md

@@ -0,0 +1,27 @@
+# Model Cache
+
+## `glibc` Memory Allocator Fragmentation
+
+Python (and PyTorch) relies on the memory allocator from the C Standard Library (`libc`). On linux, with the GNU C Standard Library implementation (`glibc`), our memory access patterns have been observed to cause severe memory fragmentation. This fragmentation results in large amounts of memory that has been freed but can't be released back to the OS. Loading models from disk and moving them between CPU/CUDA seem to be the operations that contribute most to the fragmentation. This memory fragmentation issue can result in OOM crashes during frequent model switching, even if `max_cache_size` is set to a reasonable value (e.g. a OOM crash with `max_cache_size=16` on a system with 32GB of RAM).
+
+This problem may also exist on other OSes, and other `libc` implementations. But, at the time of writing, it has only been investigated on linux with `glibc`.
+
+To better understand how the `glibc` memory allocator works, see these references:
+- Basics: https://www.gnu.org/software/libc/manual/html_node/The-GNU-Allocator.html
+- Details: https://sourceware.org/glibc/wiki/MallocInternals
+
+Note the differences between memory allocated as chunks in an arena vs. memory allocated with `mmap`. Under `glibc`'s default configuration, most model tensors get allocated as chunks in an arena making them vulnerable to the problem of fragmentation.
+
+We can work around this memory fragmentation issue by setting the following env var:
+
+```bash
+# Force blocks >1MB to be allocated with `mmap` so that they are released to the system immediately when they are freed.
+MALLOC_MMAP_THRESHOLD_=1048576
+```
+
+See the following references for more information about the `malloc` tunable parameters:
+- https://www.gnu.org/software/libc/manual/html_node/Malloc-Tunable-Parameters.html
+- https://www.gnu.org/software/libc/manual/html_node/Memory-Allocation-Tunables.html
+- https://man7.org/linux/man-pages/man3/mallopt.3.html
+
+The model cache emits debug logs that provide visibility into the state of the `libc` memory allocator. See the `LibcUtil` class for more info on how these `libc` malloc stats are collected.

invokeai/backend/model_management/convert_ckpt_to_diffusers.py

@@ -74,7 +74,7 @@ if is_accelerate_available():
     from accelerate import init_empty_weights
     from accelerate.utils import set_module_tensor_to_device
 
-logger = InvokeAILogger.getLogger(__name__)
+logger = InvokeAILogger.get_logger(__name__)
 CONVERT_MODEL_ROOT = InvokeAIAppConfig.get_config().models_path / "core/convert"
 
 
@@ -1279,12 +1279,12 @@ def download_from_original_stable_diffusion_ckpt(
         extract_ema = original_config["model"]["params"]["use_ema"]
 
     if (
-        model_version == BaseModelType.StableDiffusion2
+        model_version in [BaseModelType.StableDiffusion2, BaseModelType.StableDiffusion1]
         and original_config["model"]["params"].get("parameterization") == "v"
     ):
         prediction_type = "v_prediction"
         upcast_attention = True
-        image_size = 768
+        image_size = 768 if model_version == BaseModelType.StableDiffusion2 else 512
     else:
         prediction_type = "epsilon"
         upcast_attention = False

invokeai/backend/model_management/libc_util.py

@@ -0,0 +1,75 @@
+import ctypes
+
+
+class Struct_mallinfo2(ctypes.Structure):
+    """A ctypes Structure that matches the libc mallinfo2 struct.
+
+    Docs:
+    - https://man7.org/linux/man-pages/man3/mallinfo.3.html
+    - https://www.gnu.org/software/libc/manual/html_node/Statistics-of-Malloc.html
+
+    struct mallinfo2 {
+        size_t arena;     /* Non-mmapped space allocated (bytes) */
+        size_t ordblks;   /* Number of free chunks */
+        size_t smblks;    /* Number of free fastbin blocks */
+        size_t hblks;     /* Number of mmapped regions */
+        size_t hblkhd;    /* Space allocated in mmapped regions (bytes) */
+        size_t usmblks;   /* See below */
+        size_t fsmblks;   /* Space in freed fastbin blocks (bytes) */
+        size_t uordblks;  /* Total allocated space (bytes) */
+        size_t fordblks;  /* Total free space (bytes) */
+        size_t keepcost;  /* Top-most, releasable space (bytes) */
+    };
+    """
+
+    _fields_ = [
+        ("arena", ctypes.c_size_t),
+        ("ordblks", ctypes.c_size_t),
+        ("smblks", ctypes.c_size_t),
+        ("hblks", ctypes.c_size_t),
+        ("hblkhd", ctypes.c_size_t),
+        ("usmblks", ctypes.c_size_t),
+        ("fsmblks", ctypes.c_size_t),
+        ("uordblks", ctypes.c_size_t),
+        ("fordblks", ctypes.c_size_t),
+        ("keepcost", ctypes.c_size_t),
+    ]
+
+    def __str__(self):
+        s = ""
+        s += f"{'arena': <10}= {(self.arena/2**30):15.5f}   # Non-mmapped space allocated (GB) (uordblks + fordblks)\n"
+        s += f"{'ordblks': <10}= {(self.ordblks): >15}   # Number of free chunks\n"
+        s += f"{'smblks': <10}= {(self.smblks): >15}   # Number of free fastbin blocks \n"
+        s += f"{'hblks': <10}= {(self.hblks): >15}   # Number of mmapped regions \n"
+        s += f"{'hblkhd': <10}= {(self.hblkhd/2**30):15.5f}   # Space allocated in mmapped regions (GB)\n"
+        s += f"{'usmblks': <10}= {(self.usmblks): >15}   # Unused\n"
+        s += f"{'fsmblks': <10}= {(self.fsmblks/2**30):15.5f}   # Space in freed fastbin blocks (GB)\n"
+        s += (
+            f"{'uordblks': <10}= {(self.uordblks/2**30):15.5f}   # Space used by in-use allocations (non-mmapped)"
+            " (GB)\n"
+        )
+        s += f"{'fordblks': <10}= {(self.fordblks/2**30):15.5f}   # Space in free blocks (non-mmapped) (GB)\n"
+        s += f"{'keepcost': <10}= {(self.keepcost/2**30):15.5f}   # Top-most, releasable space (GB)\n"
+        return s
+
+
+class LibcUtil:
+    """A utility class for interacting with the C Standard Library (`libc`) via ctypes.
+
+    Note that this class will raise on __init__() if 'libc.so.6' can't be found. Take care to handle environments where
+    this shared library is not available.
+
+    TODO: Improve cross-OS compatibility of this class.
+    """
+
+    def __init__(self):
+        self._libc = ctypes.cdll.LoadLibrary("libc.so.6")
+
+    def mallinfo2(self) -> Struct_mallinfo2:
+        """Calls `libc` `mallinfo2`.
+
+        Docs: https://man7.org/linux/man-pages/man3/mallinfo.3.html
+        """
+        mallinfo2 = self._libc.mallinfo2
+        mallinfo2.restype = Struct_mallinfo2
+        return mallinfo2()

invokeai/backend/model_management/memory_snapshot.py

@@ -0,0 +1,96 @@
+import gc
+from typing import Optional
+
+import psutil
+import torch
+
+from invokeai.backend.model_management.libc_util import LibcUtil, Struct_mallinfo2
+
+GB = 2**30  # 1 GB
+
+
+class MemorySnapshot:
+    """A snapshot of RAM and VRAM usage. All values are in bytes."""
+
+    def __init__(self, process_ram: int, vram: Optional[int], malloc_info: Optional[Struct_mallinfo2]):
+        """Initialize a MemorySnapshot.
+
+        Most of the time, `MemorySnapshot` will be constructed with `MemorySnapshot.capture()`.
+
+        Args:
+            process_ram (int): CPU RAM used by the current process.
+            vram (Optional[int]): VRAM used by torch.
+            malloc_info (Optional[Struct_mallinfo2]): Malloc info obtained from LibcUtil.
+        """
+        self.process_ram = process_ram
+        self.vram = vram
+        self.malloc_info = malloc_info
+
+    @classmethod
+    def capture(cls, run_garbage_collector: bool = True):
+        """Capture and return a MemorySnapshot.
+
+        Note: This function has significant overhead, particularly if `run_garbage_collector == True`.
+
+        Args:
+            run_garbage_collector (bool, optional): If true, gc.collect() will be run before checking the process RAM
+                usage. Defaults to True.
+
+        Returns:
+            MemorySnapshot
+        """
+        if run_garbage_collector:
+            gc.collect()
+
+        # According to the psutil docs (https://psutil.readthedocs.io/en/latest/#psutil.Process.memory_info), rss is
+        # supported on all platforms.
+        process_ram = psutil.Process().memory_info().rss
+
+        if torch.cuda.is_available():
+            vram = torch.cuda.memory_allocated()
+        else:
+            # TODO: We could add support for mps.current_allocated_memory() as well. Leaving out for now until we have
+            # time to test it properly.
+            vram = None
+
+        try:
+            malloc_info = LibcUtil().mallinfo2()
+        except (OSError, AttributeError):
+            # OSError: This is expected in environments that do not have the 'libc.so.6' shared library.
+            # AttributeError: This is expected in environments that have `libc.so.6` but do not have the `mallinfo2` (e.g. glibc < 2.33)
+            # TODO: Does `mallinfo` work?
+            malloc_info = None
+
+        return cls(process_ram, vram, malloc_info)
+
+
+def get_pretty_snapshot_diff(snapshot_1: MemorySnapshot, snapshot_2: MemorySnapshot) -> str:
+    """Get a pretty string describing the difference between two `MemorySnapshot`s."""
+
+    def get_msg_line(prefix: str, val1: int, val2: int):
+        diff = val2 - val1
+        return f"{prefix: <30} ({(diff/GB):+5.3f}): {(val1/GB):5.3f}GB -> {(val2/GB):5.3f}GB\n"
+
+    msg = ""
+
+    msg += get_msg_line("Process RAM", snapshot_1.process_ram, snapshot_2.process_ram)
+
+    if snapshot_1.malloc_info is not None and snapshot_2.malloc_info is not None:
+        msg += get_msg_line("libc mmap allocated", snapshot_1.malloc_info.hblkhd, snapshot_2.malloc_info.hblkhd)
+
+        msg += get_msg_line("libc arena used", snapshot_1.malloc_info.uordblks, snapshot_2.malloc_info.uordblks)
+
+        msg += get_msg_line("libc arena free", snapshot_1.malloc_info.fordblks, snapshot_2.malloc_info.fordblks)
+
+        libc_total_allocated_1 = snapshot_1.malloc_info.arena + snapshot_1.malloc_info.hblkhd
+        libc_total_allocated_2 = snapshot_2.malloc_info.arena + snapshot_2.malloc_info.hblkhd
+        msg += get_msg_line("libc total allocated", libc_total_allocated_1, libc_total_allocated_2)
+
+        libc_total_used_1 = snapshot_1.malloc_info.uordblks + snapshot_1.malloc_info.hblkhd
+        libc_total_used_2 = snapshot_2.malloc_info.uordblks + snapshot_2.malloc_info.hblkhd
+        msg += get_msg_line("libc total used", libc_total_used_1, libc_total_used_2)
+
+    if snapshot_1.vram is not None and snapshot_2.vram is not None:
+        msg += get_msg_line("VRAM", snapshot_1.vram, snapshot_2.vram)
+
+    return msg