Merge branch 'development' into fix_generate.py

This commit is contained in:
Lincoln Stein 2022-11-05 12:47:35 -07:00 committed by GitHub
commit fefb4dc1f8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
587 changed files with 54471 additions and 6579 deletions

View File

@ -5,8 +5,7 @@ SAMPLES_DIR=${OUT_DIR}
python scripts/dream.py \ python scripts/dream.py \
--from_file ${PROMPT_FILE} \ --from_file ${PROMPT_FILE} \
--outdir ${OUT_DIR} \ --outdir ${OUT_DIR} \
--sampler plms \ --sampler plms
--full_precision
# original output by CompVis/stable-diffusion # original output by CompVis/stable-diffusion
IMAGE1=".dev_scripts/images/v1_4_astronaut_rides_horse_plms_step50_seed42.png" IMAGE1=".dev_scripts/images/v1_4_astronaut_rides_horse_plms_step50_seed42.png"

3
.dockerignore Normal file
View File

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

4
.github/CODEOWNERS vendored Normal file
View File

@ -0,0 +1,4 @@
ldm/invoke/pngwriter.py @CapableWeb
ldm/invoke/server_legacy.py @CapableWeb
scripts/legacy_api.py @CapableWeb
tests/legacy_tests.sh @CapableWeb

102
.github/ISSUE_TEMPLATE/BUG_REPORT.yml vendored Normal file
View File

@ -0,0 +1,102 @@
name: 🐞 Bug Report
description: File a bug report
title: '[bug]: '
labels: ['bug']
# assignees:
# - moderator_bot
# - lstein
body:
- type: markdown
attributes:
value: |
Thanks for taking the time to fill out this Bug Report!
- type: checkboxes
attributes:
label: Is there an existing issue for this?
description: |
Please use the [search function](https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen+label%3Abug)
irst to see if an issue already exists for the bug you encountered.
options:
- label: I have searched the existing issues
required: true
- type: markdown
attributes:
value: __Describe your environment__
- type: dropdown
id: os_dropdown
attributes:
label: OS
description: Which operating System did you use when the bug occured
multiple: false
options:
- 'Linux'
- 'Windows'
- 'macOS'
validations:
required: true
- type: dropdown
id: gpu_dropdown
attributes:
label: GPU
description: Which kind of Graphic-Adapter is your System using
multiple: false
options:
- 'cuda'
- 'amd'
- 'mps'
- 'cpu'
validations:
required: true
- type: input
id: vram
attributes:
label: VRAM
description: Size of the VRAM if known
placeholder: 8GB
validations:
required: false
- type: textarea
id: what-happened
attributes:
label: What happened?
description: |
Briefly describe what happened, what you expected to happen and how to reproduce this bug.
placeholder: When using the webinterface and right-clicking on button X instead of the popup-menu there error Y appears
validations:
required: true
- type: textarea
attributes:
label: Screenshots
description: If applicable, add screenshots to help explain your problem
placeholder: this is what the result looked like <screenshot>
validations:
required: false
- type: textarea
attributes:
label: Additional context
description: Add any other context about the problem here
placeholder: Only happens when there is full moon and Friday the 13th on Christmas Eve 🎅🏻
validations:
required: false
- type: input
id: contact
attributes:
label: Contact Details
description: __OPTIONAL__ How can we get in touch with you if we need more info (besides this issue)?
placeholder: ex. email@example.com, discordname, twitter, ...
validations:
required: false

View File

@ -0,0 +1,56 @@
name: Feature Request
description: Commit a idea or Request a new feature
title: '[enhancement]: '
labels: ['enhancement']
# assignees:
# - lstein
# - tildebyte
body:
- type: markdown
attributes:
value: |
Thanks for taking the time to fill out this Feature request!
- type: checkboxes
attributes:
label: Is there an existing issue for this?
description: |
Please make use of the [search function](https://github.com/invoke-ai/InvokeAI/labels/enhancement)
to see if a simmilar issue already exists for the feature you want to request
options:
- label: I have searched the existing issues
required: true
- type: input
id: contact
attributes:
label: Contact Details
description: __OPTIONAL__ How could we get in touch with you if we need more info (besides this issue)?
placeholder: ex. email@example.com, discordname, twitter, ...
validations:
required: false
- type: textarea
id: whatisexpected
attributes:
label: What should this feature add?
description: Please try to explain the functionality this feature should add
placeholder: |
Instead of one huge textfield, it would be nice to have forms for bug-reports, feature-requests, ...
Great benefits with automatic labeling, assigning and other functionalitys not available in that form
via old-fashioned markdown-templates. I would also love to see the use of a moderator bot 🤖 like
https://github.com/marketplace/actions/issue-moderator-with-commands to auto close old issues and other things
validations:
required: true
- type: textarea
attributes:
label: Alternatives
description: Describe alternatives you've considered
placeholder: A clear and concise description of any alternative solutions or features you've considered.
- type: textarea
attributes:
label: Aditional Content
description: Add any other context or screenshots about the feature request here.
placeholder: This is a Mockup of the design how I imagine it <screenshot>

View File

@ -1,36 +0,0 @@
---
name: Bug report
about: Create a report to help us improve
title: ''
labels: ''
assignees: ''
---
**Describe your environment**
- GPU: [cuda/amd/mps/cpu]
- VRAM: [if known]
- CPU arch: [x86/arm]
- OS: [Linux/Windows/macOS]
- Python: [Anaconda/miniconda/miniforge/pyenv/other (explain)]
- Branch: [if `git status` says anything other than "On branch main" paste it here]
- Commit: [run `git show` and paste the line that starts with "Merge" here]
**Describe the bug**
A clear and concise description of what the bug is.
**To Reproduce**
Steps to reproduce the behavior:
1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error
**Expected behavior**
A clear and concise description of what you expected to happen.
**Screenshots**
If applicable, add screenshots to help explain your problem.
**Additional context**
Add any other context about the problem here.

14
.github/ISSUE_TEMPLATE/config.yml vendored Normal file
View File

@ -0,0 +1,14 @@
blank_issues_enabled: false
contact_links:
- name: Project-Documentation
url: https://invoke-ai.github.io/InvokeAI/
about: Should be your first place to go when looking for manuals/FAQs regarding our InvokeAI Toolkit
- name: Discord
url: https://discord.gg/ZmtBAhwWhy
about: Our Discord Community could maybe help you out via live-chat
- name: GitHub Community Support
url: https://github.com/orgs/community/discussions
about: Please ask and answer questions regarding the GitHub Platform here.
- name: GitHub Security Bug Bounty
url: https://bounty.github.com/
about: Please report security vulnerabilities of the GitHub Platform here.

View File

@ -1,20 +0,0 @@
---
name: Feature request
about: Suggest an idea for this project
title: ''
labels: ''
assignees: ''
---
**Is your feature request related to a problem? Please describe.**
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
**Describe the solution you'd like**
A clear and concise description of what you want to happen.
**Describe alternatives you've considered**
A clear and concise description of any alternative solutions or features you've considered.
**Additional context**
Add any other context or screenshots about the feature request here.

48
.github/workflows/build-container.yml vendored Normal file
View File

@ -0,0 +1,48 @@
# 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'
jobs:
docker:
strategy:
fail-fast: false
matrix:
arch:
- x86_64
- aarch64
include:
- arch: x86_64
conda-env-file: environment.yml
- arch: aarch64
conda-env-file: environment-linux-aarch64.yml
runs-on: ubuntu-latest
name: ${{ matrix.arch }}
steps:
- name: prepare docker-tag
env:
repository: ${{ github.repository }}
run: echo "dockertag=${repository,,}" >> $GITHUB_ENV
- name: Checkout
uses: actions/checkout@v3
- name: Set up QEMU
uses: docker/setup-qemu-action@v2
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v2
- name: Build container
uses: docker/build-push-action@v3
with:
context: .
file: docker-build/Dockerfile
platforms: Linux/${{ matrix.arch }}
push: false
tags: ${{ env.dockertag }}:${{ matrix.arch }}
build-args: |
conda_env_file=${{ matrix.conda-env-file }}
conda_version=py39_4.12.0-Linux-${{ matrix.arch }}
invokeai_git=${{ github.repository }}
invokeai_branch=${{ github.ref_name }}

View File

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

40
.github/workflows/mkdocs-material.yml vendored Normal file
View File

@ -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

View File

@ -1,97 +0,0 @@
name: Test Dream with Conda
on:
push:
branches:
- 'main'
- 'development'
jobs:
os_matrix:
strategy:
matrix:
os: [ ubuntu-latest, macos-12 ]
name: Test dream.py on ${{ matrix.os }} with conda
runs-on: ${{ matrix.os }}
steps:
- run: |
echo The PR was merged
- name: Set platform variables
id: vars
run: |
# Note, can't "activate" via github action; specifying the env's python has the same effect
if [ "$RUNNER_OS" = "macOS" ]; then
echo "::set-output name=ENV_FILE::environment-mac.yaml"
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.yaml"
echo "::set-output name=PYTHON_BIN::/usr/share/miniconda/envs/ldm/bin/python"
fi
- name: Checkout sources
uses: actions/checkout@v3
- name: Use Cached Stable Diffusion v1.4 Model
id: cache-sd-v1-4
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
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 }}
- 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' }}
run: |
${{ steps.vars.outputs.PYTHON_BIN }} scripts/preload_models.py
# - name: Run tmate
# uses: mxschmitt/action-tmate@v3
# timeout-minutes: 30
- name: Run the tests
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/dream.py --from_file tests/preflight_prompts.txt --full_precision
elif [[ ${{ github.ref }} == 'refs/heads/development' ]]; then
time ${{ steps.vars.outputs.PYTHON_BIN }} scripts/dream.py --from_file tests/dev_prompts.txt --full_precision
fi
mkdir -p outputs/img-samples
- name: Archive results
uses: actions/upload-artifact@v3
with:
name: results
path: outputs/img-samples

123
.github/workflows/test-invoke-conda.yml vendored Normal file
View File

@ -0,0 +1,123 @@
name: Test invoke.py
on:
push:
branches:
- 'main'
- 'development'
- 'fix-gh-actions-fork'
pull_request:
branches:
- 'main'
- 'development'
jobs:
matrix:
strategy:
fail-fast: false
matrix:
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: ${{ matrix.default-shell }}
steps:
- name: Checkout sources
id: checkout-sources
uses: actions/checkout@v3
- name: create models.yaml from example
run: cp configs/models.yaml.example configs/models.yaml
- name: Use cached conda packages
id: use-cached-conda-packages
uses: actions/cache@v3
with:
path: ~/conda_pkgs_dir
key: conda-pkgs-${{ runner.os }}-${{ runner.arch }}-${{ hashFiles(matrix.environment-file) }}
- name: Activate Conda Env
id: activate-conda-env
uses: conda-incubator/setup-miniconda@v2
with:
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" >> $GITHUB_ENV
- name: Use Cached Stable Diffusion Model
id: cache-sd-model
uses: actions/cache@v3
env:
cache-name: cache-${{ matrix.stable-diffusion-model-switch }}
with:
path: ${{ matrix.stable-diffusion-model-dl-path }}
key: ${{ env.cache-name }}
- name: Download ${{ matrix.stable-diffusion-model-switch }}
id: download-stable-diffusion-model
if: ${{ steps.cache-sd-model.outputs.cache-hit != 'true' }}
run: |
[[ -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: |
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: |
mkdir -p outputs/img-samples
conda env export --name ${{ env.CONDA_ENV_NAME }} > outputs/img-samples/environment-${{ runner.os }}-${{ runner.arch }}.yml
- name: Archive results
id: archive-results
uses: actions/upload-artifact@v3
with:
name: results_${{ matrix.os }}_${{ matrix.stable-diffusion-model-switch }}
path: outputs/img-samples

29
.gitignore vendored
View File

@ -1,6 +1,14 @@
# ignore default image save location and model symbolic link # ignore default image save location and model symbolic link
outputs/ outputs/
models/ldm/stable-diffusion-v1/model.ckpt models/ldm/stable-diffusion-v1/model.ckpt
**/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
# ignore a directory which serves as a place for initial images # ignore a directory which serves as a place for initial images
inputs/ inputs/
@ -77,9 +85,6 @@ db.sqlite3-journal
instance/ instance/
.webassets-cache .webassets-cache
# WebUI temp files:
img2img-tmp.png
# Scrapy stuff: # Scrapy stuff:
.scrapy .scrapy
@ -186,3 +191,21 @@ testtube
checkpoints checkpoints
# If it's a Mac # If it's a Mac
.DS_Store .DS_Store
# Let the frontend manage its own gitignore
!frontend/*
# Scratch folder
.scratch/
.vscode/
gfpgan/
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

13
.prettierrc.yaml Normal file
View File

@ -0,0 +1,13 @@
endOfLine: lf
tabWidth: 2
useTabs: false
singleQuote: true
quoteProps: as-needed
embeddedLanguageFormatting: auto
overrides:
- files: '*.md'
options:
proseWrap: always
printWidth: 80
parser: markdown
cursorOffset: -1

13
LICENSE
View File

@ -1,17 +1,6 @@
MIT License MIT License
Copyright (c) 2022 Lincoln D. Stein (https://github.com/lstein) Copyright (c) 2022 InvokeAI Team
This software is derived from a fork of the source code available from
https://github.com/pesser/stable-diffusion and
https://github.com/CompViz/stable-diffusion. They carry the following
copyrights:
Copyright (c) 2022 Machine Vision and Learning Group, LMU Munich
Copyright (c) 2022 Robin Rombach and Patrick Esser and contributors
Please see individual source code files for copyright and authorship
attributions.
Permission is hereby granted, free of charge, to any person obtaining a copy Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal of this software and associated documentation files (the "Software"), to deal

249
README.md
View File

@ -1,64 +1,95 @@
<h1 align='center'><b>InvokeAI: A Stable Diffusion Toolkit</b></h1> <div align="center">
<p align='center'> # InvokeAI: A Stable Diffusion Toolkit
<img src="docs/assets/logo.png"/>
</p>
<p align="center"> _Formerly known as lstein/stable-diffusion_
<img src="https://img.shields.io/github/last-commit/invoke-ai/InvokeAI?logo=Python&logoColor=green&style=for-the-badge" alt="last-commit"/>
<img src="https://img.shields.io/github/stars/invoke-ai/InvokeAI?logo=GitHub&style=for-the-badge" alt="stars"/> ![project logo](docs/assets/logo.png)
<br>
<img src="https://img.shields.io/github/issues/invoke-ai/InvokeAI?logo=GitHub&style=for-the-badge" alt="issues"/> [![discord badge]][discord link]
<img src="https://img.shields.io/github/issues-pr/invoke-ai/InvokeAI?logo=GitHub&style=for-the-badge" alt="pull-requests"/>
</p> [![latest release badge]][latest release link] [![github stars badge]][github stars link] [![github forks badge]][github forks link]
[![CI checks on main badge]][CI checks on main link] [![CI checks on dev badge]][CI checks on dev link] [![latest commit to dev badge]][latest commit to dev link]
[![github open issues badge]][github open issues link] [![github open prs badge]][github open prs link]
[CI checks on dev badge]: https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/development?label=CI%20status%20on%20dev&cache=900&icon=github
[CI checks on dev link]: https://github.com/invoke-ai/InvokeAI/actions?query=branch%3Adevelopment
[CI checks on main badge]: https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/main?label=CI%20status%20on%20main&cache=900&icon=github
[CI checks on main link]: https://github.com/invoke-ai/InvokeAI/actions/workflows/test-invoke-conda.yml
[discord badge]: https://flat.badgen.net/discord/members/ZmtBAhwWhy?icon=discord
[discord link]: https://discord.gg/ZmtBAhwWhy
[github forks badge]: https://flat.badgen.net/github/forks/invoke-ai/InvokeAI?icon=github
[github forks link]: https://useful-forks.github.io/?repo=invoke-ai%2FInvokeAI
[github open issues badge]: https://flat.badgen.net/github/open-issues/invoke-ai/InvokeAI?icon=github
[github open issues link]: https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen
[github open prs badge]: https://flat.badgen.net/github/open-prs/invoke-ai/InvokeAI?icon=github
[github open prs link]: https://github.com/invoke-ai/InvokeAI/pulls?q=is%3Apr+is%3Aopen
[github stars badge]: https://flat.badgen.net/github/stars/invoke-ai/InvokeAI?icon=github
[github stars link]: https://github.com/invoke-ai/InvokeAI/stargazers
[latest commit to dev badge]: https://flat.badgen.net/github/last-commit/invoke-ai/InvokeAI/development?icon=github&color=yellow&label=last%20dev%20commit&cache=900
[latest commit to dev link]: https://github.com/invoke-ai/InvokeAI/commits/development
[latest release badge]: https://flat.badgen.net/github/release/invoke-ai/InvokeAI/development?icon=github
[latest release link]: https://github.com/invoke-ai/InvokeAI/releases
</div>
This is a fork of This is a fork of
[CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion), [CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion),
the open source text-to-image generator. It provides a streamlined the open source text-to-image generator. It provides a streamlined
process with various new features and options to aid the image process with various new features and options to aid the image
generation process. It runs on Windows, Mac and Linux machines, generation process. It runs on Windows, Mac and Linux machines, with
and runs on GPU cards with as little as 4 GB or RAM. GPU cards with as little as 4 GB of RAM. It provides both a polished
Web interface (see below), and an easy-to-use command-line interface.
**Quick links**: [<a href="https://discord.gg/NwVCmKwY">Discord Server</a>] [<a href="https://invoke-ai.github.io/InvokeAI/">Documentation and Tutorials</a>] [<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>] [<a href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion, Ideas & Q&A</a>]
<div align="center"><img src="docs/assets/invoke-web-server-1.png" width=640></div>
_Note: This fork is rapidly evolving. Please use the _Note: This fork is rapidly evolving. Please use the
[Issues](https://github.com/invoke-ai/InvokeAI/issues) tab to [Issues](https://github.com/invoke-ai/InvokeAI/issues) tab to report bugs and make feature
report bugs and make feature requests. Be sure to use the provided requests. Be sure to use the provided templates. They will help aid diagnose issues faster._
templates. They will help aid diagnose issues faster._
_This repository was formally known as lstein/stable-diffusion_ ## Table of Contents
# **Table of Contents**
1. [Installation](#installation) 1. [Installation](#installation)
2. [Major Features](#features) 2. [Hardware Requirements](#hardware-requirements)
3. [Changelog](#latest-changes) 3. [Features](#features)
4. [Troubleshooting](#troubleshooting) 4. [Latest Changes](#latest-changes)
5. [Contributing](#contributing) 5. [Troubleshooting](#troubleshooting)
6. [Support](#support) 6. [Contributing](#contributing)
7. [Contributors](#contributors)
8. [Support](#support)
9. [Further Reading](#further-reading)
# Installation ### Installation
This fork is supported across multiple platforms. You can find individual installation instructions below. This fork is supported across multiple platforms. You can find individual installation instructions
below.
- ## [Linux](docs/installation/INSTALL_LINUX.md) - #### [Linux](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_LINUX/)
- ## [Windows](docs/installation/INSTALL_WINDOWS.md)
- ## [Macintosh](docs/installation/INSTALL_MAC.md)
## **Hardware Requirements** - #### [Windows](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_WINDOWS/)
**System** - #### [Macintosh](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_MAC/)
### Hardware Requirements
#### System
You wil need one of the following: You wil need one of the following:
- An NVIDIA-based graphics card with 4 GB or more VRAM memory. - An NVIDIA-based graphics card with 4 GB or more VRAM memory.
- An Apple computer with an M1 chip. - An Apple computer with an M1 chip.
**Memory** #### Memory
- At least 12 GB Main Memory RAM. - At least 12 GB Main Memory RAM.
**Disk** #### Disk
- At least 6 GB of free disk space for the machine learning model, Python, and all its dependencies. - At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
**Note** **Note**
@ -67,99 +98,107 @@ run the dream script in full-precision mode as shown below.
Similarly, specify full-precision mode on Apple M1 hardware. Similarly, specify full-precision mode on Apple M1 hardware.
To run in full-precision mode, start `dream.py` with the Precision is auto configured based on the device. If however you encounter
`--full_precision` flag: errors like 'expected type Float but found Half' or 'not implemented for Half'
you can try starting `invoke.py` with the `--precision=float32` flag:
``` ```bash
(ldm) ~/stable-diffusion$ python scripts/dream.py --full_precision (invokeai) ~/InvokeAI$ python scripts/invoke.py --precision=float32
``` ```
# Features ### Features
## **Major Features** #### Major Features
- ## [Interactive Command Line Interface](docs/features/CLI.md) - [Web Server](https://invoke-ai.github.io/InvokeAI/features/WEB/)
- [Interactive Command Line Interface](https://invoke-ai.github.io/InvokeAI/features/CLI/)
- [Image To Image](https://invoke-ai.github.io/InvokeAI/features/IMG2IMG/)
- [Inpainting Support](https://invoke-ai.github.io/InvokeAI/features/INPAINTING/)
- [Outpainting Support](https://invoke-ai.github.io/InvokeAI/features/OUTPAINTING/)
- [Upscaling, face-restoration and outpainting](https://invoke-ai.github.io/InvokeAI/features/POSTPROCESS/)
- [Reading Prompts From File](https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#reading-prompts-from-a-file)
- [Prompt Blending](https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#prompt-blending)
- [Thresholding and Perlin Noise Initialization Options](https://invoke-ai.github.io/InvokeAI/features/OTHER/#thresholding-and-perlin-noise-initialization-options)
- [Negative/Unconditioned Prompts](https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#negative-and-unconditioned-prompts)
- [Variations](https://invoke-ai.github.io/InvokeAI/features/VARIATIONS/)
- [Personalizing Text-to-Image Generation](https://invoke-ai.github.io/InvokeAI/features/TEXTUAL_INVERSION/)
- [Simplified API for text to image generation](https://invoke-ai.github.io/InvokeAI/features/OTHER/#simplified-api)
- ## [Image To Image](docs/features/IMG2IMG.md) #### Other Features
- ## [Inpainting Support](docs/features/INPAINTING.md) - [Google Colab](https://invoke-ai.github.io/InvokeAI/features/OTHER/#google-colab)
- [Seamless Tiling](https://invoke-ai.github.io/InvokeAI/features/OTHER/#seamless-tiling)
- [Shortcut: Reusing Seeds](https://invoke-ai.github.io/InvokeAI/features/OTHER/#shortcuts-reusing-seeds)
- [Preload Models](https://invoke-ai.github.io/InvokeAI/features/OTHER/#preload-models)
- ## [GFPGAN and Real-ESRGAN Support](docs/features/UPSCALE.md) ### Latest Changes
- ## [Seamless Tiling](docs/features/OTHER.md#seamless-tiling) - v2.0.1 (13 October 2022)
- fix noisy images at high step count when using k* samplers
- dream.py script now calls invoke.py module directly rather than
via a new python process (which could break the environment)
- ## [Google Colab](docs/features/OTHER.md#google-colab) - v2.0.0 (9 October 2022)
- ## [Web Server](docs/features/WEB.md) - `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains
for backward compatibility.
- Completely new WebGUI - launch with `python3 scripts/invoke.py --web`
- Support for <a href="https://invoke-ai.github.io/InvokeAI/features/INPAINTING/">inpainting</a> and <a href="https://invoke-ai.github.io/InvokeAI/features/OUTPAINTING/">outpainting</a>
- img2img runs on all k* samplers
- Support for <a href="https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#negative-and-unconditioned-prompts">negative prompts</a>
- Support for CodeFormer face reconstruction
- Support for Textual Inversion on Macintoshes
- Support in both WebGUI and CLI for <a href="https://invoke-ai.github.io/InvokeAI/features/POSTPROCESS/">post-processing of previously-generated images</a>
using facial reconstruction, ESRGAN upscaling, outcropping (similar to DALL-E infinite canvas),
and "embiggen" upscaling. See the `!fix` command.
- New `--hires` option on `invoke>` line allows <a href="https://invoke-ai.github.io/InvokeAI/features/CLI/#txt2img">larger images to be created without duplicating elements</a>, at the cost of some performance.
- New `--perlin` and `--threshold` options allow you to add and control variation
during image generation (see <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/OTHER.md#thresholding-and-perlin-noise-initialization-options">Thresholding and Perlin Noise Initialization</a>
- Extensive metadata now written into PNG files, allowing reliable regeneration of images
and tweaking of previous settings.
- Command-line completion in `invoke.py` now works on Windows, Linux and Mac platforms.
- Improved <a href="https://invoke-ai.github.io/InvokeAI/features/CLI/">command-line completion behavior</a>.
New commands added:
- List command-line history with `!history`
- Search command-line history with `!search`
- Clear history with `!clear`
- Deprecated `--full_precision` / `-F`. Simply omit it and `invoke.py` will auto
configure. To switch away from auto use the new flag like `--precision=float32`.
- ## [Reading Prompts From File](docs/features/OTHER.md#reading-prompts-from-a-file) For older changelogs, please visit the **[CHANGELOG](https://invoke-ai.github.io/InvokeAI/CHANGELOG#v114-11-september-2022)**.
- ## [Shortcut: Reusing Seeds](docs/features/OTHER.md#shortcuts-reusing-seeds) ### Troubleshooting
- ## [Weighted Prompts](docs/features/OTHER.md#weighted-prompts) Please check out our **[Q&A](https://invoke-ai.github.io/InvokeAI/help/TROUBLESHOOT/#faq)** to get solutions for common installation
problems and other issues.
- ## [Variations](docs/features/VARIATIONS.md)
- ## [Personalizing Text-to-Image Generation](docs/features/TEXTUAL_INVERSION.md)
- ## [Simplified API for text to image generation](docs/features/OTHER.md#simplified-api)
## **Other Features**
- ### [Creating Transparent Regions for Inpainting](docs/features/INPAINTING.md#creating-transparent-regions-for-inpainting)
- ### [Preload Models](docs/features/OTHER.md#preload-models)
# Latest Changes
- v1.14 (11 September 2022)
- Memory optimizations for small-RAM cards. 512x512 now possible on 4 GB GPUs.
- Full support for Apple hardware with M1 or M2 chips.
- Add "seamless mode" for circular tiling of image. Generates beautiful effects. ([prixt](https://github.com/prixt)).
- Inpainting support.
- Improved web server GUI.
- Lots of code and documentation cleanups.
- v1.13 (3 September 2022
- Support image variations (see [VARIATIONS](docs/features/VARIATIONS.md) ([Kevin Gibbons](https://github.com/bakkot) and many contributors and reviewers)
- Supports a Google Colab notebook for a standalone server running on Google hardware [Arturo Mendivil](https://github.com/artmen1516)
- WebUI supports GFPGAN/ESRGAN facial reconstruction and upscaling [Kevin Gibbons](https://github.com/bakkot)
- WebUI supports incremental display of in-progress images during generation [Kevin Gibbons](https://github.com/bakkot)
- A new configuration file scheme that allows new models (including upcoming stable-diffusion-v1.5)
to be added without altering the code. ([David Wager](https://github.com/maddavid12))
- Can specify --grid on dream.py command line as the default.
- Miscellaneous internal bug and stability fixes.
- Works on M1 Apple hardware.
- Multiple bug fixes.
For older changelogs, please visit **[CHANGELOGS](docs/CHANGELOG.md)**.
# Troubleshooting
Please check out our **[Q&A](docs/help/TROUBLESHOOT.md)** to get solutions for common installation problems and other issues.
# Contributing # Contributing
Anyone who wishes to contribute to this project, whether documentation, features, bug fixes, code cleanup, testing, or code reviews, is very much encouraged to do so. If you are unfamiliar with Anyone who wishes to contribute to this project, whether documentation, features, bug fixes, code
how to contribute to GitHub projects, here is a [Getting Started Guide](https://opensource.com/article/19/7/create-pull-request-github). cleanup, testing, or code reviews, is very much encouraged to do so. If you are unfamiliar with how
to contribute to GitHub projects, here is a
[Getting Started Guide](https://opensource.com/article/19/7/create-pull-request-github).
A full set of contribution guidelines, along with templates, are in progress, but for now the most important thing is to **make your pull request against the "development" branch**, and not against "main". This will help keep public breakage to a minimum and will allow you to propose more radical changes. A full set of contribution guidelines, along with templates, are in progress, but for now the most
important thing is to **make your pull request against the "development" branch**, and not against
"main". This will help keep public breakage to a minimum and will allow you to propose more radical
changes.
## **Contributors** ### Contributors
This fork is a combined effort of various people from across the world. [Check out the list of all these amazing people](docs/CONTRIBUTORS.md). We thank them for their time, hard work and effort. This fork is a combined effort of various people from across the world.
[Check out the list of all these amazing people](https://invoke-ai.github.io/InvokeAI/other/CONTRIBUTORS/). We thank them for
their time, hard work and effort.
# Support ### Support
For support, For support, please use this repository's GitHub Issues tracking service. Feel free to send me an
please use this repository's GitHub Issues tracking service. Feel free email if you use and like the script.
to send me an email if you use and like the script.
Original portions of the software are Copyright (c) 2020 Lincoln D. Stein (https://github.com/lstein) Original portions of the software are Copyright (c) 2020
[Lincoln D. Stein](https://github.com/lstein)
# Further Reading ### Further Reading
Please see the original README for more information on this software Please see the original README for more information on this software and underlying algorithm,
and underlying algorithm, located in the file [README-CompViz.md](docs/README-CompViz.md). located in the file [README-CompViz.md](https://invoke-ai.github.io/InvokeAI/other/README-CompViz/).

BIN
assets/caution.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 33 KiB

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,55 @@
import argparse
import os
from ldm.invoke.args import PRECISION_CHOICES
def create_cmd_parser():
parser = argparse.ArgumentParser(description="InvokeAI web UI")
parser.add_argument(
"--host",
type=str,
help="The host to serve on",
default="localhost",
)
parser.add_argument("--port", type=int, help="The port to serve on", default=9090)
parser.add_argument(
"--cors",
nargs="*",
type=str,
help="Additional allowed origins, comma-separated",
)
parser.add_argument(
"--embedding_path",
type=str,
help="Path to a pre-trained embedding manager checkpoint - can only be set on command line",
)
# TODO: Can't get flask to serve images from any dir (saving to the dir does work when specified)
# parser.add_argument(
# "--output_dir",
# default="outputs/",
# type=str,
# help="Directory for output images",
# )
parser.add_argument(
"-v",
"--verbose",
action="store_true",
help="Enables verbose logging",
)
parser.add_argument(
"--precision",
dest="precision",
type=str,
choices=PRECISION_CHOICES,
metavar="PRECISION",
help=f'Set model precision. Defaults to auto selected based on device. Options: {", ".join(PRECISION_CHOICES)}',
default="auto",
)
parser.add_argument(
'--free_gpu_mem',
dest='free_gpu_mem',
action='store_true',
help='Force free gpu memory before final decoding',
)
return parser

View File

@ -0,0 +1,69 @@
from backend.modules.parse_seed_weights import parse_seed_weights
import argparse
SAMPLER_CHOICES = [
"ddim",
"k_dpm_2_a",
"k_dpm_2",
"k_euler_a",
"k_euler",
"k_heun",
"k_lms",
"plms",
]
def parameters_to_command(params):
"""
Converts dict of parameters into a `invoke.py` REPL command.
"""
switches = list()
if "prompt" in params:
switches.append(f'"{params["prompt"]}"')
if "steps" in params:
switches.append(f'-s {params["steps"]}')
if "seed" in params:
switches.append(f'-S {params["seed"]}')
if "width" in params:
switches.append(f'-W {params["width"]}')
if "height" in params:
switches.append(f'-H {params["height"]}')
if "cfg_scale" in params:
switches.append(f'-C {params["cfg_scale"]}')
if "sampler_name" in 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:
switches.append(f'-M {params["init_mask"]}')
if "init_color" in params and len(params["init_color"]) > 0:
switches.append(f'--init_color {params["init_color"]}')
if "strength" in params and "init_img" in params:
switches.append(f'-f {params["strength"]}')
if "fit" in params and params["fit"] == True:
switches.append(f"--fit")
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:
switches.append(f'-v {params["variation_amount"]}')
if "with_variations" in params:
seed_weight_pairs = ",".join(
f"{seed}:{weight}" for seed, weight in params["with_variations"]
)
switches.append(f"-V {seed_weight_pairs}")
return " ".join(switches)

View File

@ -0,0 +1,47 @@
def parse_seed_weights(seed_weights):
"""
Accepts seed weights as string in "12345:0.1,23456:0.2,3456:0.3" format
Validates them
If valid: returns as [[12345, 0.1], [23456, 0.2], [3456, 0.3]]
If invalid: returns False
"""
# Must be a string
if not isinstance(seed_weights, str):
return False
# String must not be empty
if len(seed_weights) == 0:
return False
pairs = []
for pair in seed_weights.split(","):
split_values = pair.split(":")
# Seed and weight are required
if len(split_values) != 2:
return False
if len(split_values[0]) == 0 or len(split_values[1]) == 1:
return False
# Try casting the seed to int and weight to float
try:
seed = int(split_values[0])
weight = float(split_values[1])
except ValueError:
return False
# Seed must be 0 or above
if not seed >= 0:
return False
# Weight must be between 0 and 1
if not (weight >= 0 and weight <= 1):
return False
# This pair is valid
pairs.append([seed, weight])
# All pairs are valid
return pairs

View File

@ -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

View File

@ -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

View File

@ -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

View File

@ -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

View File

@ -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

View File

@ -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

View File

@ -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

View File

@ -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

View File

@ -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

View File

@ -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

View File

@ -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

View File

@ -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

View File

@ -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

View File

@ -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

View File

@ -30,7 +30,7 @@ model:
target: ldm.modules.embedding_manager.EmbeddingManager target: ldm.modules.embedding_manager.EmbeddingManager
params: params:
placeholder_strings: ["*"] placeholder_strings: ["*"]
initializer_words: ["sculpture"] initializer_words: ['face', 'man', 'photo', 'africanmale']
per_image_tokens: false per_image_tokens: false
num_vectors_per_token: 1 num_vectors_per_token: 1
progressive_words: False progressive_words: False
@ -76,4 +76,4 @@ model:
target: torch.nn.Identity target: torch.nn.Identity
cond_stage_config: cond_stage_config:
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder target: ldm.modules.encoders.modules.WeightedFrozenCLIPEmbedder

View File

@ -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

View File

@ -0,0 +1,110 @@
model:
base_learning_rate: 5.0e-03
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: image
cond_stage_key: caption
image_size: 64
channels: 4
cond_stage_trainable: true # Note: different from the one we trained before
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False
embedding_reg_weight: 0.0
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: 6
progressive_words: False
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
image_size: 32 # unused
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: 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.FrozenCLIPEmbedder
data:
target: main.DataModuleFromConfig
params:
batch_size: 1
num_workers: 2
wrap: false
train:
target: ldm.data.personalized.PersonalizedBase
params:
size: 512
set: train
per_image_tokens: false
repeats: 100
validation:
target: ldm.data.personalized.PersonalizedBase
params:
size: 512
set: val
per_image_tokens: false
repeats: 10
lightning:
modelcheckpoint:
params:
every_n_train_steps: 500
callbacks:
image_logger:
target: main.ImageLogger
params:
batch_frequency: 500
max_images: 5
increase_log_steps: False
trainer:
benchmark: False
max_steps: 6200
# max_steps: 4000

75
docker-build/Dockerfile Normal file
View File

@ -0,0 +1,75 @@
FROM ubuntu AS get_miniconda
SHELL ["/bin/bash", "-c"]
# install wget
RUN apt-get update \
&& apt-get install -y \
wget \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/*
# 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
FROM ubuntu AS invokeai
# use bash
SHELL [ "/bin/bash", "-c" ]
# clean bashrc
RUN echo "" > ~/.bashrc
# 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/*
# clone repository, create models.yaml and create symlinks
ARG invokeai_git=invoke-ai/InvokeAI
ARG invokeai_branch=main
ARG project_name=invokeai
RUN git clone -b ${invokeai_branch} https://github.com/${invokeai_git}.git /${project_name} \
&& cp /${project_name}/configs/models.yaml.example /${project_name}/configs/models.yaml \
&& ln -s /data/models/v1-5-pruned-emaonly.ckpt /${project_name}/models/ldm/stable-diffusion-v1/v1-5-pruned-emaonly.ckpt \
&& ln -s /data/outputs/ /${project_name}/outputs
# set workdir
WORKDIR /${project_name}
# 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 \
&& conda activate ${project_name} \
&& python scripts/preload_models.py \
--no-interactive
# Copy entrypoint and set env
ENV CONDA_PREFIX=${conda_prefix}
ENV PROJECT_NAME=${project_name}
COPY docker-build/entrypoint.sh /
ENTRYPOINT [ "/entrypoint.sh" ]

84
docker-build/build.sh Executable file
View File

@ -0,0 +1,84 @@
#!/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=${INVOKEAI_GIT:-invoke-ai/InvokeAI}
invokeai_branch=${INVOKEAI_BRANCH:-main}
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 "downloading v1-5-pruned-emaonly.ckpt"
_runAlpine wget \
--header="Authorization: Bearer ${huggingface_token}" \
-O models/v1-5-pruned-emaonly.ckpt \
https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt
echo "done"
}
_checkVolumeContent() {
_runAlpine ls -lhA /data/models
}
_getModelMd5s() {
_runAlpine \
alpine sh -c "md5sum /data/models/*.ckpt"
}
if [[ -n "$(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="${invokeai_git}" \
--build-arg invokeai_branch="${invokeai_branch}" \
--file ./docker-build/Dockerfile \
.

8
docker-build/entrypoint.sh Executable file
View File

@ -0,0 +1,8 @@
#!/bin/bash
set -e
source "${CONDA_PREFIX}/etc/profile.d/conda.sh"
conda activate "${PROJECT_NAME}"
python scripts/invoke.py \
${@:---web --host=0.0.0.0}

13
docker-build/env.sh Normal file
View File

@ -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

15
docker-build/run.sh Executable file
View File

@ -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" ${1:+$@}

View File

@ -1,51 +1,106 @@
# **Changelog** ---
title: Changelog
---
## v1.13 (in process) # :octicons-log-16: **Changelog**
- Supports a Google Colab notebook for a standalone server running on Google hardware [Arturo Mendivil](https://github.com/artmen1516) ## v2.0.1 (13 October 2022)
- WebUI supports GFPGAN/ESRGAN facial reconstruction and upscaling [Kevin Gibbons](https://github.com/bakkot)
- WebUI supports incremental display of in-progress images during generation [Kevin Gibbons](https://github.com/bakkot) - fix noisy images at high step count when using k* samplers
- Output directory can be specified on the dream> command line. - dream.py script now calls invoke.py module directly rather than
- The grid was displaying duplicated images when not enough images to fill the final row [Muhammad Usama](https://github.com/SMUsamaShah) via a new python process (which could break the environment)
- Can specify --grid on dream.py command line as the default.
## v2.0.0 <small>(9 October 2022)</small>
- `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains
for backward compatibility.
- Completely new WebGUI - launch with `python3 scripts/invoke.py --web`
- Support for [inpainting](features/INPAINTING.md) and [outpainting](features/OUTPAINTING.md)
- img2img runs on all k* samplers
- Support for [negative prompts](features/PROMPTS.md#negative-and-unconditioned-prompts)
- Support for CodeFormer face reconstruction
- Support for Textual Inversion on Macintoshes
- Support in both WebGUI and CLI for [post-processing of previously-generated images](features/POSTPROCESS.md)
using facial reconstruction, ESRGAN upscaling, outcropping (similar to DALL-E infinite canvas),
and "embiggen" upscaling. See the `!fix` command.
- New `--hires` option on `invoke>` line allows [larger images to be created without duplicating elements](features/CLI.md#this-is-an-example-of-txt2img), at the cost of some performance.
- New `--perlin` and `--threshold` options allow you to add and control variation
during image generation (see [Thresholding and Perlin Noise Initialization](features/OTHER.md#thresholding-and-perlin-noise-initialization-options))
- Extensive metadata now written into PNG files, allowing reliable regeneration of images
and tweaking of previous settings.
- Command-line completion in `invoke.py` now works on Windows, Linux and Mac platforms.
- Improved [command-line completion behavior](features/CLI.md)
New commands added:
- List command-line history with `!history`
- Search command-line history with `!search`
- Clear history with `!clear`
- Deprecated `--full_precision` / `-F`. Simply omit it and `invoke.py` will auto
configure. To switch away from auto use the new flag like `--precision=float32`.
## v1.14 <small>(11 September 2022)</small>
- Memory optimizations for small-RAM cards. 512x512 now possible on 4 GB GPUs.
- Full support for Apple hardware with M1 or M2 chips.
- Add "seamless mode" for circular tiling of image. Generates beautiful effects.
([prixt](https://github.com/prixt)).
- Inpainting support.
- Improved web server GUI.
- Lots of code and documentation cleanups.
## v1.13 <small>(3 September 2022)</small>
- Support image variations (see [VARIATIONS](features/VARIATIONS.md)
([Kevin Gibbons](https://github.com/bakkot) and many contributors and reviewers)
- Supports a Google Colab notebook for a standalone server running on Google hardware
[Arturo Mendivil](https://github.com/artmen1516)
- WebUI supports GFPGAN/ESRGAN facial reconstruction and upscaling
[Kevin Gibbons](https://github.com/bakkot)
- WebUI supports incremental display of in-progress images during generation
[Kevin Gibbons](https://github.com/bakkot)
- A new configuration file scheme that allows new models (including upcoming
stable-diffusion-v1.5) to be added without altering the code.
([David Wager](https://github.com/maddavid12))
- Can specify --grid on invoke.py command line as the default.
- Miscellaneous internal bug and stability fixes. - Miscellaneous internal bug and stability fixes.
- Works on M1 Apple hardware.
- Multiple bug fixes.
--- ---
## v1.12 (28 August 2022) ## v1.12 <small>(28 August 2022)</small>
- Improved file handling, including ability to read prompts from standard input. - Improved file handling, including ability to read prompts from standard input.
(kudos to [Yunsaki](https://github.com/yunsaki) (kudos to [Yunsaki](https://github.com/yunsaki)
- The web server is now integrated with the dream.py script. Invoke by adding --web to - The web server is now integrated with the invoke.py script. Invoke by adding --web to
the dream.py command arguments. the invoke.py command arguments.
- Face restoration and upscaling via GFPGAN and Real-ESGAN are now automatically - Face restoration and upscaling via GFPGAN and Real-ESGAN are now automatically
enabled if the GFPGAN directory is located as a sibling to Stable Diffusion. enabled if the GFPGAN directory is located as a sibling to Stable Diffusion.
VRAM requirements are modestly reduced. Thanks to both [Blessedcoolant](https://github.com/blessedcoolant) and VRAM requirements are modestly reduced. Thanks to both [Blessedcoolant](https://github.com/blessedcoolant) and
[Oceanswave](https://github.com/oceanswave) for their work on this. [Oceanswave](https://github.com/oceanswave) for their work on this.
- You can now swap samplers on the dream> command line. [Blessedcoolant](https://github.com/blessedcoolant) - You can now swap samplers on the invoke> command line. [Blessedcoolant](https://github.com/blessedcoolant)
--- ---
## v1.11 (26 August 2022) ## v1.11 <small>(26 August 2022)</small>
- NEW FEATURE: Support upscaling and face enhancement using the GFPGAN module. (kudos to [Oceanswave](https://github.com/Oceanswave) - NEW FEATURE: Support upscaling and face enhancement using the GFPGAN module. (kudos to [Oceanswave](https://github.com/Oceanswave)
- You now can specify a seed of -1 to use the previous image's seed, -2 to use the seed for the image generated before that, etc. - You now can specify a seed of -1 to use the previous image's seed, -2 to use the seed for the image generated before that, etc.
Seed memory only extends back to the previous command, but will work on all images generated with the -n# switch. Seed memory only extends back to the previous command, but will work on all images generated with the -n# switch.
- Variant generation support temporarily disabled pending more general solution. - Variant generation support temporarily disabled pending more general solution.
- Created a feature branch named **yunsaki-morphing-dream** which adds experimental support for - Created a feature branch named **yunsaki-morphing-invoke** which adds experimental support for
iteratively modifying the prompt and its parameters. Please see[ Pull Request #86](https://github.com/lstein/stable-diffusion/pull/86) iteratively modifying the prompt and its parameters. Please see[Pull Request #86](https://github.com/lstein/stable-diffusion/pull/86)
for a synopsis of how this works. Note that when this feature is eventually added to the main branch, it will may be modified for a synopsis of how this works. Note that when this feature is eventually added to the main branch, it will may be modified
significantly. significantly.
--- ---
## v1.10 (25 August 2022) ## v1.10 <small>(25 August 2022)</small>
- A barebones but fully functional interactive web server for online generation of txt2img and img2img. - A barebones but fully functional interactive web server for online generation of txt2img and img2img.
--- ---
## v1.09 (24 August 2022) ## v1.09 <small>(24 August 2022)</small>
- A new -v option allows you to generate multiple variants of an initial image - A new -v option allows you to generate multiple variants of an initial image
in img2img mode. (kudos to [Oceanswave](https://github.com/Oceanswave). [ in img2img mode. (kudos to [Oceanswave](https://github.com/Oceanswave). [
@ -55,9 +110,9 @@
--- ---
## v1.08 (24 August 2022) ## v1.08 <small>(24 August 2022)</small>
- Escape single quotes on the dream> command before trying to parse. This avoids - Escape single quotes on the invoke> command before trying to parse. This avoids
parse errors. parse errors.
- Removed instruction to get Python3.8 as first step in Windows install. - Removed instruction to get Python3.8 as first step in Windows install.
Anaconda3 does it for you. Anaconda3 does it for you.
@ -66,7 +121,7 @@
--- ---
## v1.07 (23 August 2022) ## v1.07 <small>(23 August 2022)</small>
- Image filenames will now never fill gaps in the sequence, but will be assigned the - Image filenames will now never fill gaps in the sequence, but will be assigned the
next higher name in the chosen directory. This ensures that the alphabetic and chronological next higher name in the chosen directory. This ensures that the alphabetic and chronological
@ -74,14 +129,14 @@
--- ---
## v1.06 (23 August 2022) ## v1.06 <small>(23 August 2022)</small>
- Added weighted prompt support contributed by [xraxra](https://github.com/xraxra) - Added weighted prompt support contributed by [xraxra](https://github.com/xraxra)
- Example of using weighted prompts to tweak a demonic figure contributed by [bmaltais](https://github.com/bmaltais) - Example of using weighted prompts to tweak a demonic figure contributed by [bmaltais](https://github.com/bmaltais)
--- ---
## v1.05 (22 August 2022 - after the drop) ## v1.05 <small>(22 August 2022 - after the drop)</small>
- Filenames now use the following formats: - Filenames now use the following formats:
000010.95183149.png -- Two files produced by the same command (e.g. -n2), 000010.95183149.png -- Two files produced by the same command (e.g. -n2),
@ -94,12 +149,12 @@
be regenerated with the indicated key be regenerated with the indicated key
- It should no longer be possible for one image to overwrite another - It should no longer be possible for one image to overwrite another
- You can use the "cd" and "pwd" commands at the dream> prompt to set and retrieve - You can use the "cd" and "pwd" commands at the invoke> prompt to set and retrieve
the path of the output directory. the path of the output directory.
--- ---
## v1.04 (22 August 2022 - after the drop) ## v1.04 <small>(22 August 2022 - after the drop)</small>
- Updated README to reflect installation of the released weights. - Updated README to reflect installation of the released weights.
- Suppressed very noisy and inconsequential warning when loading the frozen CLIP - Suppressed very noisy and inconsequential warning when loading the frozen CLIP
@ -107,31 +162,31 @@
--- ---
## v1.03 (22 August 2022) ## v1.03 <small>(22 August 2022)</small>
- The original txt2img and img2img scripts from the CompViz repository have been moved into - The original txt2img and img2img scripts from the CompViz repository have been moved into
a subfolder named "orig_scripts", to reduce confusion. a subfolder named "orig_scripts", to reduce confusion.
--- ---
## v1.02 (21 August 2022) ## v1.02 <small>(21 August 2022)</small>
- A copy of the prompt and all of its switches and options is now stored in the corresponding - A copy of the prompt and all of its switches and options is now stored in the corresponding
image in a tEXt metadata field named "Dream". You can read the prompt using scripts/images2prompt.py, image in a tEXt metadata field named "Dream". You can read the prompt using scripts/images2prompt.py,
or an image editor that allows you to explore the full metadata. or an image editor that allows you to explore the full metadata.
**Please run "conda env update -f environment.yaml" to load the k_lms dependencies!!** **Please run "conda env update" to load the k_lms dependencies!!**
--- ---
## v1.01 (21 August 2022) ## v1.01 <small>(21 August 2022)</small>
- added k_lms sampling. - added k_lms sampling.
**Please run "conda env update -f environment.yaml" to load the k_lms dependencies!!** **Please run "conda env update" to load the k_lms dependencies!!**
- use half precision arithmetic by default, resulting in faster execution and lower memory requirements - use half precision arithmetic by default, resulting in faster execution and lower memory requirements
Pass argument --full_precision to dream.py to get slower but more accurate image generation Pass argument --full_precision to invoke.py to get slower but more accurate image generation
--- ---
## Links ## Links
- **[Read Me](../readme.md)** - **[Read Me](index.md)**

Binary file not shown.

After

Width:  |  Height:  |  Size: 284 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 252 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 270 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 60 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 184 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 6.6 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 20 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 198 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 6.9 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 41 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 151 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 221 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 136 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 121 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 159 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 117 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 148 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 121 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 75 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 519 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 11 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 519 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 439 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 983 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 101 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 546 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 336 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 29 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 148 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 637 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 529 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.1 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 838 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 838 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 989 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 25 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 22 KiB

After

Width:  |  Height:  |  Size: 22 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 451 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 453 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 463 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 435 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 635 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 500 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 422 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 428 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 284 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 252 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 428 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 331 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 369 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 362 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 329 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 329 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 377 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 328 KiB

Some files were not shown because too many files have changed in this diff Show More