webgui working again

- squashed commit of 52 commits from PR #1327

don't log base64 progress images

Fresh Build For WebUI

[WebUI] Loopback Default False

Fixes bugs/styling

- Fixes missing web app state on new version:
Adds stateReconciler to redux-persist.

When we add more values to the state and then release the update app, they will be automatically merged in.

Reseting web UI will be needed far less.
7159ec

- Fixes console z-index
- Moves reset web UI button to visible area

Decreases gallery width on inpainting

Increases workarea split padding to 1rem

Adds missing tooltips to site header

Changes inpainting controls settings to hover

Fixes hotkeys and settings buttons not working

Improves bounding box interactions

- Bounding box can now be moved by dragging any of its edges
- Bounding box does not affect drawing if already drawing a stroke
- Can lock bounding box to draw directly on the bounding box edges
- Removes spacebar-hold behaviour due to technical issues

Fixes silent crash when init image too large

To send the mask to the server, the UI rendered the mask onto the init image and sent the whole image. The mask was then cropped by the server.

If the image was too large, the app silently failed. Maybe it exceeds the websocket size limit.

Fixed by cropping the mask in the UI layer, sending only bounding-box-sized mask image data.

Disabled bounding box settings when locked

Styles image uploader

Builds fresh bundle

Improves bounding box interaction

Added spacebar-hold-to-transform back.

Address bounding box feedback

- Adds back toggle to hide bounding box
- Box quick toggle = q, normal toggle = shift + q
- Styles canvas alert icons

Adds hints when unable to invoke

- Popover on Invoke button indicates why exactly it is disabled, e.g. prompt is empty, something else is processing, etc.
- There may be more than one reason; all are displayed.

Fix Inpainting Alerts Styling

Preventing unnecessary re-renders across the app

Code Split Inpaint Options

Isolate features to their own components so they dont re-render the other stuff each time.

[TESTING] Remove  global isReady checking

I dont believe this is need at all because the isready state is constantly updated when needed and tracked real time in the Redux store. This causes massive re-renders. @psychedelicious If this is absolutely essential for a reason that I do not see, please hit me up on Discord.

Fresh Bundle

Fix Bounding Box Settings re-rendering on brush stroke

[Code Splitting] Bounding Box Options

Isolated all bounding box components to trigger unnecessary re-renders. Still need to fix  bounding box  triggering re-renders on the control panel inside the canvas itself. But the options panel should be a good to go with this change.

Inpainting Controls Code Spitting and Performance

Codesplit the entirety of the inpainting controls. Created new selectors for each and every component to ensure there are no unnecessary re-renders. App feels a lot smoother.

Fixes rerenders on ClearBrushHistory

Fixes crash when requesting post-generation upscale/face restoration

- Moves the inpainting paste to before the postprocessing.

Removes unused isReady state

Changes Report Bug icon to a bug

Restores shift+q bounding box shortcut

Adds alert for bounding box size to status icons

Adds asCheckbox to IAIIconButton

Rough draft of this. Not happy with the styling but it's clearer than having them look just like buttons.

Fixes crash related to old value of progress_latents in state

Styling changes and settings modal minor refactor

Fixes: uploaded JPG images not loading

Reworks CurrentImageButtons.tsx

- Change all icons to FA iconset for consistency
- Refactors IAIIconButton, IAIButton, IAIPopover to handle ref forwarding
- Redesigns buttons into group

Only generate 1 iteration when seed fixed & variations disabled

Fixes progress images select

Fixes edge case: upload over gets stuck while alt tabbing

- Press esc to close it now

Fixes display progress images select typing

Fixes current image button rerenders

Adds min width to ImageUploader

Makes fast-latents in progress default

Update Icon Button Checkbox Style Styling

Fixes next/prev image buttons

Refactor canvas buttons + more

Add Save Intermediates Step Count

For accurate mode only.

Co-Authored-By: Richard Macarthy <richardmacarthy@protonmail.com>

Restores "initial image" text

Address feedback

- moves mask clear button
- fixes intermediates
- shrinks inpainting icons by 10%

Fix Loopback Styling

Adds escape hotkey to close floating panels

Readd Hotkey for Dual Display

Updated Current Image Button Styling

.dockerignore

@@ -0,0 +1,3 @@
+*
+!environment*.yml
+!docker-build

.github/workflows/build-container.yml

@@ -0,0 +1,42 @@
+# Building the Image without pushing to confirm it is still buildable
+# confirum functionality would unfortunately need way more resources
+name: build container image
+on:
+  push:
+    branches:
+      - 'main'
+      - 'development'
+  pull_request:
+    branches:
+      - 'main'
+      - 'development'
+
+jobs:
+  docker:
+    runs-on: ubuntu-latest
+    steps:
+      - name: prepare docker-tag
+        env:
+          repository: ${{ github.repository }}
+        run: echo "dockertag=${repository,,}" >> $GITHUB_ENV
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+      - name: Cache Docker layers
+        uses: actions/cache@v2
+        with:
+          path: /tmp/.buildx-cache
+          key: buildx-${{ hashFiles('docker-build/Dockerfile') }}
+      - name: Build container
+        uses: docker/build-push-action@v3
+        with:
+          context: .
+          file: docker-build/Dockerfile
+          platforms: linux/amd64
+          push: false
+          tags: ${{ env.dockertag }}:latest
+          cache-from: type=local,src=/tmp/.buildx-cache
+          cache-to: type=local,dest=/tmp/.buildx-cache

.github/workflows/create-caches.yml

@@ -1,26 +1,43 @@
 name: Create Caches
-on:
-  workflow_dispatch
+
+on: workflow_dispatch
+
 jobs:
-  build:
+  os_matrix:
     strategy:
       matrix:
-        os: [ ubuntu-latest, macos-12 ]
-    name: Create Caches on ${{ matrix.os }} conda
+        os: [ubuntu-latest, macos-latest]
+        include:
+          - os: ubuntu-latest
+            environment-file: environment.yml
+            default-shell: bash -l {0}
+          - os: macos-latest
+            environment-file: environment-mac.yml
+            default-shell: bash -l {0}
+    name: Test invoke.py on ${{ matrix.os }} with conda
     runs-on: ${{ matrix.os }}
+    defaults:
+      run:
+        shell: ${{ matrix.default-shell }}
     steps:
-      - name: Set platform variables
-        id: vars
-        run: |
-            if [ "$RUNNER_OS" = "macOS" ]; then
-                echo "::set-output name=ENV_FILE::environment-mac.yml"
-                echo "::set-output name=PYTHON_BIN::/usr/local/miniconda/envs/ldm/bin/python"
-            elif [ "$RUNNER_OS" = "Linux" ]; then
-                echo "::set-output name=ENV_FILE::environment.yml"
-                echo "::set-output name=PYTHON_BIN::/usr/share/miniconda/envs/ldm/bin/python"
-            fi
       - name: Checkout sources
         uses: actions/checkout@v3
+
+      - name: setup miniconda
+        uses: conda-incubator/setup-miniconda@v2
+        with:
+          auto-activate-base: false
+          auto-update-conda: false
+          miniconda-version: latest
+
+      - name: set environment
+        run: |
+          [[ "$GITHUB_REF" == 'refs/heads/main' ]] \
+            && echo "TEST_PROMPTS=tests/preflight_prompts.txt" >> $GITHUB_ENV \
+            || echo "TEST_PROMPTS=tests/dev_prompts.txt" >> $GITHUB_ENV
+          echo "CONDA_ROOT=$CONDA" >> $GITHUB_ENV
+          echo "CONDA_ENV_NAME=invokeai" >> $GITHUB_ENV
+
       - name: Use Cached Stable Diffusion v1.4 Model
         id: cache-sd-v1-4
         uses: actions/cache@v3
@@ -29,42 +46,35 @@ jobs:
         with:
           path: models/ldm/stable-diffusion-v1/model.ckpt
           key: ${{ env.cache-name }}
-          restore-keys: |
-            ${{ env.cache-name }}
+          restore-keys: ${{ env.cache-name }}
+
       - name: Download Stable Diffusion v1.4 Model
         if: ${{ steps.cache-sd-v1-4.outputs.cache-hit != 'true' }}
         run: |
-          if [ ! -e models/ldm/stable-diffusion-v1 ]; then
-              mkdir -p models/ldm/stable-diffusion-v1
-          fi
-          if [ ! -e models/ldm/stable-diffusion-v1/model.ckpt ]; then
-            curl -o models/ldm/stable-diffusion-v1/model.ckpt ${{ secrets.SD_V1_4_URL }}
-          fi
-      - name: Use Cached Dependencies
-        id: cache-conda-env-ldm
-        uses: actions/cache@v3
-        env:
-          cache-name: cache-conda-env-ldm
+          [[ -d models/ldm/stable-diffusion-v1 ]] \
+            || mkdir -p models/ldm/stable-diffusion-v1
+          [[ -r models/ldm/stable-diffusion-v1/model.ckpt ]] \
+            || curl \
+              -H "Authorization: Bearer ${{ secrets.HUGGINGFACE_TOKEN }}" \
+              -o models/ldm/stable-diffusion-v1/model.ckpt \
+              -L https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt
+
+      - name: Activate Conda Env
+        uses: conda-incubator/setup-miniconda@v2
         with:
-          path: ~/.conda/envs/ldm
-          key: ${{ env.cache-name }}
-          restore-keys: |
-            ${{ env.cache-name }}-${{ runner.os }}-${{ hashFiles(steps.vars.outputs.ENV_FILE) }}
-      - name: Install Dependencies
-        if: ${{ steps.cache-conda-env-ldm.outputs.cache-hit != 'true' }}
-        run: |
-          conda env create -f ${{ steps.vars.outputs.ENV_FILE }}
+          activate-environment: ${{ env.CONDA_ENV_NAME }}
+          environment-file: ${{ matrix.environment-file }}
+
       - name: Use Cached Huggingface and Torch models
-        id: cache-huggingface-torch
+        id: cache-hugginface-torch
         uses: actions/cache@v3
         env:
-          cache-name: cache-huggingface-torch
+          cache-name: cache-hugginface-torch
         with:
           path: ~/.cache
           key: ${{ env.cache-name }}
           restore-keys: |
             ${{ env.cache-name }}-${{ hashFiles('scripts/preload_models.py') }}
-      - name: Download Huggingface and Torch models
-        if: ${{ steps.cache-huggingface-torch.outputs.cache-hit != 'true' }}
-        run: |
-          ${{ steps.vars.outputs.PYTHON_BIN }} scripts/preload_models.py
+
+      - name: run preload_models.py
+        run: python scripts/preload_models.py

.github/workflows/mkdocs-material.yml

@@ -0,0 +1,40 @@
+name: mkdocs-material
+on:
+  push:
+    branches:
+      - 'main'
+      - 'development'
+
+jobs:
+  mkdocs-material:
+    runs-on: ubuntu-latest
+    steps:
+      - name: checkout sources
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: setup python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+
+      - name: install requirements
+        run: |
+          python -m \
+            pip install -r requirements-mkdocs.txt
+
+      - name: confirm buildability
+        run: |
+          python -m \
+            mkdocs build \
+            --clean \
+            --verbose
+
+      - name: deploy to gh-pages
+        if: ${{ github.ref == 'refs/heads/main' }}
+        run: |
+          python -m \
+            mkdocs gh-deploy \
+            --clean \
+            --force

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

@@ -1,97 +1,112 @@
-name: Test Invoke with Conda
+name: Test invoke.py
 on:
   push:
     branches:
       - 'main'
       - 'development'
+  pull_request:
+    branches:
+      - 'main'
+      - 'development'
+
 jobs:
-  os_matrix:
+  matrix:
     strategy:
+      fail-fast: false
       matrix:
-        os: [ ubuntu-latest, macos-12 ]
-    name: Test invoke.py on ${{ matrix.os }} with conda
+        stable-diffusion-model:
+          # - 'https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt'
+          - 'https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt'
+        os:
+          - ubuntu-latest
+          - macOS-12
+        include:
+          - os: ubuntu-latest
+            environment-file: environment.yml
+            default-shell: bash -l {0}
+          - os: macOS-12
+            environment-file: environment-mac.yml
+            default-shell: bash -l {0}
+          # - stable-diffusion-model: https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt
+          #   stable-diffusion-model-dl-path: models/ldm/stable-diffusion-v1/sd-v1-4.ckpt
+          #   stable-diffusion-model-switch: stable-diffusion-1.4
+          - stable-diffusion-model: https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt
+            stable-diffusion-model-dl-path: models/ldm/stable-diffusion-v1/v1-5-pruned-emaonly.ckpt
+            stable-diffusion-model-switch: stable-diffusion-1.5
+    name: ${{ matrix.os }} with ${{ matrix.stable-diffusion-model-switch }}
     runs-on: ${{ matrix.os }}
+    env:
+      CONDA_ENV_NAME: invokeai
+    defaults:
+      run:
+        shell: ${{ matrix.default-shell }}
     steps:
-      - run: |
-          echo The PR was merged
-      - name: Set platform variables
-        id: vars
-        run: |
-          # Note, can't "activate" via github action; specifying the env's python has the same effect
-          if [ "$RUNNER_OS" = "macOS" ]; then
-              echo "::set-output name=ENV_FILE::environment-mac.yml"
-              echo "::set-output name=PYTHON_BIN::/usr/local/miniconda/envs/ldm/bin/python"
-          elif [ "$RUNNER_OS" = "Linux" ]; then
-              echo "::set-output name=ENV_FILE::environment.yml"
-              echo "::set-output name=PYTHON_BIN::/usr/share/miniconda/envs/ldm/bin/python"
-          fi
       - name: Checkout sources
+        id: checkout-sources
         uses: actions/checkout@v3
-      - name: Use Cached Stable Diffusion v1.4 Model
-        id: cache-sd-v1-4
+
+      - name: create models.yaml from example
+        run: cp configs/models.yaml.example configs/models.yaml
+
+      - name: Use cached conda packages
+        id: use-cached-conda-packages
         uses: actions/cache@v3
-        env:
-          cache-name: cache-sd-v1-4
         with:
-          path: models/ldm/stable-diffusion-v1/model.ckpt
-          key: ${{ env.cache-name }}
-          restore-keys: |
-            ${{ env.cache-name }}
-      - name: Download Stable Diffusion v1.4 Model
-        if: ${{ steps.cache-sd-v1-4.outputs.cache-hit != 'true' }}
-        run: |
-          if [ ! -e models/ldm/stable-diffusion-v1 ]; then
-              mkdir -p models/ldm/stable-diffusion-v1
-          fi
-          if [ ! -e models/ldm/stable-diffusion-v1/model.ckpt ]; then
-            curl -o models/ldm/stable-diffusion-v1/model.ckpt ${{ secrets.SD_V1_4_URL }}
-          fi
-      - name: Use Cached Dependencies
-        id: cache-conda-env-ldm
-        uses: actions/cache@v3
-        env:
-          cache-name: cache-conda-env-ldm
+          path: ~/conda_pkgs_dir
+          key: conda-pkgs-${{ runner.os }}-${{ runner.arch }}-${{ hashFiles(matrix.environment-file) }}
+
+      - name: Activate Conda Env
+        id: activate-conda-env
+        uses: conda-incubator/setup-miniconda@v2
         with:
-          path: ~/.conda/envs/ldm
-          key: ${{ env.cache-name }}
-          restore-keys: |
-            ${{ env.cache-name }}-${{ runner.os }}-${{ hashFiles(steps.vars.outputs.ENV_FILE) }}
-      - name: Install Dependencies
-        if: ${{ steps.cache-conda-env-ldm.outputs.cache-hit != 'true' }}
+          activate-environment: ${{ env.CONDA_ENV_NAME }}
+          environment-file: ${{ matrix.environment-file }}
+          miniconda-version: latest
+
+      - name: set test prompt to main branch validation
+        if: ${{ github.ref == 'refs/heads/main' }}
+        run: echo "TEST_PROMPTS=tests/preflight_prompts.txt" >> $GITHUB_ENV
+
+      - name: set test prompt to development branch validation
+        if: ${{ github.ref == 'refs/heads/development' }}
+        run: echo "TEST_PROMPTS=tests/dev_prompts.txt" >> $GITHUB_ENV
+
+      - name: set test prompt to Pull Request validation
+        if: ${{ github.ref != 'refs/heads/main' && github.ref != 'refs/heads/development' }}
+        run: echo "TEST_PROMPTS=tests/validate_pr_prompt.txt" >> $GITHUB_ENV
+
+      - name: Download ${{ matrix.stable-diffusion-model-switch }}
+        id: download-stable-diffusion-model
         run: |
-          conda env create -f ${{ steps.vars.outputs.ENV_FILE }}
-      - name: Use Cached Huggingface and Torch models
-        id: cache-hugginface-torch
-        uses: actions/cache@v3
-        env:
-          cache-name: cache-hugginface-torch
-        with:
-          path: ~/.cache
-          key: ${{ env.cache-name }}
-          restore-keys: |
-            ${{ env.cache-name }}-${{ hashFiles('scripts/preload_models.py') }}
-      - name: Download Huggingface and Torch models
-        if: ${{ steps.cache-hugginface-torch.outputs.cache-hit != 'true' }}
+          [[ -d models/ldm/stable-diffusion-v1 ]] \
+            || mkdir -p models/ldm/stable-diffusion-v1
+          curl \
+            -H "Authorization: Bearer ${{ secrets.HUGGINGFACE_TOKEN }}" \
+            -o ${{ matrix.stable-diffusion-model-dl-path }} \
+            -L ${{ matrix.stable-diffusion-model }}
+
+      - name: run preload_models.py
+        id: run-preload-models
         run: |
-          ${{ steps.vars.outputs.PYTHON_BIN }} scripts/preload_models.py
-#       - name: Run tmate
-#         uses: mxschmitt/action-tmate@v3
-#         timeout-minutes: 30
+          python scripts/preload_models.py \
+            --no-interactive
+
       - name: Run the tests
+        id: run-tests
+        run: |
+          time python scripts/invoke.py \
+            --model ${{ matrix.stable-diffusion-model-switch }} \
+            --from_file ${{ env.TEST_PROMPTS }}
+
+      - name: export conda env
+        id: export-conda-env
         run: |
-          # Note, can't "activate" via github action; specifying the env's python has the same effect
-          if [ $(uname) = "Darwin" ]; then
-              export PYTORCH_ENABLE_MPS_FALLBACK=1
-          fi
-          # Utterly hacky, but I don't know how else to do this
-          if [[ ${{ github.ref }} == 'refs/heads/master' ]]; then
-            time ${{ steps.vars.outputs.PYTHON_BIN }} scripts/invoke.py --from_file tests/preflight_prompts.txt
-          elif [[ ${{ github.ref }} == 'refs/heads/development' ]]; then
-            time ${{ steps.vars.outputs.PYTHON_BIN }} scripts/invoke.py --from_file tests/dev_prompts.txt
-          fi
           mkdir -p outputs/img-samples
+          conda env export --name ${{ env.CONDA_ENV_NAME }} > outputs/img-samples/environment-${{ runner.os }}-${{ runner.arch }}.yml
+
       - name: Archive results
+        id: archive-results
         uses: actions/upload-artifact@v3
         with:
-          name: results
+          name: results_${{ matrix.os }}_${{ matrix.stable-diffusion-model-switch }}
           path: outputs/img-samples

.gitignore

@@ -1,7 +1,11 @@
 # ignore default image save location and model symbolic link
 outputs/
 models/ldm/stable-diffusion-v1/model.ckpt
-ldm/dream/restoration/codeformer/weights
+ldm/invoke/restoration/codeformer/weights
+
+# ignore user models config
+configs/models.user.yaml
+config/models.user.yml
 
 # ignore the Anaconda/Miniconda installer used while building Docker image
 anaconda.sh
@@ -195,7 +199,13 @@ checkpoints
 .scratch/
 .vscode/
 gfpgan/
-models/ldm/stable-diffusion-v1/model.sha256
+models/ldm/stable-diffusion-v1/*.sha256
 
 # GFPGAN model files
 gfpgan/
+
+# config file (will be created by installer)
+configs/models.yaml
+
+# weights (will be created by installer)
+models/ldm/stable-diffusion-v1/*.ckpt

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2022 Lincoln D. Stein (https://github.com/lstein)
+Copyright (c) 2022 Lincoln Stein and InvokeAI Organization
 
 This software is derived from a fork of the source code available from
 https://github.com/pesser/stable-diffusion and

README.md

@@ -2,7 +2,7 @@
 
 # InvokeAI: A Stable Diffusion Toolkit
 
-_Formally known as lstein/stable-diffusion_
+_Formerly known as lstein/stable-diffusion_
 
 ![project logo](docs/assets/logo.png)
 

backend/modules/parameters.py

@@ -36,6 +36,8 @@ def parameters_to_command(params):
         switches.append(f'-A {params["sampler_name"]}')
     if "seamless" in params and params["seamless"] == True:
         switches.append(f"--seamless")
+    if "hires_fix" in params and params["hires_fix"] == True:
+        switches.append(f"--hires")
     if "init_img" in params and len(params["init_img"]) > 0:
         switches.append(f'-I {params["init_img"]}')
     if "init_mask" in params and len(params["init_mask"]) > 0:
@@ -46,8 +48,14 @@ def parameters_to_command(params):
         switches.append(f'-f {params["strength"]}')
         if "fit" in params and params["fit"] == True:
             switches.append(f"--fit")
-    if "gfpgan_strength" in params and params["gfpgan_strength"]:
+    if "facetool" in params:
+        switches.append(f'-ft {params["facetool"]}')
+    if "facetool_strength" in params and params["facetool_strength"]:
+        switches.append(f'-G {params["facetool_strength"]}')
+    elif "gfpgan_strength" in params and params["gfpgan_strength"]:
         switches.append(f'-G {params["gfpgan_strength"]}')
+    if "codeformer_fidelity" in params:
+        switches.append(f'-cf {params["codeformer_fidelity"]}')
     if "upscale" in params and params["upscale"]:
         switches.append(f'-U {params["upscale"][0]} {params["upscale"][1]}')
     if "variation_amount" in params and params["variation_amount"] > 0:

backend/server.py

@@ -1,821 +0,0 @@
-import mimetypes
-import transformers
-import json
-import os
-import traceback
-import eventlet
-import glob
-import shlex
-import math
-import shutil
-import sys
-
-sys.path.append(".")
-
-from argparse import ArgumentTypeError
-from modules.create_cmd_parser import create_cmd_parser
-
-parser = create_cmd_parser()
-opt = parser.parse_args()
-
-
-from flask_socketio import SocketIO
-from flask import Flask, send_from_directory, url_for, jsonify
-from pathlib import Path
-from PIL import Image
-from pytorch_lightning import logging
-from threading import Event
-from uuid import uuid4
-from send2trash import send2trash
-
-
-from ldm.generate import Generate
-from ldm.invoke.restoration import Restoration
-from ldm.invoke.pngwriter import PngWriter, retrieve_metadata
-from ldm.invoke.args import APP_ID, APP_VERSION, calculate_init_img_hash
-from ldm.invoke.conditioning import split_weighted_subprompts
-
-from modules.parameters import parameters_to_command
-
-
-"""
-USER CONFIG
-"""
-if opt.cors and "*" in opt.cors:
-    raise ArgumentTypeError('"*" is not an allowed CORS origin')
-
-
-output_dir = "outputs/"  # Base output directory for images
-host = opt.host  # Web & socket.io host
-port = opt.port  # Web & socket.io port
-verbose = opt.verbose  # enables copious socket.io logging
-precision = opt.precision
-free_gpu_mem = opt.free_gpu_mem
-embedding_path = opt.embedding_path
-additional_allowed_origins = (
-    opt.cors if opt.cors else []
-)  # additional CORS allowed origins
-model = "stable-diffusion-1.4"
-
-"""
-END USER CONFIG
-"""
-
-
-print("* Initializing, be patient...\n")
-
-
-"""
-SERVER SETUP
-"""
-
-
-# fix missing mimetypes on windows due to registry wonkiness
-mimetypes.add_type("application/javascript", ".js")
-mimetypes.add_type("text/css", ".css")
-
-app = Flask(__name__, static_url_path="", static_folder="../frontend/dist/")
-
-
-app.config["OUTPUTS_FOLDER"] = "../outputs"
-
-
-@app.route("/outputs/<path:filename>")
-def outputs(filename):
-    return send_from_directory(app.config["OUTPUTS_FOLDER"], filename)
-
-
-@app.route("/", defaults={"path": ""})
-def serve(path):
-    return send_from_directory(app.static_folder, "index.html")
-
-
-logger = True if verbose else False
-engineio_logger = True if verbose else False
-
-# default 1,000,000, needs to be higher for socketio to accept larger images
-max_http_buffer_size = 10000000
-
-cors_allowed_origins = [f"http://{host}:{port}"] + additional_allowed_origins
-
-socketio = SocketIO(
-    app,
-    logger=logger,
-    engineio_logger=engineio_logger,
-    max_http_buffer_size=max_http_buffer_size,
-    cors_allowed_origins=cors_allowed_origins,
-    ping_interval=(50, 50),
-    ping_timeout=60,
-)
-
-
-"""
-END SERVER SETUP
-"""
-
-
-"""
-APP SETUP
-"""
-
-
-class CanceledException(Exception):
-    pass
-
-
-try:
-    gfpgan, codeformer, esrgan = None, None, None
-    from ldm.invoke.restoration.base import Restoration
-
-    restoration = Restoration()
-    gfpgan, codeformer = restoration.load_face_restore_models()
-    esrgan = restoration.load_esrgan()
-
-    # coreformer.process(self, image, strength, device, seed=None, fidelity=0.75)
-
-except (ModuleNotFoundError, ImportError):
-    print(traceback.format_exc(), file=sys.stderr)
-    print(">> You may need to install the ESRGAN and/or GFPGAN modules")
-
-canceled = Event()
-
-# reduce logging outputs to error
-transformers.logging.set_verbosity_error()
-logging.getLogger("pytorch_lightning").setLevel(logging.ERROR)
-
-# Initialize and load model
-generate = Generate(
-    model,
-    precision=precision,
-    embedding_path=embedding_path,
-)
-generate.free_gpu_mem = free_gpu_mem
-generate.load_model()
-
-
-# location for "finished" images
-result_path = os.path.join(output_dir, "img-samples/")
-
-# temporary path for intermediates
-intermediate_path = os.path.join(result_path, "intermediates/")
-
-# path for user-uploaded init images and masks
-init_image_path = os.path.join(result_path, "init-images/")
-mask_image_path = os.path.join(result_path, "mask-images/")
-
-# txt log
-log_path = os.path.join(result_path, "invoke_log.txt")
-
-# make all output paths
-[
-    os.makedirs(path, exist_ok=True)
-    for path in [result_path, intermediate_path, init_image_path, mask_image_path]
-]
-
-
-"""
-END APP SETUP
-"""
-
-
-"""
-SOCKET.IO LISTENERS
-"""
-
-
-@socketio.on("requestSystemConfig")
-def handle_request_capabilities():
-    print(f">> System config requested")
-    config = get_system_config()
-    socketio.emit("systemConfig", config)
-
-
-@socketio.on("requestImages")
-def handle_request_images(page=1, offset=0, last_mtime=None):
-    chunk_size = 50
-
-    if last_mtime:
-        print(f">> Latest images requested")
-    else:
-        print(
-            f">> Page {page} of images requested (page size {chunk_size} offset {offset})"
-        )
-
-    paths = glob.glob(os.path.join(result_path, "*.png"))
-    sorted_paths = sorted(paths, key=lambda x: os.path.getmtime(x), reverse=True)
-
-    if last_mtime:
-        image_paths = filter(lambda x: os.path.getmtime(x) > last_mtime, sorted_paths)
-    else:
-
-        image_paths = sorted_paths[
-            slice(chunk_size * (page - 1) + offset, chunk_size * page + offset)
-        ]
-        page = page + 1
-
-    image_array = []
-
-    for path in image_paths:
-        metadata = retrieve_metadata(path)
-        image_array.append(
-            {
-                "url": path,
-                "mtime": os.path.getmtime(path),
-                "metadata": metadata["sd-metadata"],
-            }
-        )
-
-    socketio.emit(
-        "galleryImages",
-        {
-            "images": image_array,
-            "nextPage": page,
-            "offset": offset,
-            "onlyNewImages": True if last_mtime else False,
-        },
-    )
-
-
-@socketio.on("generateImage")
-def handle_generate_image_event(
-    generation_parameters, esrgan_parameters, gfpgan_parameters
-):
-    print(
-        f">> Image generation requested: {generation_parameters}\nESRGAN parameters: {esrgan_parameters}\nGFPGAN parameters: {gfpgan_parameters}"
-    )
-    generate_images(generation_parameters, esrgan_parameters, gfpgan_parameters)
-
-
-@socketio.on("runESRGAN")
-def handle_run_esrgan_event(original_image, esrgan_parameters):
-    print(
-        f'>> ESRGAN upscale requested for "{original_image["url"]}": {esrgan_parameters}'
-    )
-    progress = {
-        "currentStep": 1,
-        "totalSteps": 1,
-        "currentIteration": 1,
-        "totalIterations": 1,
-        "currentStatus": "Preparing",
-        "isProcessing": True,
-        "currentStatusHasSteps": False,
-    }
-
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    image = Image.open(original_image["url"])
-
-    seed = (
-        original_image["metadata"]["seed"]
-        if "seed" in original_image["metadata"]
-        else "unknown_seed"
-    )
-
-    progress["currentStatus"] = "Upscaling"
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    image = esrgan.process(
-        image=image,
-        upsampler_scale=esrgan_parameters["upscale"][0],
-        strength=esrgan_parameters["upscale"][1],
-        seed=seed,
-    )
-
-    progress["currentStatus"] = "Saving image"
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    esrgan_parameters["seed"] = seed
-    metadata = parameters_to_post_processed_image_metadata(
-        parameters=esrgan_parameters,
-        original_image_path=original_image["url"],
-        type="esrgan",
-    )
-    command = parameters_to_command(esrgan_parameters)
-
-    path = save_image(image, command, metadata, result_path, postprocessing="esrgan")
-
-    write_log_message(f'[Upscaled] "{original_image["url"]}" > "{path}": {command}')
-
-    progress["currentStatus"] = "Finished"
-    progress["currentStep"] = 0
-    progress["totalSteps"] = 0
-    progress["currentIteration"] = 0
-    progress["totalIterations"] = 0
-    progress["isProcessing"] = False
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    socketio.emit(
-        "esrganResult",
-        {
-            "url": os.path.relpath(path),
-            "mtime": os.path.getmtime(path),
-            "metadata": metadata,
-        },
-    )
-
-
-@socketio.on("runGFPGAN")
-def handle_run_gfpgan_event(original_image, gfpgan_parameters):
-    print(
-        f'>> GFPGAN face fix requested for "{original_image["url"]}": {gfpgan_parameters}'
-    )
-    progress = {
-        "currentStep": 1,
-        "totalSteps": 1,
-        "currentIteration": 1,
-        "totalIterations": 1,
-        "currentStatus": "Preparing",
-        "isProcessing": True,
-        "currentStatusHasSteps": False,
-    }
-
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    image = Image.open(original_image["url"])
-
-    seed = (
-        original_image["metadata"]["seed"]
-        if "seed" in original_image["metadata"]
-        else "unknown_seed"
-    )
-
-    progress["currentStatus"] = "Fixing faces"
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    image = gfpgan.process(
-        image=image, strength=gfpgan_parameters["gfpgan_strength"], seed=seed
-    )
-
-    progress["currentStatus"] = "Saving image"
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    gfpgan_parameters["seed"] = seed
-    metadata = parameters_to_post_processed_image_metadata(
-        parameters=gfpgan_parameters,
-        original_image_path=original_image["url"],
-        type="gfpgan",
-    )
-    command = parameters_to_command(gfpgan_parameters)
-
-    path = save_image(image, command, metadata, result_path, postprocessing="gfpgan")
-
-    write_log_message(f'[Fixed faces] "{original_image["url"]}" > "{path}": {command}')
-
-    progress["currentStatus"] = "Finished"
-    progress["currentStep"] = 0
-    progress["totalSteps"] = 0
-    progress["currentIteration"] = 0
-    progress["totalIterations"] = 0
-    progress["isProcessing"] = False
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    socketio.emit(
-        "gfpganResult",
-        {
-            "url": os.path.relpath(path),
-            "mtime": os.path.mtime(path),
-            "metadata": metadata,
-        },
-    )
-
-
-@socketio.on("cancel")
-def handle_cancel():
-    print(f">> Cancel processing requested")
-    canceled.set()
-    socketio.emit("processingCanceled")
-
-
-# TODO: I think this needs a safety mechanism.
-@socketio.on("deleteImage")
-def handle_delete_image(path, uuid):
-    print(f'>> Delete requested "{path}"')
-    send2trash(path)
-    socketio.emit("imageDeleted", {"url": path, "uuid": uuid})
-
-
-# TODO: I think this needs a safety mechanism.
-@socketio.on("uploadInitialImage")
-def handle_upload_initial_image(bytes, name):
-    print(f'>> Init image upload requested "{name}"')
-    uuid = uuid4().hex
-    split = os.path.splitext(name)
-    name = f"{split[0]}.{uuid}{split[1]}"
-    file_path = os.path.join(init_image_path, name)
-    os.makedirs(os.path.dirname(file_path), exist_ok=True)
-    newFile = open(file_path, "wb")
-    newFile.write(bytes)
-    socketio.emit("initialImageUploaded", {"url": file_path, "uuid": ""})
-
-
-# TODO: I think this needs a safety mechanism.
-@socketio.on("uploadMaskImage")
-def handle_upload_mask_image(bytes, name):
-    print(f'>> Mask image upload requested "{name}"')
-    uuid = uuid4().hex
-    split = os.path.splitext(name)
-    name = f"{split[0]}.{uuid}{split[1]}"
-    file_path = os.path.join(mask_image_path, name)
-    os.makedirs(os.path.dirname(file_path), exist_ok=True)
-    newFile = open(file_path, "wb")
-    newFile.write(bytes)
-    socketio.emit("maskImageUploaded", {"url": file_path, "uuid": ""})
-
-
-"""
-END SOCKET.IO LISTENERS
-"""
-
-
-"""
-ADDITIONAL FUNCTIONS
-"""
-
-
-def get_system_config():
-    return {
-        "model": "stable diffusion",
-        "model_id": model,
-        "model_hash": generate.model_hash,
-        "app_id": APP_ID,
-        "app_version": APP_VERSION,
-    }
-
-
-def parameters_to_post_processed_image_metadata(parameters, original_image_path, type):
-    # top-level metadata minus `image` or `images`
-    metadata = get_system_config()
-
-    orig_hash = calculate_init_img_hash(original_image_path)
-
-    image = {"orig_path": original_image_path, "orig_hash": orig_hash}
-
-    if type == "esrgan":
-        image["type"] = "esrgan"
-        image["scale"] = parameters["upscale"][0]
-        image["strength"] = parameters["upscale"][1]
-    elif type == "gfpgan":
-        image["type"] = "gfpgan"
-        image["strength"] = parameters["gfpgan_strength"]
-    else:
-        raise TypeError(f"Invalid type: {type}")
-
-    metadata["image"] = image
-    return metadata
-
-
-def parameters_to_generated_image_metadata(parameters):
-    # top-level metadata minus `image` or `images`
-
-    metadata = get_system_config()
-    # remove any image keys not mentioned in RFC #266
-    rfc266_img_fields = [
-        "type",
-        "postprocessing",
-        "sampler",
-        "prompt",
-        "seed",
-        "variations",
-        "steps",
-        "cfg_scale",
-        "threshold",
-        "perlin",
-        "step_number",
-        "width",
-        "height",
-        "extra",
-        "seamless",
-    ]
-
-    rfc_dict = {}
-
-    for item in parameters.items():
-        key, value = item
-        if key in rfc266_img_fields:
-            rfc_dict[key] = value
-
-    postprocessing = []
-
-    # 'postprocessing' is either null or an
-    if "gfpgan_strength" in parameters:
-
-        postprocessing.append(
-            {"type": "gfpgan", "strength": float(parameters["gfpgan_strength"])}
-        )
-
-    if "upscale" in parameters:
-        postprocessing.append(
-            {
-                "type": "esrgan",
-                "scale": int(parameters["upscale"][0]),
-                "strength": float(parameters["upscale"][1]),
-            }
-        )
-
-    rfc_dict["postprocessing"] = postprocessing if len(postprocessing) > 0 else None
-
-    # semantic drift
-    rfc_dict["sampler"] = parameters["sampler_name"]
-
-    # display weighted subprompts (liable to change)
-    subprompts = split_weighted_subprompts(parameters["prompt"])
-    subprompts = [{"prompt": x[0], "weight": x[1]} for x in subprompts]
-    rfc_dict["prompt"] = subprompts
-
-    # 'variations' should always exist and be an array, empty or consisting of {'seed': seed, 'weight': weight} pairs
-    variations = []
-
-    if "with_variations" in parameters:
-        variations = [
-            {"seed": x[0], "weight": x[1]} for x in parameters["with_variations"]
-        ]
-
-    rfc_dict["variations"] = variations
-
-    if "init_img" in parameters:
-        rfc_dict["type"] = "img2img"
-        rfc_dict["strength"] = parameters["strength"]
-        rfc_dict["fit"] = parameters["fit"]  # TODO: Noncompliant
-        rfc_dict["orig_hash"] = calculate_init_img_hash(parameters["init_img"])
-        rfc_dict["init_image_path"] = parameters["init_img"]  # TODO: Noncompliant
-        rfc_dict["sampler"] = "ddim"  # TODO: FIX ME WHEN IMG2IMG SUPPORTS ALL SAMPLERS
-        if "init_mask" in parameters:
-            rfc_dict["mask_hash"] = calculate_init_img_hash(
-                parameters["init_mask"]
-            )  # TODO: Noncompliant
-            rfc_dict["mask_image_path"] = parameters["init_mask"]  # TODO: Noncompliant
-    else:
-        rfc_dict["type"] = "txt2img"
-
-    metadata["image"] = rfc_dict
-
-    return metadata
-
-
-def make_unique_init_image_filename(name):
-    uuid = uuid4().hex
-    split = os.path.splitext(name)
-    name = f"{split[0]}.{uuid}{split[1]}"
-    return name
-
-
-def write_log_message(message, log_path=log_path):
-    """Logs the filename and parameters used to generate or process that image to log file"""
-    message = f"{message}\n"
-    with open(log_path, "a", encoding="utf-8") as file:
-        file.writelines(message)
-
-
-def save_image(
-    image, command, metadata, output_dir, step_index=None, postprocessing=False
-):
-    pngwriter = PngWriter(output_dir)
-    prefix = pngwriter.unique_prefix()
-
-    seed = "unknown_seed"
-
-    if "image" in metadata:
-        if "seed" in metadata["image"]:
-            seed = metadata["image"]["seed"]
-
-    filename = f"{prefix}.{seed}"
-
-    if step_index:
-        filename += f".{step_index}"
-    if postprocessing:
-        filename += f".postprocessed"
-
-    filename += ".png"
-
-    path = pngwriter.save_image_and_prompt_to_png(
-        image=image, dream_prompt=command, metadata=metadata, name=filename
-    )
-
-    return path
-
-
-def calculate_real_steps(steps, strength, has_init_image):
-    return math.floor(strength * steps) if has_init_image else steps
-
-
-def generate_images(generation_parameters, esrgan_parameters, gfpgan_parameters):
-    canceled.clear()
-
-    step_index = 1
-    prior_variations = (
-        generation_parameters["with_variations"]
-        if "with_variations" in generation_parameters
-        else []
-    )
-    """
-    If a result image is used as an init image, and then deleted, we will want to be
-    able to use it as an init image in the future. Need to copy it.
-
-    If the init/mask image doesn't exist in the init_image_path/mask_image_path,
-    make a unique filename for it and copy it there.
-    """
-    if "init_img" in generation_parameters:
-        filename = os.path.basename(generation_parameters["init_img"])
-        if not os.path.exists(os.path.join(init_image_path, filename)):
-            unique_filename = make_unique_init_image_filename(filename)
-            new_path = os.path.join(init_image_path, unique_filename)
-            shutil.copy(generation_parameters["init_img"], new_path)
-            generation_parameters["init_img"] = new_path
-        if "init_mask" in generation_parameters:
-            filename = os.path.basename(generation_parameters["init_mask"])
-            if not os.path.exists(os.path.join(mask_image_path, filename)):
-                unique_filename = make_unique_init_image_filename(filename)
-                new_path = os.path.join(init_image_path, unique_filename)
-                shutil.copy(generation_parameters["init_img"], new_path)
-                generation_parameters["init_mask"] = new_path
-
-    totalSteps = calculate_real_steps(
-        steps=generation_parameters["steps"],
-        strength=generation_parameters["strength"]
-        if "strength" in generation_parameters
-        else None,
-        has_init_image="init_img" in generation_parameters,
-    )
-
-    progress = {
-        "currentStep": 1,
-        "totalSteps": totalSteps,
-        "currentIteration": 1,
-        "totalIterations": generation_parameters["iterations"],
-        "currentStatus": "Preparing",
-        "isProcessing": True,
-        "currentStatusHasSteps": False,
-    }
-
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    def image_progress(sample, step):
-        if canceled.is_set():
-            raise CanceledException
-
-        nonlocal step_index
-        nonlocal generation_parameters
-        nonlocal progress
-
-        progress["currentStep"] = step + 1
-        progress["currentStatus"] = "Generating"
-        progress["currentStatusHasSteps"] = True
-
-        if (
-            generation_parameters["progress_images"]
-            and step % 5 == 0
-            and step < generation_parameters["steps"] - 1
-        ):
-            image = generate.sample_to_image(sample)
-
-            metadata = parameters_to_generated_image_metadata(generation_parameters)
-            command = parameters_to_command(generation_parameters)
-            path = save_image(image, command, metadata, intermediate_path, step_index=step_index, postprocessing=False)
-
-            step_index += 1
-            socketio.emit(
-                "intermediateResult",
-                {
-                    "url": os.path.relpath(path),
-                    "mtime": os.path.getmtime(path),
-                    "metadata": metadata,
-                },
-            )
-        socketio.emit("progressUpdate", progress)
-        eventlet.sleep(0)
-
-    def image_done(image, seed, first_seed):
-        nonlocal generation_parameters
-        nonlocal esrgan_parameters
-        nonlocal gfpgan_parameters
-        nonlocal progress
-
-        step_index = 1
-        nonlocal prior_variations
-
-        progress["currentStatus"] = "Generation complete"
-        socketio.emit("progressUpdate", progress)
-        eventlet.sleep(0)
-
-        all_parameters = generation_parameters
-        postprocessing = False
-
-        if (
-            "variation_amount" in all_parameters
-            and all_parameters["variation_amount"] > 0
-        ):
-            first_seed = first_seed or seed
-            this_variation = [[seed, all_parameters["variation_amount"]]]
-            all_parameters["with_variations"] = prior_variations + this_variation
-            all_parameters["seed"] = first_seed
-        elif ("with_variations" in all_parameters):
-            all_parameters["seed"] = first_seed
-        else:
-            all_parameters["seed"] = seed
-
-        if esrgan_parameters:
-            progress["currentStatus"] = "Upscaling"
-            progress["currentStatusHasSteps"] = False
-            socketio.emit("progressUpdate", progress)
-            eventlet.sleep(0)
-
-            image = esrgan.process(
-                image=image,
-                upsampler_scale=esrgan_parameters["level"],
-                strength=esrgan_parameters["strength"],
-                seed=seed,
-            )
-
-            postprocessing = True
-            all_parameters["upscale"] = [
-                esrgan_parameters["level"],
-                esrgan_parameters["strength"],
-            ]
-
-        if gfpgan_parameters:
-            progress["currentStatus"] = "Fixing faces"
-            progress["currentStatusHasSteps"] = False
-            socketio.emit("progressUpdate", progress)
-            eventlet.sleep(0)
-
-            image = gfpgan.process(
-                image=image, strength=gfpgan_parameters["strength"], seed=seed
-            )
-            postprocessing = True
-            all_parameters["gfpgan_strength"] = gfpgan_parameters["strength"]
-
-        progress["currentStatus"] = "Saving image"
-        socketio.emit("progressUpdate", progress)
-        eventlet.sleep(0)
-
-        metadata = parameters_to_generated_image_metadata(all_parameters)
-        command = parameters_to_command(all_parameters)
-
-        path = save_image(
-            image, command, metadata, result_path, postprocessing=postprocessing
-        )
-
-        print(f'>> Image generated: "{path}"')
-        write_log_message(f'[Generated] "{path}": {command}')
-
-        if progress["totalIterations"] > progress["currentIteration"]:
-            progress["currentStep"] = 1
-            progress["currentIteration"] += 1
-            progress["currentStatus"] = "Iteration finished"
-            progress["currentStatusHasSteps"] = False
-        else:
-            progress["currentStep"] = 0
-            progress["totalSteps"] = 0
-            progress["currentIteration"] = 0
-            progress["totalIterations"] = 0
-            progress["currentStatus"] = "Finished"
-            progress["isProcessing"] = False
-
-        socketio.emit("progressUpdate", progress)
-        eventlet.sleep(0)
-
-        socketio.emit(
-            "generationResult",
-            {
-                "url": os.path.relpath(path),
-                "mtime": os.path.getmtime(path),
-                "metadata": metadata,
-            },
-        )
-        eventlet.sleep(0)
-
-    try:
-        generate.prompt2image(
-            **generation_parameters,
-            step_callback=image_progress,
-            image_callback=image_done,
-        )
-
-    except KeyboardInterrupt:
-        raise
-    except CanceledException:
-        pass
-    except Exception as e:
-        socketio.emit("error", {"message": (str(e))})
-        print("\n")
-        traceback.print_exc()
-        print("\n")
-
-
-"""
-END ADDITIONAL FUNCTIONS
-"""
-
-
-if __name__ == "__main__":
-    print(f">> Starting server at http://{host}:{port}")
-    socketio.run(app, host=host, port=port)

configs/autoencoder/autoencoder_kl_16x16x16.yaml

@@ -1,54 +0,0 @@
-model:
-  base_learning_rate: 4.5e-6
-  target: ldm.models.autoencoder.AutoencoderKL
-  params:
-    monitor: "val/rec_loss"
-    embed_dim: 16
-    lossconfig:
-      target: ldm.modules.losses.LPIPSWithDiscriminator
-      params:
-        disc_start: 50001
-        kl_weight: 0.000001
-        disc_weight: 0.5
-
-    ddconfig:
-      double_z: True
-      z_channels: 16
-      resolution: 256
-      in_channels: 3
-      out_ch: 3
-      ch: 128
-      ch_mult: [ 1,1,2,2,4]  # num_down = len(ch_mult)-1
-      num_res_blocks: 2
-      attn_resolutions: [16]
-      dropout: 0.0
-
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 12
-    wrap: True
-    train:
-      target: ldm.data.imagenet.ImageNetSRTrain
-      params:
-        size: 256
-        degradation: pil_nearest
-    validation:
-      target: ldm.data.imagenet.ImageNetSRValidation
-      params:
-        size: 256
-        degradation: pil_nearest
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 1000
-        max_images: 8
-        increase_log_steps: True
-
-  trainer:
-    benchmark: True
-    accumulate_grad_batches: 2

configs/autoencoder/autoencoder_kl_32x32x4.yaml

@@ -1,53 +0,0 @@
-model:
-  base_learning_rate: 4.5e-6
-  target: ldm.models.autoencoder.AutoencoderKL
-  params:
-    monitor: "val/rec_loss"
-    embed_dim: 4
-    lossconfig:
-      target: ldm.modules.losses.LPIPSWithDiscriminator
-      params:
-        disc_start: 50001
-        kl_weight: 0.000001
-        disc_weight: 0.5
-
-    ddconfig:
-      double_z: True
-      z_channels: 4
-      resolution: 256
-      in_channels: 3
-      out_ch: 3
-      ch: 128
-      ch_mult: [ 1,2,4,4 ]  # num_down = len(ch_mult)-1
-      num_res_blocks: 2
-      attn_resolutions: [ ]
-      dropout: 0.0
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 12
-    wrap: True
-    train:
-      target: ldm.data.imagenet.ImageNetSRTrain
-      params:
-        size: 256
-        degradation: pil_nearest
-    validation:
-      target: ldm.data.imagenet.ImageNetSRValidation
-      params:
-        size: 256
-        degradation: pil_nearest
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 1000
-        max_images: 8
-        increase_log_steps: True
-
-  trainer:
-    benchmark: True
-    accumulate_grad_batches: 2

configs/autoencoder/autoencoder_kl_64x64x3.yaml

@@ -1,54 +0,0 @@
-model:
-  base_learning_rate: 4.5e-6
-  target: ldm.models.autoencoder.AutoencoderKL
-  params:
-    monitor: "val/rec_loss"
-    embed_dim: 3
-    lossconfig:
-      target: ldm.modules.losses.LPIPSWithDiscriminator
-      params:
-        disc_start: 50001
-        kl_weight: 0.000001
-        disc_weight: 0.5
-
-    ddconfig:
-      double_z: True
-      z_channels: 3
-      resolution: 256
-      in_channels: 3
-      out_ch: 3
-      ch: 128
-      ch_mult: [ 1,2,4 ]  # num_down = len(ch_mult)-1
-      num_res_blocks: 2
-      attn_resolutions: [ ]
-      dropout: 0.0
-
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 12
-    wrap: True
-    train:
-      target: ldm.data.imagenet.ImageNetSRTrain
-      params:
-        size: 256
-        degradation: pil_nearest
-    validation:
-      target: ldm.data.imagenet.ImageNetSRValidation
-      params:
-        size: 256
-        degradation: pil_nearest
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 1000
-        max_images: 8
-        increase_log_steps: True
-
-  trainer:
-    benchmark: True
-    accumulate_grad_batches: 2

configs/autoencoder/autoencoder_kl_8x8x64.yaml

@@ -1,53 +0,0 @@
-model:
-  base_learning_rate: 4.5e-6
-  target: ldm.models.autoencoder.AutoencoderKL
-  params:
-    monitor: "val/rec_loss"
-    embed_dim: 64
-    lossconfig:
-      target: ldm.modules.losses.LPIPSWithDiscriminator
-      params:
-        disc_start: 50001
-        kl_weight: 0.000001
-        disc_weight: 0.5
-
-    ddconfig:
-      double_z: True
-      z_channels: 64
-      resolution: 256
-      in_channels: 3
-      out_ch: 3
-      ch: 128
-      ch_mult: [ 1,1,2,2,4,4]  # num_down = len(ch_mult)-1
-      num_res_blocks: 2
-      attn_resolutions: [16,8]
-      dropout: 0.0
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 12
-    wrap: True
-    train:
-      target: ldm.data.imagenet.ImageNetSRTrain
-      params:
-        size: 256
-        degradation: pil_nearest
-    validation:
-      target: ldm.data.imagenet.ImageNetSRValidation
-      params:
-        size: 256
-        degradation: pil_nearest
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 1000
-        max_images: 8
-        increase_log_steps: True
-
-  trainer:
-    benchmark: True
-    accumulate_grad_batches: 2

configs/latent-diffusion/celebahq-ldm-vq-4.yaml

@@ -1,86 +0,0 @@
-model:
-  base_learning_rate: 2.0e-06
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0195
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    image_size: 64
-    channels: 3
-    monitor: val/loss_simple_ema
-
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 64
-        in_channels: 3
-        out_channels: 3
-        model_channels: 224
-        attention_resolutions:
-        # note: this isn\t actually the resolution but
-        # the downsampling factor, i.e. this corresnponds to
-        # attention on spatial resolution 8,16,32, as the
-        # spatial reolution of the latents is 64 for f4
-        - 8
-        - 4
-        - 2
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 3
-        - 4
-        num_head_channels: 32
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        embed_dim: 3
-        n_embed: 8192
-        ckpt_path: models/first_stage_models/vq-f4/model.ckpt
-        ddconfig:
-          double_z: false
-          z_channels: 3
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    cond_stage_config: __is_unconditional__
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 48
-    num_workers: 5
-    wrap: false
-    train:
-      target: taming.data.faceshq.CelebAHQTrain
-      params:
-        size: 256
-    validation:
-      target: taming.data.faceshq.CelebAHQValidation
-      params:
-        size: 256
-
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-  trainer:
-    benchmark: True

configs/latent-diffusion/cin-ldm-vq-f8.yaml

@@ -1,98 +0,0 @@
-model:
-  base_learning_rate: 1.0e-06
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0195
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    cond_stage_key: class_label
-    image_size: 32
-    channels: 4
-    cond_stage_trainable: true
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 32
-        in_channels: 4
-        out_channels: 4
-        model_channels: 256
-        attention_resolutions:
-        #note: this isn\t actually the resolution but
-        # the downsampling factor, i.e. this corresnponds to
-        # attention on spatial resolution 8,16,32, as the
-        # spatial reolution of the latents is 32 for f8
-        - 4
-        - 2
-        - 1
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 4
-        num_head_channels: 32
-        use_spatial_transformer: true
-        transformer_depth: 1
-        context_dim: 512
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        embed_dim: 4
-        n_embed: 16384
-        ckpt_path: configs/first_stage_models/vq-f8/model.yaml
-        ddconfig:
-          double_z: false
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions:
-          - 32
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    cond_stage_config:
-      target: ldm.modules.encoders.modules.ClassEmbedder
-      params:
-        embed_dim: 512
-        key: class_label
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 64
-    num_workers: 12
-    wrap: false
-    train:
-      target: ldm.data.imagenet.ImageNetTrain
-      params:
-        config:
-          size: 256
-    validation:
-      target: ldm.data.imagenet.ImageNetValidation
-      params:
-        config:
-          size: 256
-
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-  trainer:
-    benchmark: True

configs/latent-diffusion/cin256-v2.yaml

@@ -1,68 +0,0 @@
-model:
-  base_learning_rate: 0.0001
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0195
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    cond_stage_key: class_label
-    image_size: 64
-    channels: 3
-    cond_stage_trainable: true
-    conditioning_key: crossattn
-    monitor: val/loss
-    use_ema: False
-    
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 64
-        in_channels: 3
-        out_channels: 3
-        model_channels: 192
-        attention_resolutions:
-        - 8
-        - 4
-        - 2
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 3
-        - 5
-        num_heads: 1
-        use_spatial_transformer: true
-        transformer_depth: 1
-        context_dim: 512
-    
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        embed_dim: 3
-        n_embed: 8192
-        ddconfig:
-          double_z: false
-          z_channels: 3
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    
-    cond_stage_config:
-      target: ldm.modules.encoders.modules.ClassEmbedder
-      params:
-        n_classes: 1001
-        embed_dim: 512
-        key: class_label

configs/latent-diffusion/ffhq-ldm-vq-4.yaml

@@ -1,85 +0,0 @@
-model:
-  base_learning_rate: 2.0e-06
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0195
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    image_size: 64
-    channels: 3
-    monitor: val/loss_simple_ema
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 64
-        in_channels: 3
-        out_channels: 3
-        model_channels: 224
-        attention_resolutions:
-        # note: this isn\t actually the resolution but
-        # the downsampling factor, i.e. this corresnponds to
-        # attention on spatial resolution 8,16,32, as the
-        # spatial reolution of the latents is 64 for f4
-        - 8
-        - 4
-        - 2
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 3
-        - 4
-        num_head_channels: 32
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        embed_dim: 3
-        n_embed: 8192
-        ckpt_path: configs/first_stage_models/vq-f4/model.yaml
-        ddconfig:
-          double_z: false
-          z_channels: 3
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    cond_stage_config: __is_unconditional__
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 42
-    num_workers: 5
-    wrap: false
-    train:
-      target: taming.data.faceshq.FFHQTrain
-      params:
-        size: 256
-    validation:
-      target: taming.data.faceshq.FFHQValidation
-      params:
-        size: 256
-
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-  trainer:
-    benchmark: True

configs/latent-diffusion/lsun_bedrooms-ldm-vq-4.yaml

@@ -1,85 +0,0 @@
-model:
-  base_learning_rate: 2.0e-06
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0195
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    image_size: 64
-    channels: 3
-    monitor: val/loss_simple_ema
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 64
-        in_channels: 3
-        out_channels: 3
-        model_channels: 224
-        attention_resolutions:
-        # note: this isn\t actually the resolution but
-        # the downsampling factor, i.e. this corresnponds to
-        # attention on spatial resolution 8,16,32, as the
-        # spatial reolution of the latents is 64 for f4
-        - 8
-        - 4
-        - 2
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 3
-        - 4
-        num_head_channels: 32
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        ckpt_path: configs/first_stage_models/vq-f4/model.yaml
-        embed_dim: 3
-        n_embed: 8192
-        ddconfig:
-          double_z: false
-          z_channels: 3
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    cond_stage_config: __is_unconditional__
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 48
-    num_workers: 5
-    wrap: false
-    train:
-      target: ldm.data.lsun.LSUNBedroomsTrain
-      params:
-        size: 256
-    validation:
-      target: ldm.data.lsun.LSUNBedroomsValidation
-      params:
-        size: 256
-
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-  trainer:
-    benchmark: True

configs/latent-diffusion/lsun_churches-ldm-kl-8.yaml

@@ -1,91 +0,0 @@
-model:
-  base_learning_rate: 5.0e-5   # set to target_lr by starting main.py with '--scale_lr False'
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0155
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    loss_type: l1
-    first_stage_key: "image"
-    cond_stage_key: "image"
-    image_size: 32
-    channels: 4
-    cond_stage_trainable: False
-    concat_mode: False
-    scale_by_std: True
-    monitor: 'val/loss_simple_ema'
-
-    scheduler_config: # 10000 warmup steps
-      target: ldm.lr_scheduler.LambdaLinearScheduler
-      params:
-        warm_up_steps: [10000]
-        cycle_lengths: [10000000000000]
-        f_start: [1.e-6]
-        f_max: [1.]
-        f_min: [ 1.]
-
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 32
-        in_channels: 4
-        out_channels: 4
-        model_channels: 192
-        attention_resolutions: [ 1, 2, 4, 8 ]   # 32, 16, 8, 4
-        num_res_blocks: 2
-        channel_mult: [ 1,2,2,4,4 ]  # 32, 16, 8, 4, 2
-        num_heads: 8
-        use_scale_shift_norm: True
-        resblock_updown: True
-
-    first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
-      params:
-        embed_dim: 4
-        monitor: "val/rec_loss"
-        ckpt_path: "models/first_stage_models/kl-f8/model.ckpt"
-        ddconfig:
-          double_z: True
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult: [ 1,2,4,4 ]  # num_down = len(ch_mult)-1
-          num_res_blocks: 2
-          attn_resolutions: [ ]
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-
-    cond_stage_config: "__is_unconditional__"
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 96
-    num_workers: 5
-    wrap: False
-    train:
-      target: ldm.data.lsun.LSUNChurchesTrain
-      params:
-        size: 256
-    validation:
-      target: ldm.data.lsun.LSUNChurchesValidation
-      params:
-        size: 256
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-
-  trainer:
-    benchmark: True

configs/latent-diffusion/txt2img-1p4B-eval.yaml

@@ -1,71 +0,0 @@
-model:
-  base_learning_rate: 5.0e-05
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.00085
-    linear_end: 0.012
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    cond_stage_key: caption
-    image_size: 32
-    channels: 4
-    cond_stage_trainable: true
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    scale_factor: 0.18215
-    use_ema: False
-
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 32
-        in_channels: 4
-        out_channels: 4
-        model_channels: 320
-        attention_resolutions:
-        - 4
-        - 2
-        - 1
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 4
-        - 4
-        num_heads: 8
-        use_spatial_transformer: true
-        transformer_depth: 1
-        context_dim: 1280
-        use_checkpoint: true
-        legacy: False
-
-    first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
-      params:
-        embed_dim: 4
-        monitor: val/rec_loss
-        ddconfig:
-          double_z: true
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-
-    cond_stage_config:
-      target: ldm.modules.encoders.modules.BERTEmbedder
-      params:
-        n_embed: 1280
-        n_layer: 32

configs/models.yaml

@@ -1,18 +0,0 @@
-# This file describes the alternative machine learning models
-#  available to the dream script.
-#
-# To add a new model, follow the examples below. Each
-# model requires a model config file, a weights file,
-# and the width and height of the images it
-# was trained on.
-
-laion400m:
-    config:  configs/latent-diffusion/txt2img-1p4B-eval.yaml
-    weights: models/ldm/text2img-large/model.ckpt
-    width: 256
-    height: 256
-stable-diffusion-1.4:
-    config:  configs/stable-diffusion/v1-inference.yaml
-    weights: models/ldm/stable-diffusion-v1/model.ckpt
-    width: 512
-    height: 512

configs/models.yaml.example

@@ -0,0 +1,27 @@
+# This file describes the alternative machine learning models
+# available to InvokeAI script.
+#
+# To add a new model, follow the examples below. Each
+# model requires a model config file, a weights file,
+# and the width and height of the images it
+# was trained on.
+stable-diffusion-1.5:
+  description: The newest Stable Diffusion version 1.5 weight file (4.27 GB)
+  weights: ./models/ldm/stable-diffusion-v1/v1-5-pruned-emaonly.ckpt
+  config: ./configs/stable-diffusion/v1-inference.yaml
+  width: 512
+  height: 512
+  vae: ./models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
+  default: true
+stable-diffusion-1.4:
+  description: Stable Diffusion inference model version 1.4
+  config: configs/stable-diffusion/v1-inference.yaml
+  weights: models/ldm/stable-diffusion-v1/sd-v1-4.ckpt
+  vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
+  width: 512
+  height: 512
+inpainting-1.5:
+  weights: models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt
+  config: configs/stable-diffusion/v1-inpainting-inference.yaml
+  vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
+  description: RunwayML SD 1.5 model optimized for inpainting

configs/retrieval-augmented-diffusion/768x768.yaml

@@ -1,68 +0,0 @@
-model:
-  base_learning_rate: 0.0001
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.015
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: jpg
-    cond_stage_key: nix
-    image_size: 48
-    channels: 16
-    cond_stage_trainable: false
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    scale_by_std: false
-    scale_factor: 0.22765929
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 48
-        in_channels: 16
-        out_channels: 16
-        model_channels: 448
-        attention_resolutions:
-        - 4
-        - 2
-        - 1
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 3
-        - 4
-        use_scale_shift_norm: false
-        resblock_updown: false
-        num_head_channels: 32
-        use_spatial_transformer: true
-        transformer_depth: 1
-        context_dim: 768
-        use_checkpoint: true
-    first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
-      params:
-        monitor: val/rec_loss
-        embed_dim: 16
-        ddconfig:
-          double_z: true
-          z_channels: 16
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 1
-          - 2
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions:
-          - 16
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    cond_stage_config:
-      target: torch.nn.Identity

configs/stable-diffusion/v1-inference.yaml

@@ -76,4 +76,4 @@ model:
           target: torch.nn.Identity
 
     cond_stage_config:
-      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
+      target: ldm.modules.encoders.modules.WeightedFrozenCLIPEmbedder

configs/stable-diffusion/v1-inpainting-inference.yaml

@@ -0,0 +1,79 @@
+model:
+  base_learning_rate: 7.5e-05
+  target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: hybrid   # important
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    finetune_keys: null
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 2500 ] # NOTE for resuming. use 10000 if starting from scratch
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ['face', 'man', 'photo', 'africanmale']
+        per_image_tokens: false
+        num_vectors_per_token: 1
+        progressive_words: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 9  # 4 data + 4 downscaled image + 1 mask
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.WeightedFrozenCLIPEmbedder

docker-build/Dockerfile

@@ -1,57 +1,74 @@
-FROM        debian 
+FROM ubuntu AS get_miniconda
 
-ARG         gsd
-ENV         GITHUB_STABLE_DIFFUSION $gsd
+SHELL ["/bin/bash", "-c"]
 
-ARG         rsd
-ENV         REQS $rsd
+# install wget
+RUN apt-get update \
+  && apt-get install -y \
+    wget \
+  && apt-get clean \
+  && rm -rf /var/lib/apt/lists/*
 
-ARG         cs
-ENV         CONDA_SUBDIR $cs
+# download and install miniconda
+ARG conda_version=py39_4.12.0-Linux-x86_64
+ARG conda_prefix=/opt/conda
+RUN wget --progress=dot:giga -O /miniconda.sh \
+  https://repo.anaconda.com/miniconda/Miniconda3-${conda_version}.sh \
+  && bash /miniconda.sh -b -p ${conda_prefix} \
+  && rm -f /miniconda.sh
 
-ENV         PIP_EXISTS_ACTION="w"
+FROM ubuntu AS invokeai
 
-# TODO: Optimize image size
+# use bash
+SHELL [ "/bin/bash", "-c" ]
 
-SHELL       ["/bin/bash", "-c"]
+# clean bashrc
+RUN echo "" > ~/.bashrc
 
-WORKDIR     /
-RUN         apt update && apt upgrade -y \
-            && apt install -y \
-            git \
-            libgl1-mesa-glx \
-            libglib2.0-0 \
-            pip \
-            python3 \
-            && git clone $GITHUB_STABLE_DIFFUSION
+# Install necesarry packages
+RUN apt-get update \
+  && apt-get install -y \
+    --no-install-recommends \
+    gcc \
+    git \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    pip \
+    python3 \
+    python3-dev \
+  && apt-get clean \
+  && rm -rf /var/lib/apt/lists/*
 
-# Install Anaconda or Miniconda
-COPY        anaconda.sh .
-RUN         bash anaconda.sh -b -u -p /anaconda && /anaconda/bin/conda init bash
+# clone repository and create symlinks
+ARG invokeai_git=https://github.com/invoke-ai/InvokeAI.git
+ARG project_name=invokeai
+RUN git clone ${invokeai_git} /${project_name} \
+  && mkdir /${project_name}/models/ldm/stable-diffusion-v1 \
+  && ln -s /data/models/sd-v1-4.ckpt /${project_name}/models/ldm/stable-diffusion-v1/model.ckpt \
+  && ln -s /data/outputs/ /${project_name}/outputs
 
-# SD 
-WORKDIR     /stable-diffusion 
-RUN         source ~/.bashrc \
-            && conda create -y --name ldm && conda activate ldm \
-            && conda config --env --set subdir $CONDA_SUBDIR \
-            && pip3 install -r $REQS \   
-            && pip3 install basicsr facexlib realesrgan \          
-            && mkdir models/ldm/stable-diffusion-v1 \
-            && ln -s "/data/sd-v1-4.ckpt" models/ldm/stable-diffusion-v1/model.ckpt 
+# set workdir
+WORKDIR /${project_name}
 
-# Face restoreation
-# by default expected in a sibling directory to stable-diffusion
-WORKDIR     /       
-RUN         git clone https://github.com/TencentARC/GFPGAN.git 
+# install conda env and preload models
+ARG conda_prefix=/opt/conda
+ARG conda_env_file=environment.yml
+COPY --from=get_miniconda ${conda_prefix} ${conda_prefix}
+RUN source ${conda_prefix}/etc/profile.d/conda.sh \
+  && conda init bash \
+  && source ~/.bashrc \
+  && conda env create \
+    --name ${project_name} \
+    --file ${conda_env_file} \
+  && rm -Rf ~/.cache \
+  && conda clean -afy \
+  && echo "conda activate ${project_name}" >> ~/.bashrc \
+  && ln -s /data/models/GFPGANv1.4.pth ./src/gfpgan/experiments/pretrained_models/GFPGANv1.4.pth \
+  && conda activate ${project_name} \
+  && python scripts/preload_models.py
 
-WORKDIR     /GFPGAN 
-RUN         pip3 install -r requirements.txt \
-            && python3 setup.py develop \
-            && ln -s "/data/GFPGANv1.4.pth" experiments/pretrained_models/GFPGANv1.4.pth
-
-WORKDIR     /stable-diffusion 
-RUN         python3 scripts/preload_models.py         
-
-WORKDIR     /
-COPY        entrypoint.sh .
-ENTRYPOINT ["/entrypoint.sh"]
+# Copy entrypoint and set env
+ENV CONDA_PREFIX=${conda_prefix}
+ENV PROJECT_NAME=${project_name}
+COPY docker-build/entrypoint.sh /
+ENTRYPOINT [ "/entrypoint.sh" ]

docker-build/build.sh

@@ -0,0 +1,81 @@
+#!/usr/bin/env bash
+set -e
+# IMPORTANT: You need to have a token on huggingface.co to be able to download the checkpoint!!!
+# configure values by using env when executing build.sh
+# f.e. env ARCH=aarch64 GITHUB_INVOKE_AI=https://github.com/yourname/yourfork.git ./build.sh
+
+source ./docker-build/env.sh || echo "please run from repository root" || exit 1
+
+invokeai_conda_version=${INVOKEAI_CONDA_VERSION:-py39_4.12.0-${platform/\//-}}
+invokeai_conda_prefix=${INVOKEAI_CONDA_PREFIX:-\/opt\/conda}
+invokeai_conda_env_file=${INVOKEAI_CONDA_ENV_FILE:-environment.yml}
+invokeai_git=${INVOKEAI_GIT:-https://github.com/invoke-ai/InvokeAI.git}
+huggingface_token=${HUGGINGFACE_TOKEN?}
+
+# print the settings
+echo "You are using these values:"
+echo -e "project_name:\t\t ${project_name}"
+echo -e "volumename:\t\t ${volumename}"
+echo -e "arch:\t\t\t ${arch}"
+echo -e "platform:\t\t ${platform}"
+echo -e "invokeai_conda_version:\t ${invokeai_conda_version}"
+echo -e "invokeai_conda_prefix:\t ${invokeai_conda_prefix}"
+echo -e "invokeai_conda_env_file: ${invokeai_conda_env_file}"
+echo -e "invokeai_git:\t\t ${invokeai_git}"
+echo -e "invokeai_tag:\t\t ${invokeai_tag}\n"
+
+_runAlpine() {
+  docker run \
+    --rm \
+    --interactive \
+    --tty \
+    --mount source="$volumename",target=/data \
+    --workdir /data \
+    alpine "$@"
+}
+
+_copyCheckpoints() {
+  echo "creating subfolders for models and outputs"
+  _runAlpine mkdir models
+  _runAlpine mkdir outputs
+  echo -n "downloading sd-v1-4.ckpt"
+  _runAlpine wget --header="Authorization: Bearer ${huggingface_token}" -O models/sd-v1-4.ckpt https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt
+  echo "done"
+  echo "downloading GFPGANv1.4.pth"
+  _runAlpine wget -O models/GFPGANv1.4.pth https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth
+}
+
+_checkVolumeContent() {
+  _runAlpine ls -lhA /data/models
+}
+
+_getModelMd5s() {
+  _runAlpine  \
+    alpine sh -c "md5sum /data/models/*"
+}
+
+if [[ -n "$(docker volume ls -f name="${volumename}" -q)" ]]; then
+  echo "Volume already exists"
+  if [[ -z "$(_checkVolumeContent)" ]]; then
+    echo "looks empty, copying checkpoint"
+    _copyCheckpoints
+  fi
+  echo "Models in ${volumename}:"
+  _checkVolumeContent
+else
+  echo -n "createing docker volume "
+  docker volume create "${volumename}"
+  _copyCheckpoints
+fi
+
+# Build Container
+docker build \
+  --platform="${platform}" \
+  --tag "${invokeai_tag}" \
+  --build-arg project_name="${project_name}" \
+  --build-arg conda_version="${invokeai_conda_version}" \
+  --build-arg conda_prefix="${invokeai_conda_prefix}" \
+  --build-arg conda_env_file="${invokeai_conda_env_file}" \
+  --build-arg invokeai_git="${invokeai_git}" \
+  --file ./docker-build/Dockerfile \
+  .

docker-build/entrypoint.sh

@@ -1,10 +1,8 @@
 #!/bin/bash
+set -e
 
-cd /stable-diffusion
+source "${CONDA_PREFIX}/etc/profile.d/conda.sh"
+conda activate "${PROJECT_NAME}"
 
-if [ $# -eq 0 ]; then
-    python3 scripts/dream.py --full_precision -o /data
-    # bash
-else
-    python3 scripts/dream.py --full_precision -o /data "$@"
-fi
+python scripts/invoke.py \
+  ${@:---web --host=0.0.0.0}

docker-build/env.sh

@@ -0,0 +1,13 @@
+#!/usr/bin/env bash
+
+project_name=${PROJECT_NAME:-invokeai}
+volumename=${VOLUMENAME:-${project_name}_data}
+arch=${ARCH:-x86_64}
+platform=${PLATFORM:-Linux/${arch}}
+invokeai_tag=${INVOKEAI_TAG:-${project_name}-${arch}}
+
+export project_name
+export volumename
+export arch
+export platform
+export invokeai_tag

docker-build/run.sh

@@ -0,0 +1,15 @@
+#!/usr/bin/env bash
+set -e
+
+source ./docker-build/env.sh || echo "please run from repository root" || exit 1
+
+docker run \
+  --interactive \
+  --tty \
+  --rm \
+  --platform "$platform" \
+  --name "$project_name" \
+  --hostname "$project_name" \
+  --mount source="$volumename",target=/data \
+  --publish 9090:9090 \
+  "$invokeai_tag" ${1:+$@}

docs/assets/preflight-checks/outputs/invoke_log.md

@@ -0,0 +1,116 @@
+## 000001.1863159593.png
+![](000001.1863159593.png)
+
+banana sushi -s 50 -S 1863159593 -W 512 -H 512 -C 7.5 -A k_lms
+## 000002.1151955949.png
+![](000002.1151955949.png)
+
+banana sushi -s 50 -S 1151955949 -W 512 -H 512 -C 7.5 -A plms
+## 000003.2736230502.png
+![](000003.2736230502.png)
+
+banana sushi -s 50 -S 2736230502 -W 512 -H 512 -C 7.5 -A ddim
+## 000004.42.png
+![](000004.42.png)
+
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms
+## 000005.42.png
+![](000005.42.png)
+
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms
+## 000006.478163327.png
+![](000006.478163327.png)
+
+banana sushi -s 50 -S 478163327 -W 640 -H 448 -C 7.5 -A k_lms
+## 000007.2407640369.png
+![](000007.2407640369.png)
+
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 2407640369:0.1
+## 000008.2772421987.png
+![](000008.2772421987.png)
+
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 2772421987:0.1
+## 000009.3532317557.png
+![](000009.3532317557.png)
+
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 3532317557:0.1
+## 000010.2028635318.png
+![](000010.2028635318.png)
+
+banana sushi -s 50 -S 2028635318 -W 512 -H 512 -C 7.5 -A k_lms
+## 000011.1111168647.png
+![](000011.1111168647.png)
+
+pond with waterlillies -s 50 -S 1111168647 -W 512 -H 512 -C 7.5 -A k_lms
+## 000012.1476370516.png
+![](000012.1476370516.png)
+
+pond with waterlillies -s 50 -S 1476370516 -W 512 -H 512 -C 7.5 -A k_lms
+## 000013.4281108706.png
+![](000013.4281108706.png)
+
+banana sushi -s 50 -S 4281108706 -W 960 -H 960 -C 7.5 -A k_lms
+## 000014.2396987386.png
+![](000014.2396987386.png)
+
+old sea captain with crow on shoulder -s 50 -S 2396987386 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A k_lms -f 0.75
+## 000015.1252923272.png
+![](000015.1252923272.png)
+
+old sea captain with crow on shoulder -s 50 -S 1252923272 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512-transparent.png -A k_lms -f 0.75
+## 000016.2633891320.png
+![](000016.2633891320.png)
+
+old sea captain with crow on shoulder -s 50 -S 2633891320 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A plms -f 0.75
+## 000017.1134411920.png
+![](000017.1134411920.png)
+
+old sea captain with crow on shoulder -s 50 -S 1134411920 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A k_euler_a -f 0.75
+## 000018.47.png
+![](000018.47.png)
+
+big red dog playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+## 000019.47.png
+![](000019.47.png)
+
+big red++++ dog playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+## 000020.47.png
+![](000020.47.png)
+
+big red dog playing with cat+++ -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+## 000021.47.png
+![](000021.47.png)
+
+big (red dog).swap(tiger) playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+## 000022.47.png
+![](000022.47.png)
+
+dog:1,cat:2 -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+## 000023.47.png
+![](000023.47.png)
+
+dog:2,cat:1 -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+## 000024.1029061431.png
+![](000024.1029061431.png)
+
+medusa with cobras -s 50 -S 1029061431 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/curly.png -A k_lms -f 0.75 -tm hair
+## 000025.1284519352.png
+![](000025.1284519352.png)
+
+bearded man -s 50 -S 1284519352 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/curly.png -A k_lms -f 0.75 -tm face
+## curly.942491079.gfpgan.png
+![](curly.942491079.gfpgan.png)
+
+!fix ./docs/assets/preflight-checks/inputs/curly.png -s 50 -S 942491079 -W 512 -H 512 -C 7.5 -A k_lms -G 0.8 -ft gfpgan -U 2.0 0.75
+## curly.942491079.outcrop.png
+![](curly.942491079.outcrop.png)
+
+!fix ./docs/assets/preflight-checks/inputs/curly.png -s 50 -S 942491079 -W 512 -H 512 -C 7.5 -A k_lms -c top 64
+## curly.942491079.outpaint.png
+![](curly.942491079.outpaint.png)
+
+!fix ./docs/assets/preflight-checks/inputs/curly.png -s 50 -S 942491079 -W 512 -H 512 -C 7.5 -A k_lms -D top 64
+## curly.942491079.outcrop-01.png
+![](curly.942491079.outcrop-01.png)
+
+!fix ./docs/assets/preflight-checks/inputs/curly.png -s 50 -S 942491079 -W 512 -H 512 -C 7.5 -A k_lms -c top 64

docs/assets/preflight-checks/outputs/invoke_log.txt

@@ -0,0 +1,29 @@
+outputs/preflight/000001.1863159593.png: banana sushi -s 50 -S 1863159593 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000002.1151955949.png: banana sushi -s 50 -S 1151955949 -W 512 -H 512 -C 7.5 -A plms
+outputs/preflight/000003.2736230502.png: banana sushi -s 50 -S 2736230502 -W 512 -H 512 -C 7.5 -A ddim
+outputs/preflight/000004.42.png: banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000005.42.png: banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000006.478163327.png: banana sushi -s 50 -S 478163327 -W 640 -H 448 -C 7.5 -A k_lms
+outputs/preflight/000007.2407640369.png: banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 2407640369:0.1
+outputs/preflight/000008.2772421987.png: banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 2772421987:0.1
+outputs/preflight/000009.3532317557.png: banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 3532317557:0.1
+outputs/preflight/000010.2028635318.png: banana sushi -s 50 -S 2028635318 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000011.1111168647.png: pond with waterlillies -s 50 -S 1111168647 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000012.1476370516.png: pond with waterlillies -s 50 -S 1476370516 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000013.4281108706.png: banana sushi -s 50 -S 4281108706 -W 960 -H 960 -C 7.5 -A k_lms
+outputs/preflight/000014.2396987386.png: old sea captain with crow on shoulder -s 50 -S 2396987386 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A k_lms -f 0.75
+outputs/preflight/000015.1252923272.png: old sea captain with crow on shoulder -s 50 -S 1252923272 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512-transparent.png -A k_lms -f 0.75
+outputs/preflight/000016.2633891320.png: old sea captain with crow on shoulder -s 50 -S 2633891320 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A plms -f 0.75
+outputs/preflight/000017.1134411920.png: old sea captain with crow on shoulder -s 50 -S 1134411920 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A k_euler_a -f 0.75
+outputs/preflight/000018.47.png: big red dog playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000019.47.png: big red++++ dog playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000020.47.png: big red dog playing with cat+++ -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000021.47.png: big (red dog).swap(tiger) playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000022.47.png: dog:1,cat:2 -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000023.47.png: dog:2,cat:1 -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000024.1029061431.png: medusa with cobras -s 50 -S 1029061431 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/curly.png -A k_lms -f 0.75 -tm hair
+outputs/preflight/000025.1284519352.png: bearded man -s 50 -S 1284519352 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/curly.png -A k_lms -f 0.75 -tm face
+outputs/preflight/curly.942491079.gfpgan.png: !fix ./docs/assets/preflight-checks/inputs/curly.png -s 50 -S 942491079 -W 512 -H 512 -C 7.5 -A k_lms -G 0.8 -ft gfpgan -U 2.0 0.75
+outputs/preflight/curly.942491079.outcrop.png: !fix ./docs/assets/preflight-checks/inputs/curly.png -s 50 -S 942491079 -W 512 -H 512 -C 7.5 -A k_lms -c top 64
+outputs/preflight/curly.942491079.outpaint.png: !fix ./docs/assets/preflight-checks/inputs/curly.png -s 50 -S 942491079 -W 512 -H 512 -C 7.5 -A k_lms -D top 64
+outputs/preflight/curly.942491079.outcrop-01.png: !fix ./docs/assets/preflight-checks/inputs/curly.png -s 50 -S 942491079 -W 512 -H 512 -C 7.5 -A k_lms -c top 64

docs/assets/preflight-checks/preflight_prompts.txt

@@ -0,0 +1,61 @@
+# outputs/preflight/000001.1863159593.png
+banana sushi -s 50 -S 1863159593 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000002.1151955949.png
+banana sushi -s 50 -S 1151955949 -W 512 -H 512 -C 7.5 -A plms
+# outputs/preflight/000003.2736230502.png
+banana sushi -s 50 -S 2736230502 -W 512 -H 512 -C 7.5 -A ddim
+# outputs/preflight/000004.42.png
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000005.42.png
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000006.478163327.png
+banana sushi -s 50 -S 478163327 -W 640 -H 448 -C 7.5 -A k_lms
+# outputs/preflight/000007.2407640369.png
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 2407640369:0.1
+# outputs/preflight/000007.2772421987.png
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 2772421987:0.1
+# outputs/preflight/000007.3532317557.png
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 3532317557:0.1
+# outputs/preflight/000008.2028635318.png
+banana sushi -s 50 -S 2028635318 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000009.1111168647.png
+pond with waterlillies -s 50 -S 1111168647 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000010.1476370516.png
+pond with waterlillies -s 50 -S 1476370516 -W 512 -H 512 -C 7.5 -A k_lms --seamless
+# outputs/preflight/000011.4281108706.png
+banana sushi -s 50 -S 4281108706 -W 960 -H 960 -C 7.5 -A k_lms
+# outputs/preflight/000012.2396987386.png
+old sea captain with crow on shoulder -s 50 -S 2396987386 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A k_lms -f 0.75
+# outputs/preflight/000013.1252923272.png
+old sea captain with crow on shoulder -s 50 -S 1252923272 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512-transparent.png -A k_lms -f 0.75
+# outputs/preflight/000014.2633891320.png
+old sea captain with crow on shoulder -s 50 -S 2633891320 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A plms -f 0.75
+# outputs/preflight/000015.1134411920.png
+old sea captain with crow on shoulder -s 50 -S 1134411920 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A k_euler_a -f 0.75
+# outputs/preflight/000016.42.png
+big red dog playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000017.42.png
+big red++++ dog playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000018.42.png
+big red dog playing with cat+++ -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000019.42.png
+big (red dog).swap(tiger) playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000020.42.png
+dog:1,cat:2 -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000021.42.png
+dog:2,cat:1 -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000022.1029061431.png
+medusa with cobras -s 50 -S 1029061431 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/curly.png -A k_lms -f 0.75 -tm hair
+# outputs/preflight/000023.1284519352.png
+bearded man -s 50 -S 1284519352 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/curly.png -A k_lms -f 0.75 -tm face
+# outputs/preflight/000024.curly.hair.deselected.png
+!mask -I docs/assets/preflight-checks/inputs/curly.png -tm hair
+# outputs/preflight/curly.942491079.gfpgan.png
+!fix ./docs/assets/preflight-checks/inputs/curly.png -U2 -G0.8
+# outputs/preflight/curly.942491079.outcrop.png
+!fix ./docs/assets/preflight-checks/inputs/curly.png -c top 64
+# outputs/preflight/curly.942491079.outpaint.png
+!fix ./docs/assets/preflight-checks/inputs/curly.png -D top 64
+# outputs/preflight/curly.942491079.outcrop-01.png
+!switch inpainting-1.5
+!fix ./docs/assets/preflight-checks/inputs/curly.png -c top 64

docs/features/CLI.md

@@ -8,7 +8,7 @@ hide:
 
 ## **Interactive Command Line Interface**
 
-The `invoke.py` script, located in `scripts/dream.py`, provides an interactive
+The `invoke.py` script, located in `scripts/`, provides an interactive
 interface to image generation similar to the "invoke mothership" bot that Stable
 AI provided on its Discord server.
 
@@ -85,6 +85,8 @@ overridden on a per-prompt basis (see [List of prompt arguments](#list-of-prompt
 | `--from_file <path>`                      |                                           | `None`                                         | Read list of prompts from a file. Use `-` to read from standard input                                |
 | `--model <modelname>`                     |                                           | `stable-diffusion-1.4`                         | Loads model specified in configs/models.yaml. Currently one of "stable-diffusion-1.4" or "laion400m" |
 | `--full_precision`                        | `-F`                                      | `False`                                        | Run in slower full-precision mode. Needed for Macintosh M1/M2 hardware and some older video cards.   |
+| `--png_compression <0-9>`                 | `-z<0-9>`                                 |  6                                             | Select level of compression for output files, from 0 (no compression) to 9 (max compression)         |
+| `--safety-checker`                        |                                           |  False                                         | Activate safety checker for NSFW and other potentially disturbing imagery                            |
 | `--web`                                   |                                           | `False`                                        | Start in web server mode                                                                             |
 | `--host <ip addr>`                        |                                           | `localhost`                                    | Which network interface web server should listen on. Set to 0.0.0.0 to listen on any.                |
 | `--port <port>`                           |                                           | `9090`                                         | Which port web server should listen for requests on.                                                 |
@@ -96,7 +98,6 @@ overridden on a per-prompt basis (see [List of prompt arguments](#list-of-prompt
 | `--embedding_path <path>`                 |                                           | `None`                                         | Path to pre-trained embedding manager checkpoints, for custom models                                 |
 | `--gfpgan_dir`                            |                                           | `src/gfpgan`                                   | Path to where GFPGAN is installed.                                                                   |
 | `--gfpgan_model_path`                     |                                           | `experiments/pretrained_models/GFPGANv1.4.pth` | Path to GFPGAN model file, relative to `--gfpgan_dir`.                                               |
-| `--device <device>`                       | `-d<device>`                              | `torch.cuda.current_device()`                  | Device to run SD on, e.g. "cuda:0"                                                                   |
 | `--free_gpu_mem`                          |                                           | `False`                                        | Free GPU memory after sampling, to allow image decoding and saving in low VRAM conditions            |
 | `--precision`                             |                                           | `auto`                                         | Set model precision, default is selected by device. Options: auto, float32, float16, autocast        |
 
@@ -144,46 +145,49 @@ Here are the invoke> command that apply to txt2img:
 
 | Argument <img width="680" align="right"/> | Shortcut <img width="420" align="right"/> | Default <img width="480" align="right"/> | Description |
 |--------------------|------------|---------------------|--------------|
-| `"my prompt"`        |            |                    | Text prompt to use. The quotation marks are optional. |
-| `--width <int>`      | `-W<int>`   | `512`                 | Width of generated image |
-| `--height <int>`     | `-H<int>`   | `512`                 | Height of generated image |
-| `--iterations <int>` | `-n<int>`   | `1`                   | How many images to generate from this prompt |
-| `--steps <int>`      | `-s<int>`   | `50`                  | How many steps of refinement to apply |
-| `--cfg_scale <float>`| `-C<float>` | `7.5`                 | How hard to try to match the prompt to the generated image; any number greater than 1.0 works, but the useful range is roughly 5.0 to 20.0 |
-| `--seed <int>`       | `-S<int>`   | `None`                | Set the random seed for the next series of images. This can be used to recreate an image generated previously.|
-| `--sampler <sampler>`| `-A<sampler>`| `k_lms`              | Sampler to use. Use -h to get list of available samplers. |
-| `--hires_fix`        |           |                     | Larger images often have duplication artefacts. This option suppresses duplicates by generating the image at low res, and then using img2img to increase the resolution |
-| `--grid`             | `-g`        | `False`               | Turn on grid mode to return a single image combining all the images generated by this prompt |
-| `--individual`       | `-i`        | `True`                | Turn off grid mode (deprecated; leave off `--grid` instead) |
-| `--outdir <path>`    |  `-o<path>` | `outputs/img_samples`  | Temporarily change the location of these images |
-| `--seamless`         |           | `False`               | Activate seamless tiling for interesting effects |
-| `--log_tokenization` | `-t`        | `False`               | Display a color-coded list of the parsed tokens derived from the prompt |
-| `--skip_normalization`| `-x`       | `False`               | Weighted subprompts will not be normalized. See [Weighted Prompts](./OTHER.md#weighted-prompts) |
-| `--upscale <int> <float>` | `-U <int> <float>` | `-U 1 0.75`| Upscale image by magnification factor (2, 4), and set strength of upscaling (0.0-1.0). If strength not set, will default to 0.75. |
-| `--gfpgan_strength <float>`  | `-G <float>` | `-G0`        | Fix faces using the GFPGAN algorithm; argument indicates how hard the algorithm should try (0.0-1.0) |
-| `--save_original`    | `-save_orig`| `False`               | When upscaling or fixing faces, this will cause the original image to be saved rather than replaced. |
-| `--variation <float>`  |`-v<float>`| `0.0`                 | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](./VARIATIONS.md). |
-| `--with_variations <pattern>` | `-V<pattern>`| `None`      | Combine two or more variations. See [Variations](./VARIATIONS.md) for now to use this. |
+| "my prompt"        |            |                    | Text prompt to use. The quotation marks are optional. |
+| --width <int>      | -W<int>   | 512                 | Width of generated image |
+| --height <int>     | -H<int>   | 512                 | Height of generated image |
+| --iterations <int> | -n<int>   | 1                   | How many images to generate from this prompt |
+| --steps <int>      | -s<int>   | 50                  | How many steps of refinement to apply |
+| --cfg_scale <float>| -C<float> | 7.5                 | How hard to try to match the prompt to the generated image; any number greater than 1.0 works, but the useful range is roughly 5.0 to 20.0 |
+| --seed <int>       | -S<int>   | None                | Set the random seed for the next series of images. This can be used to recreate an image generated previously.|
+| --sampler <sampler>| -A<sampler>| k_lms              | Sampler to use. Use -h to get list of available samplers. |
+| --karras_max <int> |           | 29                  | When using k_* samplers, set the maximum number of steps before shifting from using the Karras noise schedule (good for low step counts) to the LatentDiffusion noise schedule (good for high step counts) This value is sticky. [29] |
+| --hires_fix        |           |                     | Larger images often have duplication artefacts. This option suppresses duplicates by generating the image at low res, and then using img2img to increase the resolution |
+| --png_compression <0-9> | -z<0-9> |  6           | Select level of compression for output files, from 0 (no compression) to 9 (max compression)         |
+| --grid             | -g        | False               | Turn on grid mode to return a single image combining all the images generated by this prompt |
+| --individual       | -i        | True                | Turn off grid mode (deprecated; leave off --grid instead) |
+| --outdir <path>    |  -o<path> | outputs/img_samples  | Temporarily change the location of these images |
+| --seamless         |           | False               | Activate seamless tiling for interesting effects |
+| --seamless_axes    |           | x,y                 | Specify which axes to use circular convolution on. |
+| --log_tokenization | -t        | False               | Display a color-coded list of the parsed tokens derived from the prompt |
+| --skip_normalization| -x       | False               | Weighted subprompts will not be normalized. See [Weighted Prompts](./OTHER.md#weighted-prompts) |
+| --upscale <int> <float> | -U <int> <float> | -U 1 0.75| Upscale image by magnification factor (2, 4), and set strength of upscaling (0.0-1.0). If strength not set, will default to 0.75. |
+| --facetool_strength <float>  | -G <float> | -G0        | Fix faces (defaults to using the GFPGAN algorithm); argument indicates how hard the algorithm should try (0.0-1.0) |
+| --facetool <name> | -ft <name> | -ft gfpgan | Select face restoration algorithm to use: gfpgan, codeformer |
+| --codeformer_fidelity | -cf <float> | 0.75 | Used along with CodeFormer. Takes values between 0 and 1. 0 produces high quality but low accuracy. 1 produces high accuracy but low quality |
+| --save_original    | -save_orig| False               | When upscaling or fixing faces, this will cause the original image to be saved rather than replaced. |
+| --variation <float>  |-v<float>| 0.0                 | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with -S<seed> and -n<int> to generate a series a riffs on a starting image. See [Variations](./VARIATIONS.md). |
+| --with_variations <pattern> |    | None              | Combine two or more variations. See [Variations](./VARIATIONS.md) for now to use this. |
+| --save_intermediates <n>    |    | None              | Save the image from every nth step into an "intermediates" folder inside the output directory |
 
-!!! note
+Note that the width and height of the image must be multiples of
+64. You can provide different values, but they will be rounded down to
+the nearest multiple of 64.
 
-    The width and height of the image must be multiples of
-    64. You can provide different values, but they will be rounded down to
-    the nearest multiple of 64.
 
-### img2img
+### This is an example of img2img:	
 
-!!! example
+~~~~
+invoke> waterfall and rainbow -I./vacation-photo.png -W640 -H480 --fit
+~~~~
 
-    ```bash
-    invoke> waterfall and rainbow -I./vacation-photo.png -W640 -H480 --fit
-    ```
-
-    This will modify the indicated vacation photograph by making it more
-    like the prompt. Results will vary greatly depending on what is in the
-    image. We also ask to `--fit` the image into a box no bigger than
-    640x480. Otherwise the image size will be identical to the provided
-    photo and you may run out of memory if it is large.
+This will modify the indicated vacation photograph by making it more
+like the prompt. Results will vary greatly depending on what is in the
+image. We also ask to --fit the image into a box no bigger than
+640x480. Otherwise the image size will be identical to the provided
+photo and you may run out of memory if it is large.
 
 In addition to the command-line options recognized by txt2img, img2img
 accepts additional options:
@@ -210,16 +214,49 @@ accepts additional options:
     [Inpainting](./INPAINTING.md) for details.
 
 inpainting accepts all the arguments used for txt2img and img2img, as
-well as the --mask (-M) argument:
+well as the --mask (-M) and --text_mask (-tm) arguments:
 
 | Argument <img width="100" align="right"/> |  Shortcut  |  Default            |  Description |
 |--------------------|------------|---------------------|--------------|
 | `--init_mask <path>` | `-M<path>`   | `None`                |Path to an image the same size as the initial_image, with areas for inpainting made transparent.|
+| `--invert_mask   ` |                | False                 |If true, invert the mask so that transparent areas are opaque and vice versa.|
+| `--text_mask <prompt> [<float>]` | `-tm <prompt> [<float>]` | <none>  | Create a mask from a text prompt describing part of the image|
 
-## Convenience commands
+The mask may either be an image with transparent areas, in which case
+the inpainting will occur in the transparent areas only, or a black
+and white image, in which case all black areas will be painted into.
 
-In addition to the standard image generation arguments, there are a
-series of convenience commands that begin with !:
+`--text_mask` (short form `-tm`) is a way to generate a mask using a
+text description of the part of the image to replace. For example, if
+you have an image of a breakfast plate with a bagel, toast and
+scrambled eggs, you can selectively mask the bagel and replace it with
+a piece of cake this way:
+
+~~~
+invoke> a piece of cake -I /path/to/breakfast.png -tm bagel
+~~~
+
+The algorithm uses <a
+href="https://github.com/timojl/clipseg">clipseg</a> to classify
+different regions of the image. The classifier puts out a confidence
+score for each region it identifies. Generally regions that score
+above 0.5 are reliable, but if you are getting too much or too little
+masking you can adjust the threshold down (to get more mask), or up
+(to get less). In this example, by passing `-tm` a higher value, we
+are insisting on a more stringent classification.
+
+~~~
+invoke> a piece of cake -I /path/to/breakfast.png -tm bagel 0.6
+~~~
+
+# Other Commands
+
+The CLI offers a number of commands that begin with "!".
+
+## Postprocessing images
+
+To postprocess a file using face restoration or upscaling, use the
+`!fix` command.
 
 ### `!fix`
 
@@ -252,29 +289,171 @@ Some examples:
     Outputs:
     [1] outputs/img-samples/000017.4829112.gfpgan-00.png: !fix "outputs/img-samples/0000045.4829112.png" -s 50 -S  -W 512 -H 512 -C 7.5 -A k_lms -G 0.8
 
+### !mask
+
+This command takes an image, a text prompt, and uses the `clipseg`
+algorithm to automatically generate a mask of the area that matches
+the text prompt. It is useful for debugging the text masking process
+prior to inpainting with the `--text_mask` argument. See
+[INPAINTING.md] for details.
+
+## Model selection and importation
+
+The CLI allows you to add new models on the fly, as well as to switch
+among them rapidly without leaving the script.
+
+### !models
+
+This prints out a list of the models defined in `config/models.yaml'.
+The active model is bold-faced
+
+Example:
+<pre>
+laion400m                 not loaded  <no description>
+<b>stable-diffusion-1.4          active  Stable Diffusion v1.4</b>
+waifu-diffusion           not loaded  Waifu Diffusion v1.3
+</pre>
+
+### !switch <model>
+
+This quickly switches from one model to another without leaving the 
+CLI script. `invoke.py` uses a memory caching system; once a model
+has been loaded, switching back and forth is quick. The following
+example shows this in action. Note how the second column of the 
+`!models` table changes to `cached` after a model is first loaded,
+and that the long initialization step is not needed when loading
+a cached model.
+
+<pre>
+invoke> !models
+laion400m                 not loaded  <no description>
+<b>stable-diffusion-1.4          cached  Stable Diffusion v1.4</b>
+waifu-diffusion               active  Waifu Diffusion v1.3
+
+invoke> !switch waifu-diffusion
+>> Caching model stable-diffusion-1.4 in system RAM
+>> Loading waifu-diffusion from models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt
+   | LatentDiffusion: Running in eps-prediction mode
+   | DiffusionWrapper has 859.52 M params.
+   | Making attention of type 'vanilla' with 512 in_channels
+   | Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
+   | Making attention of type 'vanilla' with 512 in_channels
+   | Using faster float16 precision
+>> Model loaded in 18.24s
+>> Max VRAM used to load the model: 2.17G 
+>> Current VRAM usage:2.17G
+>> Setting Sampler to k_lms
+
+invoke> !models
+laion400m                 not loaded  <no description>
+stable-diffusion-1.4          cached  Stable Diffusion v1.4
+<b>waifu-diffusion               active  Waifu Diffusion v1.3</b>
+
+invoke> !switch stable-diffusion-1.4
+>> Caching model waifu-diffusion in system RAM
+>> Retrieving model stable-diffusion-1.4 from system RAM cache
+>> Setting Sampler to k_lms
+
+invoke> !models
+laion400m                 not loaded  <no description>
+<b>stable-diffusion-1.4          active  Stable Diffusion v1.4</b>
+waifu-diffusion               cached  Waifu Diffusion v1.3
+</pre>
+
+### !import_model <path/to/model/weights>
+
+This command imports a new model weights file into InvokeAI, makes it
+available for image generation within the script, and writes out the
+configuration for the model into `config/models.yaml` for use in 
+subsequent sessions.
+
+Provide `!import_model` with the path to a weights file ending in
+`.ckpt`.  If you type a partial path and press tab, the CLI will
+autocomplete. Although it will also autocomplete to `.vae` files,
+these are not currenty supported (but will be soon).
+
+When you hit return, the CLI will prompt you to fill in additional
+information about the model, including the short name you wish to use
+for it with the `!switch` command, a brief description of the model,
+the default image width and height to use with this model, and the
+model's configuration file. The latter three fields are automatically
+filled with reasonable defaults. In the example below, the bold-faced
+text shows what the user typed in with the exception of the width,
+height and configuration file paths, which were filled in
+automatically.
+
+Example:
+
+<pre>
+invoke> <b>!import_model models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt</b>
+>> Model import in process. Please enter the values needed to configure this model:
+
+Name for this model: <b>waifu-diffusion</b>
+Description of this model: <b>Waifu Diffusion v1.3</b>
+Configuration file for this model: <b>configs/stable-diffusion/v1-inference.yaml</b>
+Default image width: <b>512</b>
+Default image height: <b>512</b>
+>> New configuration:
+waifu-diffusion:
+  config: configs/stable-diffusion/v1-inference.yaml
+  description: Waifu Diffusion v1.3
+  height: 512
+  weights: models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt
+  width: 512
+OK to import [n]? <b>y</b>
+>> Caching model stable-diffusion-1.4 in system RAM
+>> Loading waifu-diffusion from models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt
+   | LatentDiffusion: Running in eps-prediction mode
+   | DiffusionWrapper has 859.52 M params.
+   | Making attention of type 'vanilla' with 512 in_channels
+   | Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
+   | Making attention of type 'vanilla' with 512 in_channels
+   | Using faster float16 precision
+invoke> 
+</pre>
+
+###!edit_model <name_of_model>
+
+The `!edit_model` command can be used to modify a model that is
+already defined in `config/models.yaml`. Call it with the short
+name of the model you wish to modify, and it will allow you to
+modify the model's `description`, `weights` and other fields.
+
+Example:
+<pre>
+invoke> <b>!edit_model waifu-diffusion</b>
+>> Editing model waifu-diffusion from configuration file ./configs/models.yaml
+description: <b>Waifu diffusion v1.4beta</b>
+weights: models/ldm/stable-diffusion-v1/<b>model-epoch10-float16.ckpt</b>
+config: configs/stable-diffusion/v1-inference.yaml
+width: 512
+height: 512
+
+>> New configuration:
+waifu-diffusion:
+  config: configs/stable-diffusion/v1-inference.yaml
+  description: Waifu diffusion v1.4beta
+  weights: models/ldm/stable-diffusion-v1/model-epoch10-float16.ckpt
+  height: 512
+  width: 512
+
+OK to import [n]? y
+>> Caching model stable-diffusion-1.4 in system RAM
+>> Loading waifu-diffusion from models/ldm/stable-diffusion-v1/model-epoch10-float16.ckpt
+...
+</pre>
+=======
     invoke> !fix 000017.4829112.gfpgan-00.png --embiggen 3
     ...lots of text...
     Outputs:
     [2] outputs/img-samples/000018.2273800735.embiggen-00.png: !fix "outputs/img-samples/000017.243781548.gfpgan-00.png" -s 50 -S 2273800735 -W 512 -H 512 -C 7.5 -A k_lms --embiggen 3.0 0.75 0.25
     ```
+## History processing
 
-### `!fetch`
+The CLI provides a series of convenient commands for reviewing previous
+actions, retrieving them, modifying them, and re-running them.
 
-This command retrieves the generation parameters from a previously
-generated image and either loads them into the command line.  You may
-provide either the name of a file in the current output directory, or
-a full file path.
-
-```bash
-invoke> !fetch 0000015.8929913.png
-# the script returns the next line, ready for editing and running:
-invoke> a fantastic alien landscape -W 576 -H 512 -s 60 -A plms -C 7.5
-```
-
-Note that this command may behave unexpectedly if given a PNG file that
-was not generated by InvokeAI.
-
-### `!history`
+### !history
 
 The invoke script keeps track of all the commands you issue during a
 session, allowing you to re-run them. On Mac and Linux systems, it
@@ -299,7 +478,44 @@ invoke> !20
 invoke> watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
 ```
 
-### `!search <search string>`
+### !fetch
+
+This command retrieves the generation parameters from a previously
+generated image and either loads them into the command line
+(Linux|Mac), or prints them out in a comment for copy-and-paste
+(Windows). You may provide either the name of a file in the current
+output directory, or a full file path.  Specify path to a folder with
+image png files, and wildcard *.png to retrieve the dream command used
+to generate the images, and save them to a file commands.txt for
+further processing.
+
+This example loads the generation command for a single png file:
+
+```bash
+invoke> !fetch 0000015.8929913.png
+# the script returns the next line, ready for editing and running:
+invoke> a fantastic alien landscape -W 576 -H 512 -s 60 -A plms -C 7.5
+```
+
+This one fetches the generation commands from a batch of files and
+stores them into `selected.txt`:
+
+```bash
+invoke> !fetch outputs\selected-imgs\*.png selected.txt
+```
+
+### !replay
+
+This command replays a text file generated by !fetch or created manually
+
+~~~
+invoke> !replay outputs\selected-imgs\selected.txt
+~~~
+
+Note that these commands may behave unexpectedly if given a PNG file that
+was not generated by InvokeAI.
+
+### !search <search string>
 
 This is similar to !history but it only returns lines that contain
 `search string`. For example:

docs/features/IMG2IMG.md

@@ -59,16 +59,13 @@ information underneath the transparent needs to be preserved, not erased.
 
 !!! warning
 
-    `img2img` does not work properly on initial images smaller than 512x512. Please scale your
-    image to at least 512x512 before using it. Larger images are not a problem, but may run out of VRAM on your
-    GPU card.
-
-    To fix this, use the `--fit` option, which downscales the initial image to fit within the box specified
-    by width x height:
-
-    ```bash
-    invoke> "tree on a hill with a river, national geographic" -I./test-pictures/big-sketch.png -H512 -W512 --fit
-    ```
+**IMPORTANT ISSUE** `img2img` does not work properly on initial images smaller than 512x512. Please scale your
+image to at least 512x512 before using it. Larger images are not a problem, but may run out of VRAM on your
+GPU card. To fix this, use the --fit option, which downscales the initial image to fit within the box specified
+by width x height:
+~~~
+tree on a hill with a river, national geographic -I./test-pictures/big-sketch.png -H512 -W512 --fit
+~~~
 
 ## How does it actually work, though?
 
@@ -78,7 +75,7 @@ gaussian noise and progressively refines it over the requested number of steps,
 
 **Let's start** by thinking about vanilla `prompt2img`, just generating an image from a prompt. If the step count is 10, then the "latent space" (Stable Diffusion's internal representation of the image) for the prompt "fire" with seed `1592514025` develops something like this:
 
-```bash
+```commandline
 invoke> "fire" -s10 -W384 -H384 -S1592514025
 ```
 
@@ -113,9 +110,9 @@ With strength `0.4`, the steps look more like this:
 Notice how much more fuzzy the starting image is for strength `0.7` compared to `0.4`, and notice also how much longer the sequence is with `0.7`:
 
 |  | strength = 0.7 | strength = 0.4 |
-| -- | :--: | :--: |
-| initial image that SD sees | ![step-0-32](../assets/img2img/000032.step-0.png) | ![step-0-30](../assets/img2img/000030.step-0.png) |
-| steps argument to `dream>` | `-S10` | `-S10` |
+| -- | -- | -- |
+| initial image that SD sees | ![](../assets/img2img/000032.step-0.png) | ![](../assets/img2img/000030.step-0.png) |
+| steps argument to `invoke>` | `-S10` | `-S10` |
 | steps actually taken | 7 | 4 |
 | latent space at each step | ![gravity32](../assets/img2img/000032.steps.gravity.png) | ![gravity30](../assets/img2img/000030.steps.gravity.png) |
 | output | ![000032.1592514025](../assets/img2img/000032.1592514025.png) | ![000030.1592514025](../assets/img2img/000030.1592514025.png) |
@@ -124,11 +121,11 @@ Both of the outputs look kind of like what I was thinking of. With the strength
 
 If you want to try this out yourself, all of these are using a seed of `1592514025` with a width/height of `384`, step count `10`, the default sampler (`k_lms`), and the single-word prompt `"fire"`:
 
-```bash
+```commandline
 invoke> "fire" -s10 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png --strength 0.7
 ```
 
-The code for rendering intermediates is on my (damian0815's) branch [document-img2img](https://github.com/damian0815/InvokeAI/tree/document-img2img) - run `invoke.py` and check your `outputs/img-samples/intermediates` folder while generating an image.
+The code for rendering intermediates is on my (damian0815's) branch [document-img2img](https://github.com/damian0815/InvokeAI/tree/document-img2img) - run `invoke.py` and check your `outputs/img-samples/intermediates` folder while generating an image. 
 
 ### Compensating for the reduced step count
 
@@ -136,7 +133,7 @@ After putting this guide together I was curious to see how the difference would
 
 Here's strength `0.4` (note step count `50`, which is `20 ÷ 0.4` to make sure SD does `20` steps from my image):
 
-```bash
+```commandline
 invoke> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
 ```
 
@@ -146,7 +143,7 @@ invoke> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
 
 and here is strength `0.7` (note step count `30`, which is roughly `20 ÷ 0.7` to make sure SD does `20` steps from my image):
 
-```bash
+```commandline
 invoke> "fire" -s30 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.7
 ```
 

docs/features/INPAINTING.md

@@ -6,27 +6,234 @@ title: Inpainting
 
 ## **Creating Transparent Regions for Inpainting**
 
-Inpainting is really cool. To do it, you start with an initial image and use a photoeditor to make
-one or more regions transparent (i.e. they have a "hole" in them). You then provide the path to this
-image at the invoke> command line using the `-I` switch. Stable Diffusion will only paint within the
-transparent region.
+Inpainting is really cool. To do it, you start with an initial image
+and use a photoeditor to make one or more regions transparent
+(i.e. they have a "hole" in them). You then provide the path to this
+image at the dream> command line using the `-I` switch. Stable
+Diffusion will only paint within the transparent region.
 
-There's a catch. In the current implementation, you have to prepare the initial image correctly so
-that the underlying colors are preserved under the transparent area. Many imaging editing
-applications will by default erase the color information under the transparent pixels and replace
-them with white or black, which will lead to suboptimal inpainting. You also must take care to
-export the PNG file in such a way that the color information is preserved.
+There's a catch. In the current implementation, you have to prepare
+the initial image correctly so that the underlying colors are
+preserved under the transparent area. Many imaging editing
+applications will by default erase the color information under the
+transparent pixels and replace them with white or black, which will
+lead to suboptimal inpainting. It often helps to apply incomplete
+transparency, such as any value between 1 and 99%
 
-If your photoeditor is erasing the underlying color information, `invoke.py` will give you a big fat
-warning. If you can't find a way to coax your photoeditor to retain color values under transparent
-areas, then you can combine the `-I` and `-M` switches to provide both the original unedited image
-and the masked (partially transparent) image:
+You also must take care to export the PNG file in such a way that the
+color information is preserved. There is often an option in the export
+dialog that lets you specify this.
+
+If your photoeditor is erasing the underlying color information,
+`dream.py` will give you a big fat warning. If you can't find a way to
+coax your photoeditor to retain color values under transparent areas,
+then you can combine the `-I` and `-M` switches to provide both the
+original unedited image and the masked (partially transparent) image:
 
 ```bash
 invoke> "man with cat on shoulder" -I./images/man.png -M./images/man-transparent.png
 ```
 
-We are hoping to get rid of the need for this workaround in an upcoming release.
+## **Masking using Text**
+
+You can also create a mask using a text prompt to select the part of
+the image you want to alter, using the <a
+href="https://github.com/timojl/clipseg">clipseg</a> algorithm. This
+works on any image, not just ones generated by InvokeAI.
+
+The `--text_mask` (short form `-tm`) option takes two arguments. The
+first argument is a text description of the part of the image you wish
+to mask (paint over). If the text description contains a space, you must
+surround it with quotation marks. The optional second argument is the
+minimum threshold for the mask classifier's confidence score, described
+in more detail below.
+
+To see how this works in practice, here's an image of a still life
+painting that I got off the web.
+
+<img src="../assets/still-life-scaled.jpg">
+
+You can selectively mask out the
+orange and replace it with a baseball in this way:
+
+~~~
+invoke> a baseball -I /path/to/still_life.png -tm orange
+~~~
+
+<img src="../assets/still-life-inpainted.png">
+
+The clipseg classifier produces a confidence score for each region it
+identifies. Generally regions that score above 0.5 are reliable, but
+if you are getting too much or too little masking you can adjust the
+threshold down (to get more mask), or up (to get less). In this
+example, by passing `-tm` a higher value, we are insisting on a tigher
+mask. However, if you make it too high, the orange may not be picked
+up at all!
+
+~~~
+invoke> a baseball -I /path/to/breakfast.png -tm orange 0.6
+~~~
+
+The `!mask` command may be useful for debugging problems with the
+text2mask feature. The syntax is `!mask /path/to/image.png -tm <text>
+<threshold>`
+
+It will generate three files:
+
+- The image with the selected area highlighted.
+  - it will be named XXXXX.<imagename>.<prompt>.selected.png
+- The image with the un-selected area highlighted.
+  - it will be named XXXXX.<imagename>.<prompt>.deselected.png
+- The image with the selected area converted into a black and white
+  image according to the threshold level
+  - it will be named XXXXX.<imagename>.<prompt>.masked.png
+
+The `.masked.png` file can then be directly passed to the `invoke>`
+prompt in the CLI via the `-M` argument. Do not attempt this with
+the `selected.png` or `deselected.png` files, as they contain some
+transparency throughout the image and will not produce the desired
+results.
+
+Here is an example of how `!mask` works:
+
+```
+invoke> !mask ./test-pictures/curly.png -tm hair 0.5
+>> generating masks from ./test-pictures/curly.png
+>> Initializing clipseg model for text to mask inference
+Outputs:
+[941.1] outputs/img-samples/000019.curly.hair.deselected.png: !mask ./test-pictures/curly.png -tm hair 0.5
+[941.2] outputs/img-samples/000019.curly.hair.selected.png: !mask ./test-pictures/curly.png -tm hair 0.5
+[941.3] outputs/img-samples/000019.curly.hair.masked.png: !mask ./test-pictures/curly.png -tm hair 0.5
+```
+
+**Original image "curly.png"**
+<img src="../assets/outpainting/curly.png">
+
+**000019.curly.hair.selected.png**
+<img src="../assets/inpainting/000019.curly.hair.selected.png">
+
+**000019.curly.hair.deselected.png**
+<img src="../assets/inpainting/000019.curly.hair.deselected.png">
+
+**000019.curly.hair.masked.png**
+<img src="../assets/inpainting/000019.curly.hair.masked.png">
+
+It looks like we selected the hair pretty well at the 0.5 threshold
+(which is the default, so we didn't actually have to specify it), so
+let's have some fun:
+
+```
+invoke> medusa with cobras -I ./test-pictures/curly.png -M 000019.curly.hair.masked.png -C20
+>> loaded input image of size 512x512 from ./test-pictures/curly.png
+...
+Outputs:
+[946] outputs/img-samples/000024.801380492.png: "medusa with cobras" -s 50 -S 801380492 -W 512 -H 512 -C 20.0 -I ./test-pictures/curly.png -A k_lms -f 0.75
+```
+
+<img src="../assets/inpainting/000024.801380492.png">
+
+You can also skip the `!mask` creation step and just select the masked
+
+region directly:
+```
+invoke> medusa with cobras -I ./test-pictures/curly.png -tm hair -C20
+```
+
+## Using the RunwayML inpainting model
+
+The [RunwayML Inpainting Model
+v1.5](https://huggingface.co/runwayml/stable-diffusion-inpainting) is
+a specialized version of [Stable Diffusion
+v1.5](https://huggingface.co/spaces/runwayml/stable-diffusion-v1-5)
+that contains extra channels specifically designed to enhance
+inpainting and outpainting. While it can do regular `txt2img` and
+`img2img`, it really shines when filling in missing regions. It has an
+almost uncanny ability to blend the new regions with existing ones in
+a semantically coherent way.
+
+To install the inpainting model, follow the
+[instructions](INSTALLING-MODELS.md) for installing a new model. You
+may use either the CLI (`invoke.py` script) or directly edit the
+`configs/models.yaml` configuration file to do this. The main thing to
+watch out for is that the the model `config` option must be set up to
+use `v1-inpainting-inference.yaml` rather than the `v1-inference.yaml`
+file that is used by Stable Diffusion 1.4 and 1.5.
+
+After installation, your `models.yaml` should contain an entry that
+looks like this one:
+
+ inpainting-1.5:
+   weights: models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt
+   description: SD inpainting v1.5
+   config: configs/stable-diffusion/v1-inpainting-inference.yaml
+   vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
+   width: 512
+   height: 512
+
+As shown in the example, you may include a VAE fine-tuning weights
+file as well. This is strongly recommended.
+
+To use the custom inpainting model, launch `invoke.py` with the
+argument `--model inpainting-1.5` or alternatively from within the
+script use the `!switch inpainting-1.5` command to load and switch to
+the inpainting model.
+
+You can now do inpainting and outpainting exactly as described above,
+but there will (likely) be a noticeable improvement in
+coherence. Txt2img and Img2img will work as well.
+
+There are a few caveats to be aware of:
+
+1. The inpainting model is larger than the standard model, and will
+   use nearly 4 GB of GPU VRAM. This makes it unlikely to run on
+   a 4 GB graphics card.
+
+2. When operating in Img2img mode, the inpainting model is much less
+   steerable than the standard model. It is great for making small
+   changes, such as changing the pattern of a fabric, or slightly
+   changing a subject's expression or hair, but the model will
+   resist making the dramatic alterations that the standard
+   model lets you do.
+
+3. While the `--hires` option works fine with the inpainting model,
+   some special features, such as `--embiggen` are disabled.
+
+4. Prompt weighting (`banana++ sushi`) and merging work well with
+   the inpainting model, but prompt swapping (a ("fluffy cat").swap("smiling dog") eating a hotdog`)
+   will not have any effect due to the way the model is set up.
+   You may use text masking (with `-tm thing-to-mask`) as an
+   effective replacement.
+
+5. The model tends to oversharpen image if you use high step or CFG
+   values. If you need to do large steps, use the standard model.
+
+6. The `--strength` (`-f`) option has no effect on the inpainting
+   model due to its fundamental differences with the standard
+   model. It will always take the full number of steps you specify.
+
+## Troubleshooting
+
+Here are some troubleshooting tips for inpainting and outpainting.
+
+## Inpainting is not changing the masked region enough!
+
+One of the things to understand about how inpainting works is that it
+is equivalent to running img2img on just the masked (transparent)
+area. img2img builds on top of the existing image data, and therefore
+will attempt to preserve colors, shapes and textures to the best of
+its ability. Unfortunately this means that if you want to make a
+dramatic change in the inpainted region, for example replacing a red
+wall with a blue one, the algorithm will fight you.
+
+You have a couple of options. The first is to increase the values of
+the requested steps (`-sXXX`), strength (`-f0.XX`), and/or
+condition-free guidance (`-CXX.X`). If this is not working for you, a
+more extreme step is to provide the `--inpaint_replace 0.X` (`-r0.X`)
+option. This value ranges from 0.0 to 1.0. The higher it is the less
+attention the algorithm will pay to the data underneath the masked
+region. At high values this will enable you to replace colored regions
+entirely, but beware that the masked region mayl not blend in with the
+surrounding unmasked regions as well.
 
 ---
 
@@ -35,10 +242,10 @@ We are hoping to get rid of the need for this workaround in an upcoming release.
 [GIMP](https://www.gimp.org/) is a popular Linux photoediting tool.
 
 1. Open image in GIMP.
-2. Layer --> Transparency --> Add Alpha Channel
-3. Use lasoo tool to select region to mask
-4. Choose Select --> Float to create a floating selection
-5. Open the Layers toolbar (++ctrl+l++) and select "Floating Selection"
+2. Layer->Transparency->Add Alpha Channel
+3. Use lasso tool to select region to mask
+4. Choose Select -> Float to create a floating selection
+5. Open the Layers toolbar (^L) and select "Floating Selection"
 6. Set opacity to a value between 0% and 99%
 7. Export as PNG
 8. In the export dialogue, Make sure the "Save colour values from
@@ -58,7 +265,7 @@ We are hoping to get rid of the need for this workaround in an upcoming release.
 
 3. Because we'll be applying a mask over the area we want to preserve, you should now select the inverse by using the ++shift+ctrl+i++ shortcut, or right clicking and using the "Select Inverse" option.
 
-4. You'll now create a mask by selecting the image layer, and Masking the selection. Make sure that you don't delete any of the undrlying image, or your inpainting results will be dramatically impacted.
+4. You'll now create a mask by selecting the image layer, and Masking the selection. Make sure that you don't delete any of the underlying image, or your inpainting results will be dramatically impacted.
 
     <div align="center" markdown>![step4](../assets/step4.png)</div>
 

docs/features/OTHER.md

@@ -26,6 +26,12 @@ for each `invoke>` prompt as shown here:
 invoke> "pond garden with lotus by claude monet" --seamless -s100 -n4
 ```
 
+By default this will tile on both the X and Y axes. However, you can also specify specific axes to tile on with `--seamless_axes`.
+Possible values are `x`, `y`, and `x,y`:
+```python
+invoke> "pond garden with lotus by claude monet" --seamless --seamless_axes=x -s100 -n4
+```
+
 ---
 
 ## **Shortcuts: Reusing Seeds**
@@ -69,6 +75,23 @@ combination of integers and floating point numbers, and they do not need to add
 
 ---
 
+## **Filename Format**
+
+The argument `--fnformat` allows to specify the filename of the
+ image. Supported wildcards are all arguments what can be set such as
+ `perlin`, `seed`, `threshold`, `height`, `width`, `gfpgan_strength`,
+ `sampler_name`, `steps`, `model`, `upscale`, `prompt`, `cfg_scale`,
+ `prefix`.
+
+The following prompt
+```bash
+dream> a red car --steps 25 -C 9.8 --perlin 0.1 --fnformat {prompt}_steps.{steps}_cfg.{cfg_scale}_perlin.{perlin}.png
+```
+
+generates a file with the name: `outputs/img-samples/a red car_steps.25_cfg.9.8_perlin.0.1.png`
+
+---
+
 ## **Thresholding and Perlin Noise Initialization Options**
 
 Two new options are the thresholding (`--threshold`) and the perlin noise initialization (`--perlin`) options. Thresholding limits the range of the latent values during optimization, which helps combat oversaturation with higher CFG scale values. Perlin noise initialization starts with a percentage (a value ranging from 0 to 1) of perlin noise mixed into the initial noise. Both features allow for more variations and options in the course of generating images.

docs/features/OUTPAINTING.md

@@ -15,13 +15,52 @@ InvokeAI supports two versions of outpainting, one called "outpaint"
 and the other "outcrop." They work slightly differently and each has
 its advantages and drawbacks.
 
+### Outpainting
+
+Outpainting is the same as inpainting, except that the painting occurs
+in the regions outside of the original image. To outpaint using the
+`invoke.py` command line script, prepare an image in which the borders
+to be extended are pure black. Add an alpha channel (if there isn't one
+already), and make the borders completely transparent and the interior
+completely opaque. If you wish to modify the interior as well, you may
+create transparent holes in the transparency layer, which `img2img` will
+paint into as usual.
+
+Pass the image as the argument to the `-I` switch as you would for
+regular inpainting:
+
+ invoke> a stream by a river -I /path/to/transparent_img.png
+
+You'll likely be delighted by the results.
+
+### Tips
+
+1. Do not try to expand the image too much at once. Generally it is best
+   to expand the margins in 64-pixel increments. 128 pixels often works,
+   but your mileage may vary depending on the nature of the image you are
+   trying to outpaint into.
+
+2. There are a series of switches that can be used to adjust how the
+   inpainting algorithm operates. In particular, you can use these to
+   minimize the seam that sometimes appears between the original image
+   and the extended part. These switches are:
+
+  --seam_size SEAM_SIZE    Size of the mask around the seam between original and outpainted image (0)
+  --seam_blur SEAM_BLUR    The amount to blur the seam inwards (0)
+  --seam_strength STRENGTH The img2img strength to use when filling the seam (0.7)
+  --seam_steps SEAM_STEPS  The number of steps to use to fill the seam. (10)
+  --tile_size TILE_SIZE    The tile size to use for filling outpaint areas (32)
+
 ### Outcrop
 
-The `outcrop` extension allows you to extend the image in 64 pixel
-increments in any dimension. You can apply the module to any image
-previously-generated by InvokeAI. Note that it will **not** work with
-arbitrary photographs or Stable Diffusion images created by other
-implementations.
+The `outcrop` extension gives you a convenient `!fix` postprocessing
+command that allows you to extend a previously-generated image in 64
+pixel increments in any direction. You can apply the module to any
+image previously-generated by InvokeAI. Note that it works with
+arbitrary PNG photographs, but not currently with JPG or other
+formats. Outcropping is particularly effective when combined with the
+[runwayML custom inpainting
+model](INPAINTING.md#using-the-runwayml-inpainting-model).
 
 Consider this image:
 
@@ -64,42 +103,3 @@ you'll get a slightly different result. You can run it repeatedly
 until you get an image you like. Unfortunately `!fix` does not
 currently respect the `-n` (`--iterations`) argument.
 
-## Outpaint
-
-The `outpaint` extension does the same thing, but with subtle
-differences. Starting with the same image, here is how we would add an
-additional 64 pixels to the top of the image:
-
-```bash
-invoke> !fix images/curly.png --out_direction top 64
-```
-
-(you can abbreviate `--out_direction` as `-D`.
-
-The result is shown here:
-
-<div align="center" markdown>
-![curly_woman_outpaint](../assets/outpainting/curly-outpaint.png)
-</div>
-
-Although the effect is similar, there are significant differences from
-outcropping:
-
-- You can only specify one direction to extend at a time.
-- The image is **not** resized. Instead, the image is shifted by the specified
-number of pixels. If you look carefully, you'll see that less of the lady's
-torso is visible in the image.
-- Because the image dimensions remain the same, there's no rounding
-to multiples of 64.
-- Attempting to outpaint larger areas will frequently give rise to ugly
-   ghosting effects.
-- For best results, try increasing the step number.
-- If you don't specify a pixel value in `-D`, it will default to half
-   of the whole image, which is likely not what you want.
-
-!!! tip
-
-    Neither `outpaint` nor `outcrop` are perfect, but we continue to tune
-    and improve them. If one doesn't work, try the other. You may also
-    wish to experiment with other `img2img` arguments, such as `-C`, `-f`
-    and `-s`.

docs/features/POSTPROCESS.md

@@ -70,7 +70,7 @@ If you do not explicitly specify an upscaling_strength, it will default to 0.75.
 
 ### Face Restoration
 
-`-G : <gfpgan_strength>`
+`-G : <facetool_strength>`
 
 This prompt argument controls the strength of the face restoration that is being
 applied. Similar to upscaling, values between `0.5 to 0.8` are recommended.

docs/features/PROMPTS.md

@@ -45,7 +45,7 @@ Here's a prompt that depicts what it does.
 
 original prompt:
 
-`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
+`#!bash "A fantastical translucent pony made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
 <div align="center" markdown>
 ![step1](../assets/negative_prompt_walkthru/step1.png)
@@ -84,6 +84,109 @@ Getting close - but there's no sense in having a saddle when our horse doesn't h
 
 ---
 
+## **Prompt Syntax Features**
+
+The InvokeAI prompting language has the following features:
+
+### Attention weighting 
+Append a word or phrase with `-` or `+`, or a weight between `0` and `2` (`1`=default), to decrease or increase "attention" (= a mix of per-token CFG weighting multiplier and, for `-`, a weighted blend with the prompt without the term).
+
+The following syntax is recognised:
+  * single words without parentheses: `a tall thin man picking apricots+`
+  * single or multiple words with parentheses: `a tall thin man picking (apricots)+` `a tall thin man picking (apricots)-` `a tall thin man (picking apricots)+` `a tall thin man (picking apricots)-` 
+  * more effect with more symbols `a tall thin man (picking apricots)++`
+  * nesting `a tall thin man (picking apricots+)++` (`apricots` effectively gets `+++`)
+  * all of the above with explicit numbers `a tall thin man picking (apricots)1.1` `a tall thin man (picking (apricots)1.3)1.1`. (`+` is equivalent to 1.1, `++` is pow(1.1,2), `+++` is pow(1.1,3), etc; `-` means 0.9, `--` means pow(0.9,2), etc.)
+  * attention also applies to `[unconditioning]` so `a tall thin man picking apricots [(ladder)0.01]` will *very gently* nudge SD away from trying to draw the man on a ladder
+
+You can use this to increase or decrease the amount of something. Starting from this prompt of `a man picking apricots from a tree`, let's see what happens if we increase and decrease how much attention we want Stable Diffusion to pay to the word `apricots`:
+
+![an AI generated image of a man picking apricots from a tree](../assets/prompt_syntax/apricots-0.png)
+
+Using `-` to reduce apricot-ness:
+
+| `a man picking apricots- from a tree` | `a man picking apricots-- from a tree` | `a man picking apricots--- from a tree` |
+| -- | -- | -- |
+| ![an AI generated image of a man picking apricots from a tree, with smaller apricots](../assets/prompt_syntax/apricots--1.png) | ![an AI generated image of a man picking apricots from a tree, with even smaller and fewer apricots](../assets/prompt_syntax/apricots--2.png) | ![an AI generated image of a man picking apricots from a tree, with very few very small apricots](../assets/prompt_syntax/apricots--3.png) |
+
+Using `+` to increase apricot-ness:
+
+| `a man picking apricots+ from a tree` | `a man picking apricots++ from a tree` | `a man picking apricots+++ from a tree` | `a man picking apricots++++ from a tree` | `a man picking apricots+++++ from a tree` |
+| -- | -- | -- | -- | -- |
+| ![an AI generated image of a man picking apricots from a tree, with larger, more vibrant apricots](../assets/prompt_syntax/apricots-1.png) | ![an AI generated image of a man picking apricots from a tree with even larger, even more vibrant apricots](../assets/prompt_syntax/apricots-2.png) | ![an AI generated image of a man picking apricots from a tree, but the man has been replaced by a pile of apricots](../assets/prompt_syntax/apricots-3.png) | ![an AI generated image of a man picking apricots from a tree, but the man has been replaced by a mound of giant melting-looking apricots](../assets/prompt_syntax/apricots-4.png) | ![an AI generated image of a man picking apricots from a tree, but the man and the leaves and parts of the ground have all been replaced by giant melting-looking apricots](../assets/prompt_syntax/apricots-5.png) |
+
+You can also change the balance between different parts of a prompt. For example, below is a `mountain man`:
+
+![an AI generated image of a mountain man](../assets/prompt_syntax/mountain-man.png)
+
+And here he is with more mountain:
+
+| `mountain+ man` | `mountain++ man` | `mountain+++ man` | 
+| -- | -- | -- |
+| ![](../assets/prompt_syntax/mountain1-man.png) | ![](../assets/prompt_syntax/mountain2-man.png) | ![](../assets/prompt_syntax/mountain3-man.png) |
+
+Or, alternatively, with more man:
+
+| `mountain man+` | `mountain man++` | `mountain man+++` | `mountain man++++` | 
+| -- | -- | -- | -- |
+| ![](../assets/prompt_syntax/mountain-man1.png) | ![](../assets/prompt_syntax/mountain-man2.png) | ![](../assets/prompt_syntax/mountain-man3.png) | ![](../assets/prompt_syntax/mountain-man4.png) |
+
+### Blending between prompts
+
+* `("a tall thin man picking apricots", "a tall thin man picking pears").blend(1,1)`
+* The existing prompt blending using `:<weight>` will continue to be supported - `("a tall thin man picking apricots", "a tall thin man picking pears").blend(1,1)` is equivalent to `a tall thin man picking apricots:1 a tall thin man picking pears:1` in the old syntax.
+* Attention weights can be nested inside blends.
+* Non-normalized blends are supported by passing `no_normalize` as an additional argument to the blend weights, eg `("a tall thin man picking apricots", "a tall thin man picking pears").blend(1,-1,no_normalize)`. very fun to explore local maxima in the feature space, but also easy to produce garbage output.
+
+See the section below on "Prompt Blending" for more information about how this works.
+
+### Cross-Attention Control ('prompt2prompt')
+
+Sometimes an image you generate is almost right, and you just want to
+change one detail without affecting the rest. You could use a photo editor and inpainting
+to overpaint the area, but that's a pain. Here's where `prompt2prompt`
+comes in handy.
+
+Generate an image with a given prompt, record the seed of the image,
+and then use the `prompt2prompt` syntax to substitute words in the
+original prompt for words in a new prompt. This works for `img2img` as well.
+
+* `a ("fluffy cat").swap("smiling dog") eating a hotdog`.
+  * quotes optional: `a (fluffy cat).swap(smiling dog) eating a hotdog`.
+  * for single word substitutions parentheses are also optional: `a cat.swap(dog) eating a hotdog`.
+* Supports options `s_start`, `s_end`, `t_start`, `t_end` (each 0-1) loosely corresponding to bloc97's `prompt_edit_spatial_start/_end` and `prompt_edit_tokens_start/_end` but with the math swapped to make it easier to intuitively understand.
+  * Example usage:`a (cat).swap(dog, s_end=0.3) eating a hotdog` - the `s_end` argument means that the "spatial" (self-attention) edit will stop having any effect after 30% (=0.3) of the steps have been done, leaving Stable Diffusion with 70% of the steps where it is free to decide for itself how to reshape the cat-form into a dog form. 
+  * The numbers represent a percentage through the step sequence where the edits should happen. 0 means the start (noisy starting image), 1 is the end (final image).
+    * For img2img, the step sequence does not start at 0 but instead at (1-strength) - so if strength is 0.7, s_start and s_end must both be greater than 0.3 (1-0.7) to have any effect. 
+* Convenience option `shape_freedom` (0-1) to specify how much "freedom" Stable Diffusion should have to change the shape of the subject being swapped. 
+  * `a (cat).swap(dog, shape_freedom=0.5) eating a hotdog`.
+
+
+
+The `prompt2prompt` code is based off [bloc97's
+colab](https://github.com/bloc97/CrossAttentionControl).
+
+Note that `prompt2prompt` is not currently working with the runwayML
+inpainting model, and may never work due to the way this model is set
+up. If you attempt to use `prompt2prompt` you will get the original
+image back. However, since this model is so good at inpainting, a
+good substitute is to use the `clipseg` text masking option:
+
+```
+invoke> a fluffy cat eating a hotdot
+Outputs:
+[1010] outputs/000025.2182095108.png: a fluffy cat eating a hotdog
+invoke> a smiling dog eating a hotdog -I 000025.2182095108.png -tm cat
+```
+
+### Escaping parantheses () and speech marks ""
+
+If the model you are using has parentheses () or speech marks "" as
+part of its syntax, you will need to "escape" these using a backslash,
+so that`(my_keyword)` becomes `\(my_keyword\)`. Otherwise, the prompt
+parser will attempt to interpret the parentheses as part of the prompt
+syntax and it will get confused.
+
 ## **Prompt Blending**
 
 You may blend together different sections of the prompt to explore the

docs/features/WEBUIHOTKEYS.md

@@ -0,0 +1,58 @@
+# **WebUI Hotkey List**
+
+## General
+
+| Setting      | Hotkey                 |
+| ------------ | ---------------------- |
+| a            | Set All Parameters     |
+| s            | Set Seed               |
+| u            | Upscale                |
+| r            | Restoration            |
+| i            | Show Metadata          |
+| Ddl          | Delete Image           |
+| alt + a      | Focus prompt input     |
+| shift + i    | Send To Image to Image |
+| ctrl + enter | Start processing       |
+| shift + x    | cancel Processing      |
+| shift + d    | Toggle Dark Mode       |
+| `            | Toggle console         |
+
+## Tabs
+
+| Setting | Hotkey                    |
+| ------- | ------------------------- |
+| 1       | Go to Text To Image Tab   |
+| 2       | Go to Image to Image Tab  |
+| 3       | Go to Inpainting Tab      |
+| 4       | Go to Outpainting Tab     |
+| 5       | Go to Nodes Tab           |
+| 6       | Go to Post Processing Tab |
+
+## Gallery
+
+| Setting      | Hotkey                          |
+| ------------ | ------------------------------- |
+| g            | Toggle Gallery                  |
+| left arrow   | Go to previous image in gallery |
+| right arrow  | Go to next image in gallery     |
+| shift + p    | Pin gallery                     |
+| shift + up   | Increase gallery image size     |
+| shift + down | Decrease gallery image size     |
+| shift + r    | Reset image gallery size        |
+
+## Inpainting
+
+| Setting                    | Hotkey                |
+| -------------------------- | --------------------- |
+| [                          | Decrease brush size   |
+| ]                          | Increase brush size   |
+| alt + [                    | Decrease mask opacity |
+| alt + ]                    | Increase mask opacity |
+| b                          | Select brush          |
+| e                          | Select eraser         |
+| ctrl + z                   | Undo brush stroke     |
+| ctrl + shift + z, ctrl + y | Redo brush stroke     |
+| h                          | Hide mask             |
+| shift + m                  | Invert mask           |
+| shift + c                  | Clear mask            |
+| shift + j                  | Expand canvas         |

docs/index.md

@@ -12,7 +12,7 @@ title: Home
 -->
 <div align="center" markdown>
 
-# ^^**InvokeAI: A Stable Diffusion Toolkit**^^ :tools: <br> <small>Formally known as lstein/stable-diffusion</small>
+# ^^**InvokeAI: A Stable Diffusion Toolkit**^^ :tools: <br> <small>Formerly known as lstein/stable-diffusion</small>
 
 ![project logo](assets/logo.png)