Compare commits

..

34 Commits

Author SHA1 Message Date
Lincoln Stein
0ca842ad87 Merge branch 'main' of github.com:invoke-ai/InvokeAI into main 2022-11-03 06:52:17 -04:00
Lincoln Stein
12e7e6e8df move getpass_asterisk from conda dependency to pip dependency
- Addresses Issue #1354
2022-11-03 06:51:34 -04:00
Lincoln Stein
152b7fc2bc fix up branch that 1-click installers will pull from 2022-11-03 00:32:49 -04:00
Lincoln Stein
4bb6c8180e Update index.md 2022-11-03 00:19:57 -04:00
Lincoln Stein
a338616ced final documentation fixes prior to release 2022-11-03 00:00:09 -04:00
Lincoln Stein
65a99c47d3 add missing documentation image 2022-11-02 23:41:50 -04:00
Lincoln Stein
e4bb49b4f0 update outpaint documentation 2022-11-02 23:41:16 -04:00
Lincoln Stein
2ad489a1ef dream->invoke in inpainting docs 2022-11-02 23:18:30 -04:00
Lincoln Stein
ecb904f8b7 update environment-mac.yml 2022-11-02 23:12:48 -04:00
mauwii
61ead2c92d replace old fashined markdown templates with forms
this will help the readability of issues a lot 🤓
2022-11-02 22:26:01 -04:00
spezialspezial
c5a8c499ab Raise exception instead of undefined internal state
Hi, please consider raising a proper exception here instead of an undefined internal state. This happens for example if the filepath to the model.ckpt is invalid on first load.
2022-11-02 22:26:00 -04:00
psychedelicious
bd6278c361 Fixes indentation causing rendering issue with github.io page 2022-11-02 22:25:13 -04:00
Eric Wolf
e24d4dc15b Fix discord link
The discord badge has the correct link but the quick links did not
2022-11-02 22:25:12 -04:00
Lincoln Stein
3d4c70604d update requirements to address #1149 2022-11-02 22:25:12 -04:00
mauwii
d73aea43b7 update precision info 2022-11-02 22:17:50 -04:00
mauwii
358f0af79a fix prompt in README.md 2022-11-02 22:17:50 -04:00
mauwii
0650735f74 (re-) fix a lot in mkdocs 2022-11-02 22:17:50 -04:00
mauwii
e469bbb89e fix links to point to invoke-ai.github.io 2022-11-02 22:17:14 -04:00
Lincoln Stein
a46633a355 adding license using GitHub template
Did not attempt to add additional copyright information.
2022-11-02 22:17:14 -04:00
Lincoln Stein
7275006c37 remove license files temporarily 2022-11-02 22:17:14 -04:00
Lincoln Stein
e438d46314 remove additional copyrights from license file
Trying to get GitHub to recognize our MIT license. Perhaps the additional copyrights are confusing it.
2022-11-02 22:17:14 -04:00
Lincoln Stein
bf8d6d8908 Second try at getting GitHub to register license 2022-11-02 22:17:13 -04:00
majick
b9e1aeb2dd Fix broken links to CLI.md
* Looks like there was a bad paste
2022-11-02 22:16:28 -04:00
mauwii
fd81a69b4d add current branch to push trigger 2022-11-02 22:16:13 -04:00
mauwii
5a15ad3148 switch to default channel in environment-mac.yml 2022-11-02 22:15:45 -04:00
mauwii
22a37ef714 use very short validation for Pull Requests 2022-11-02 22:12:15 -04:00
mauwii
59c8024f0c remove pr trigger 2022-11-02 22:10:31 -04:00
Matthias Wild
22b3a59f16 squash merge update-gh-actions into fix-gh-actions
* fix mkdocs deployment

* update path to python bin

* add trigger for current branch

* change path to python_bin for mac as well

* try to use setup-python@v4 instead of setting env

* remove setup conda action

* try to use $CONDA

* remove overseen action

* change branch from master to main

* sort out if then else for faster syntax

* remove more if functions

* add updates to create-caches as well

* eliminate the rest of if functions

* try to unpin pytorch and torchvision

* restore pinned versions

* try switching from set-output to use env

* update test-invoke-conda as well

* fix env var creation

* quote variable

* add second equal to compare

* try another way to use outputs

* fix outputs

* pip install for mac before creating conda env

* fix output variable

* fix python bin path

* remove pip install for before creating conda env

* unpin streamlit version in conda mac env

* try to make git-workflows better readable

* remove 4gotten trigger

* Update-gh-actions (#6)

* fix mkdocs deployment

* update path to python bin

* add trigger for current branch

* change path to python_bin for mac as well

* try to use setup-python@v4 instead of setting env

* remove setup conda action

* try to use $CONDA

* remove overseen action

* change branch from master to main

* sort out if then else for faster syntax

* remove more if functions

* add updates to create-caches as well

* eliminate the rest of if functions

* try to unpin pytorch and torchvision

* restore pinned versions

* try switching from set-output to use env

* update test-invoke-conda as well

* fix env var creation

* quote variable

* add second equal to compare

* try another way to use outputs

* fix outputs

* pip install for mac before creating conda env

* fix output variable

* fix python bin path

* remove pip install for before creating conda env

* unpin streamlit version in conda mac env

* try to make git-workflows better readable

* use macos-latest

* try to update conda before creating mac env

* better conda update trial

* re-pin streamlit version

* re-added trigger to run workflow in current branch

* try to find out if conda mac env could be updated

* install cmake, protobuf and rust b4 conda

* add yes to conda update

* lets try anaconda3-2022.05

* try environment.yml for mac as well

* reenable conda mac env, add pip install
also fix gitignore by changing from dream to invoke

* remove
- unecesary virtualenv creation
- conda update

change != macos back to == linux

* remove cmake from brew install since pre-installed

* disable opencv-python pip requirement

* fixed commands to find latest package versions

* update requirements for mac env

* back to the roots - only install conda env
depending on runner_os with or without extra env variables

* check out macOS in azure-pipelines
since becoming kind of tired of the GitHub Runner which is broken as ...

* let's try to setup python and update conda env

* initialize conda before using it

* add trigger in azure-pipelines.yml

* And another go for update first ....

* update azure-pipelines.yml
- add caching
- add checkpoint download
- add paths to trigger
and more

* unquote checkpoint-url

* fix chekpoint-url variable

* mkdir before downloading model

* set pr trigger to main, rename anaconda cache

* unique cacheHitVariables

* try to use macos-latest instead of macos-12

* update test-invoke-conda.yml:
- remove unecesarry echo step
- use s-weigand/setup-conda@v1
- remove conda update from install deps step since updated with action

* update test-invoke-conda.yml:
- rename conda env cache from ldm to invokeai
- reorder steps:
  1. checkout sources
  2. setup python
  3. setup conda
  4. keep order after set platform variables

* change macos back to 12 since also fails with 11

* update condition in run the tests
make difference between main or not main

* fix path to cache invokeai conda env

* fix invokeai conda env cache path

* update mkdocs-flow.yml

* change conda-channel priority

* update create-caches

* update conda env also when cache was used

* os dependend conda env cache path

* use existing CONDA env pointing to conda root

* create CONDA_ROOT output from $CONDA

* use output variable to define test prompts

* use setup-python v4, get rid of PYTHON_BIN env

* add runner.os to result artifacts name

* update test-invoke-conda.yml:
- reuse macos-latest
- disable setup python 3.9
- setup conda with default python version
- create or update conda environment depending on cache success
- remove name parameter from conda update since name is set in env yml

* improve mkdocs-flow.yml

* disable cache-hugginface-torch
since preload_models.py downloads to more than one location

* update mkdocs-flow.yml with new name

* rename mkdocs action to mkdocs-material

* try to ignore error when creating conda env
maybe it would still be usable, lets see ;P

* remove bloat

* update environment-mac.yml
to match dependencies of invoke-ai/InvokeAI's main branch

* disable conda update, tweak prompt condition

* try to set some env vars for macOS to fix conda

* stop ignoring error, use env instead of outputs

* tweak `[[` connditions

* update python and pip dependencie
makes a difference of 1 sec per itteration compared to 3.9!!!
also I see no reason why using a old pip version would be beneficial

* remove unecesarry env for macOS
everything was pre-tested on my MacBook Air 2020 with M1

* update conda env in setup step

* activate conda env after installation

* update test-invoke-conda.yml
- set conda env dependent on matrix.os
- set CONDA_ENV_NAME to prevent breaking action when renaming conda env
- fix conda env activation

* fix activate conda env

* set bash -l as default shell

* use action to activate conda env

* add conda env file to env activation

* try to replace s-weigeand with conda-incubator

* remove azure-pipelines.yml
funniest part is that the macos runner is the same as the one on github!

* include environment-file in matrix
- also disable auto-activate-base and auto-update-conda
- include macos-latest and macos-12 for debugging purpose
- set miniforge-version in matrix

* fix miniforge-variant, set fail-fast to false

* add step to setup miniconda
- make default shell a matrix variable
- remove bloat

* use a mac env yml without pinned versions

* unpin nomkl, pytorch and torchvision
also removed opencv-pyhton

* cache conda pkgs dir instead of conda env

* use python 3.10, exclude macos-12 from cache

* fix expression

* prepare for PR

* fix doubled id

* reuse pinned versions in mac conda env
- updated python pip version
- unpined pytorch and torchvision
- removed opencv-python
- updated versions to most recent (tested locally)

* fix classical copy/paste error

* remove unused env from shell-block comment

* fix hashFiles function to determine restore-keys

* reenable caching `~.cache`, update create-caches

* unpin all versions in mac conda env file
this was the only way I got it working in the action, also works locally
tested on MacBook Air 2020 M1
remove environment-mac-unpinned.yml

* prepare merge by removing this branch from trigger

* include pull_request trigger for main and dev

* remove pull_request trigger
2022-11-02 22:10:31 -04:00
mauwii
48e21486cb remove pr trigger 2022-11-02 22:07:42 -04:00
Matthias Wild
a6fa882b7c squash merge update-gh-actions into fix-gh-actions
* fix mkdocs deployment

* update path to python bin

* add trigger for current branch

* change path to python_bin for mac as well

* try to use setup-python@v4 instead of setting env

* remove setup conda action

* try to use $CONDA

* remove overseen action

* change branch from master to main

* sort out if then else for faster syntax

* remove more if functions

* add updates to create-caches as well

* eliminate the rest of if functions

* try to unpin pytorch and torchvision

* restore pinned versions

* try switching from set-output to use env

* update test-invoke-conda as well

* fix env var creation

* quote variable

* add second equal to compare

* try another way to use outputs

* fix outputs

* pip install for mac before creating conda env

* fix output variable

* fix python bin path

* remove pip install for before creating conda env

* unpin streamlit version in conda mac env

* try to make git-workflows better readable

* remove 4gotten trigger

* Update-gh-actions (#6)

* fix mkdocs deployment

* update path to python bin

* add trigger for current branch

* change path to python_bin for mac as well

* try to use setup-python@v4 instead of setting env

* remove setup conda action

* try to use $CONDA

* remove overseen action

* change branch from master to main

* sort out if then else for faster syntax

* remove more if functions

* add updates to create-caches as well

* eliminate the rest of if functions

* try to unpin pytorch and torchvision

* restore pinned versions

* try switching from set-output to use env

* update test-invoke-conda as well

* fix env var creation

* quote variable

* add second equal to compare

* try another way to use outputs

* fix outputs

* pip install for mac before creating conda env

* fix output variable

* fix python bin path

* remove pip install for before creating conda env

* unpin streamlit version in conda mac env

* try to make git-workflows better readable

* use macos-latest

* try to update conda before creating mac env

* better conda update trial

* re-pin streamlit version

* re-added trigger to run workflow in current branch

* try to find out if conda mac env could be updated

* install cmake, protobuf and rust b4 conda

* add yes to conda update

* lets try anaconda3-2022.05

* try environment.yml for mac as well

* reenable conda mac env, add pip install
also fix gitignore by changing from dream to invoke

* remove
- unecesary virtualenv creation
- conda update

change != macos back to == linux

* remove cmake from brew install since pre-installed

* disable opencv-python pip requirement

* fixed commands to find latest package versions

* update requirements for mac env

* back to the roots - only install conda env
depending on runner_os with or without extra env variables

* check out macOS in azure-pipelines
since becoming kind of tired of the GitHub Runner which is broken as ...

* let's try to setup python and update conda env

* initialize conda before using it

* add trigger in azure-pipelines.yml

* And another go for update first ....

* update azure-pipelines.yml
- add caching
- add checkpoint download
- add paths to trigger
and more

* unquote checkpoint-url

* fix chekpoint-url variable

* mkdir before downloading model

* set pr trigger to main, rename anaconda cache

* unique cacheHitVariables

* try to use macos-latest instead of macos-12

* update test-invoke-conda.yml:
- remove unecesarry echo step
- use s-weigand/setup-conda@v1
- remove conda update from install deps step since updated with action

* update test-invoke-conda.yml:
- rename conda env cache from ldm to invokeai
- reorder steps:
  1. checkout sources
  2. setup python
  3. setup conda
  4. keep order after set platform variables

* change macos back to 12 since also fails with 11

* update condition in run the tests
make difference between main or not main

* fix path to cache invokeai conda env

* fix invokeai conda env cache path

* update mkdocs-flow.yml

* change conda-channel priority

* update create-caches

* update conda env also when cache was used

* os dependend conda env cache path

* use existing CONDA env pointing to conda root

* create CONDA_ROOT output from $CONDA

* use output variable to define test prompts

* use setup-python v4, get rid of PYTHON_BIN env

* add runner.os to result artifacts name

* update test-invoke-conda.yml:
- reuse macos-latest
- disable setup python 3.9
- setup conda with default python version
- create or update conda environment depending on cache success
- remove name parameter from conda update since name is set in env yml

* improve mkdocs-flow.yml

* disable cache-hugginface-torch
since preload_models.py downloads to more than one location

* update mkdocs-flow.yml with new name

* rename mkdocs action to mkdocs-material

* try to ignore error when creating conda env
maybe it would still be usable, lets see ;P

* remove bloat

* update environment-mac.yml
to match dependencies of invoke-ai/InvokeAI's main branch

* disable conda update, tweak prompt condition

* try to set some env vars for macOS to fix conda

* stop ignoring error, use env instead of outputs

* tweak `[[` connditions

* update python and pip dependencie
makes a difference of 1 sec per itteration compared to 3.9!!!
also I see no reason why using a old pip version would be beneficial

* remove unecesarry env for macOS
everything was pre-tested on my MacBook Air 2020 with M1

* update conda env in setup step

* activate conda env after installation

* update test-invoke-conda.yml
- set conda env dependent on matrix.os
- set CONDA_ENV_NAME to prevent breaking action when renaming conda env
- fix conda env activation

* fix activate conda env

* set bash -l as default shell

* use action to activate conda env

* add conda env file to env activation

* try to replace s-weigeand with conda-incubator

* remove azure-pipelines.yml
funniest part is that the macos runner is the same as the one on github!

* include environment-file in matrix
- also disable auto-activate-base and auto-update-conda
- include macos-latest and macos-12 for debugging purpose
- set miniforge-version in matrix

* fix miniforge-variant, set fail-fast to false

* add step to setup miniconda
- make default shell a matrix variable
- remove bloat

* use a mac env yml without pinned versions

* unpin nomkl, pytorch and torchvision
also removed opencv-pyhton

* cache conda pkgs dir instead of conda env

* use python 3.10, exclude macos-12 from cache

* fix expression

* prepare for PR

* fix doubled id

* reuse pinned versions in mac conda env
- updated python pip version
- unpined pytorch and torchvision
- removed opencv-python
- updated versions to most recent (tested locally)

* fix classical copy/paste error

* remove unused env from shell-block comment

* fix hashFiles function to determine restore-keys

* reenable caching `~.cache`, update create-caches

* unpin all versions in mac conda env file
this was the only way I got it working in the action, also works locally
tested on MacBook Air 2020 M1
remove environment-mac-unpinned.yml

* prepare merge by removing this branch from trigger

* include pull_request trigger for main and dev

* remove pull_request trigger
2022-11-02 22:07:42 -04:00
Lincoln Stein
aa12adccf3 restore inline images
<div> around the inline images works great in gh-pages, but breaks plain old markdown in GitHub code display. This removes the <div>s, causing slight degradation in quality of gh-page appearance.
2022-11-02 22:02:17 -04:00
Lincoln Stein
282a2f642b restore inline images
<div> seems to be messing with the ability of the plain-old markdown processor to display inline images. Slightly degrades appearance of gh-pages.
2022-11-02 22:02:16 -04:00
Eric Wolf
d211c34f7b Update 'ldm' env to 'invokeai' in troubleshooting steps 2022-11-02 22:01:48 -04:00
Conor Reid
e995e97690 Update generate.py
Fixed spelling mistake (open source king)
2022-11-02 22:01:17 -04:00
494 changed files with 26977 additions and 30755 deletions

View File

@@ -1,12 +1,3 @@
*
!backend
!configs
!environments-and-requirements
!frontend
!installer
!ldm
!main.py
!scripts
!server
!static
!setup.py
!environment*.yml
!docker-build

3
.github/CODEOWNERS vendored
View File

@@ -2,6 +2,3 @@ ldm/invoke/pngwriter.py @CapableWeb
ldm/invoke/server_legacy.py @CapableWeb
scripts/legacy_api.py @CapableWeb
tests/legacy_tests.sh @CapableWeb
installer/ @tildebyte
.github/workflows/ @mauwii
docker_build/ @mauwii

View File

@@ -6,21 +6,14 @@ on:
branches:
- 'main'
- 'development'
- 'update-dockerfile'
pull_request:
branches:
- 'main'
- 'development'
jobs:
docker:
strategy:
fail-fast: false
matrix:
arch:
- x86_64
- aarch64
pip-requirements:
- requirements-lin-amd.txt
- requirements-lin-cuda.txt
runs-on: ubuntu-latest
name: ${{ matrix.pip-requirements }} ${{ matrix.arch }}
steps:
- name: prepare docker-tag
env:
@@ -32,12 +25,18 @@ jobs:
uses: docker/setup-qemu-action@v2
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v2
- name: Cache Docker layers
uses: actions/cache@v2
with:
path: /tmp/.buildx-cache
key: buildx-${{ hashFiles('docker-build/Dockerfile') }}
- name: Build container
uses: docker/build-push-action@v3
with:
context: .
file: docker-build/Dockerfile
platforms: Linux/${{ matrix.arch }}
platforms: linux/amd64
push: false
tags: ${{ env.dockertag }}:${{ matrix.pip-requirements }}-${{ matrix.arch }}
build-args: pip_requirements=${{ matrix.pip-requirements }}
tags: ${{ env.dockertag }}:latest
cache-from: type=local,src=/tmp/.buildx-cache
cache-to: type=local,dest=/tmp/.buildx-cache

80
.github/workflows/create-caches.yml vendored Normal file
View File

@@ -0,0 +1,80 @@
name: Create Caches
on: workflow_dispatch
jobs:
os_matrix:
strategy:
matrix:
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: ${{ matrix.default-shell }}
steps:
- name: Checkout sources
uses: actions/checkout@v3
- name: setup miniconda
uses: conda-incubator/setup-miniconda@v2
with:
auto-activate-base: false
auto-update-conda: false
miniconda-version: latest
- name: set environment
run: |
[[ "$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
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: |
[[ -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:
activate-environment: ${{ env.CONDA_ENV_NAME }}
environment-file: ${{ matrix.environment-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: run preload_models.py
run: python scripts/preload_models.py

View File

@@ -22,7 +22,7 @@ jobs:
- name: install requirements
run: |
python -m \
pip install -r docs/requirements-mkdocs.txt
pip install -r requirements-mkdocs.txt
- name: confirm buildability
run: |

View File

@@ -13,32 +13,31 @@ on:
jobs:
matrix:
strategy:
fail-fast: false
matrix:
stable-diffusion-model:
- 'stable-diffusion-1.5'
environment-yaml:
- environment-lin-amd.yml
- environment-lin-cuda.yml
- environment-mac.yml
# - '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:
- environment-yaml: environment-lin-amd.yml
os: ubuntu-latest
- os: ubuntu-latest
environment-file: environment.yml
default-shell: bash -l {0}
- environment-yaml: environment-lin-cuda.yml
os: ubuntu-latest
- os: macOS-12
environment-file: environment-mac.yml
default-shell: bash -l {0}
- environment-yaml: environment-mac.yml
os: macos-12
default-shell: bash -l {0}
- stable-diffusion-model: stable-diffusion-1.5
stable-diffusion-model-url: 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
stable-diffusion-model-dl-name: v1-5-pruned-emaonly.ckpt
name: ${{ matrix.environment-yaml }} on ${{ matrix.os }}
# - 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: ${{ matrix.os }}
env:
CONDA_ENV_NAME: invokeai
INVOKEAI_ROOT: '${{ github.workspace }}/invokeai'
defaults:
run:
shell: ${{ matrix.default-shell }}
@@ -48,26 +47,21 @@ jobs:
uses: actions/checkout@v3
- name: create models.yaml from example
run: |
mkdir -p ${{ env.INVOKEAI_ROOT }}/configs
cp configs/models.yaml.example ${{ env.INVOKEAI_ROOT }}/configs/models.yaml
- name: create environment.yml
run: cp "environments-and-requirements/${{ matrix.environment-yaml }}" environment.yml
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 }}-${{ hashFiles(matrix.environment-yaml) }}
key: conda-pkgs-${{ 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: environment.yml
environment-file: ${{ matrix.environment-file }}
miniconda-version: latest
- name: set test prompt to main branch validation
@@ -82,38 +76,28 @@ jobs:
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 }}
with:
path: ${{ env.INVOKEAI_ROOT }}/${{ matrix.stable-diffusion-model-dl-path }}
key: ${{ env.cache-name }}
- name: Download ${{ matrix.stable-diffusion-model }}
- name: Download ${{ matrix.stable-diffusion-model-switch }}
id: download-stable-diffusion-model
if: ${{ steps.cache-sd-model.outputs.cache-hit != 'true' }}
run: |
mkdir -p "${{ env.INVOKEAI_ROOT }}/${{ matrix.stable-diffusion-model-dl-path }}"
[[ -d models/ldm/stable-diffusion-v1 ]] \
|| mkdir -p models/ldm/stable-diffusion-v1
curl \
-H "Authorization: Bearer ${{ secrets.HUGGINGFACE_TOKEN }}" \
-o "${{ env.INVOKEAI_ROOT }}/${{ matrix.stable-diffusion-model-dl-path }}/${{ matrix.stable-diffusion-model-dl-name }}" \
-L ${{ matrix.stable-diffusion-model-url }}
-o ${{ matrix.stable-diffusion-model-dl-path }} \
-L ${{ matrix.stable-diffusion-model }}
- name: run configure_invokeai.py
- name: run preload_models.py
id: run-preload-models
run: |
python scripts/configure_invokeai.py --no-interactive --yes
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 }} \
--from_file ${{ env.TEST_PROMPTS }} \
--root="${{ env.INVOKEAI_ROOT }}" \
--outdir="${{ env.INVOKEAI_ROOT }}/outputs"
--model ${{ matrix.stable-diffusion-model-switch }} \
--from_file ${{ env.TEST_PROMPTS }}
- name: export conda env
id: export-conda-env
@@ -125,5 +109,5 @@ jobs:
id: archive-results
uses: actions/upload-artifact@v3
with:
name: results_${{ matrix.requirements-file }}_${{ matrix.python-version }}
path: ${{ env.INVOKEAI_ROOT }}/outputs
name: results_${{ matrix.os }}_${{ matrix.stable-diffusion-model-switch }}
path: outputs/img-samples

View File

@@ -1,122 +0,0 @@
name: Test invoke.py pip
on:
push:
branches:
- 'main'
- 'development'
pull_request:
branches:
- 'main'
- 'development'
jobs:
matrix:
strategy:
matrix:
stable-diffusion-model:
- stable-diffusion-1.5
requirements-file:
- requirements-lin-cuda.txt
- requirements-lin-amd.txt
- requirements-mac-mps-cpu.txt
python-version:
# - '3.9'
- '3.10'
include:
- requirements-file: requirements-lin-cuda.txt
os: ubuntu-latest
default-shell: bash -l {0}
- requirements-file: requirements-lin-amd.txt
os: ubuntu-latest
default-shell: bash -l {0}
- requirements-file: requirements-mac-mps-cpu.txt
os: macOS-12
default-shell: bash -l {0}
- stable-diffusion-model: stable-diffusion-1.5
stable-diffusion-model-url: 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
stable-diffusion-model-dl-name: v1-5-pruned-emaonly.ckpt
name: ${{ matrix.requirements-file }} on ${{ matrix.python-version }}
runs-on: ${{ matrix.os }}
defaults:
run:
shell: ${{ matrix.default-shell }}
env:
INVOKEAI_ROOT: '${{ github.workspace }}/invokeai'
steps:
- name: Checkout sources
id: checkout-sources
uses: actions/checkout@v3
- name: create models.yaml from example
run: |
mkdir -p ${{ env.INVOKEAI_ROOT }}/configs
cp configs/models.yaml.example ${{ env.INVOKEAI_ROOT }}/configs/models.yaml
- 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" >> $GITHUB_ENV
- name: create requirements.txt
run: cp 'environments-and-requirements/${{ matrix.requirements-file }}' '${{ matrix.requirements-file }}'
- name: setup python
uses: actions/setup-python@v4
with:
python-version: ${{ matrix.python-version }}
cache: 'pip'
cache-dependency-path: ${{ matrix.requirements-file }}
# - name: install dependencies
# run: ${{ env.pythonLocation }}/bin/pip install --upgrade pip setuptools wheel
- name: install requirements
run: ${{ env.pythonLocation }}/bin/pip install -r '${{ matrix.requirements-file }}'
- name: Use Cached Stable Diffusion Model
id: cache-sd-model
uses: actions/cache@v3
env:
cache-name: cache-${{ matrix.stable-diffusion-model }}
with:
path: ${{ env.INVOKEAI_ROOT }}/${{ matrix.stable-diffusion-model-dl-path }}
key: ${{ env.cache-name }}
- name: Download ${{ matrix.stable-diffusion-model }}
id: download-stable-diffusion-model
if: ${{ steps.cache-sd-model.outputs.cache-hit != 'true' }}
run: |
mkdir -p "${{ env.INVOKEAI_ROOT }}/${{ matrix.stable-diffusion-model-dl-path }}"
curl \
-H "Authorization: Bearer ${{ secrets.HUGGINGFACE_TOKEN }}" \
-o "${{ env.INVOKEAI_ROOT }}/${{ matrix.stable-diffusion-model-dl-path }}/${{ matrix.stable-diffusion-model-dl-name }}" \
-L ${{ matrix.stable-diffusion-model-url }}
- name: run configure_invokeai.py
id: run-preload-models
run: |
${{ env.pythonLocation }}/bin/python scripts/configure_invokeai.py --no-interactive --yes
- name: Run the tests
id: run-tests
run: |
time ${{ env.pythonLocation }}/bin/python scripts/invoke.py \
--model ${{ matrix.stable-diffusion-model }} \
--from_file ${{ env.TEST_PROMPTS }} \
--root="${{ env.INVOKEAI_ROOT }}" \
--outdir="${{ env.INVOKEAI_ROOT }}/outputs"
- name: Archive results
id: archive-results
uses: actions/upload-artifact@v3
with:
name: results_${{ matrix.requirements-file }}_${{ matrix.python-version }}
path: ${{ env.INVOKEAI_ROOT }}/outputs

30
.gitignore vendored
View File

@@ -1,8 +1,7 @@
# ignore default image save location and model symbolic link
outputs/
models/ldm/stable-diffusion-v1/model.ckpt
**/restoration/codeformer/weights
ldm/invoke/restoration/codeformer/weights
# ignore user models config
configs/models.user.yaml
config/models.user.yml
@@ -201,7 +200,6 @@ checkpoints
gfpgan/
models/ldm/stable-diffusion-v1/*.sha256
# GFPGAN model files
gfpgan/
@@ -209,28 +207,4 @@ gfpgan/
configs/models.yaml
# weights (will be created by installer)
models/ldm/stable-diffusion-v1/*.ckpt
models/clipseg
models/gfpgan
# ignore initfile
.invokeai
# ignore environment.yml and requirements.txt
# these are links to the real files in environments-and-requirements
environment.yml
requirements.txt
# source installer files
source_installer/*zip
source_installer/invokeAI
install.bat
install.sh
update.bat
update.sh
# this may be present if the user created a venv
invokeai
# no longer stored in source directory
models
models/ldm/stable-diffusion-v1/*.ckpt

View File

@@ -1,128 +0,0 @@
# Contributor Covenant Code of Conduct
## Our Pledge
We as members, contributors, and leaders pledge to make participation in our
community a harassment-free experience for everyone, regardless of age, body
size, visible or invisible disability, ethnicity, sex characteristics, gender
identity and expression, level of experience, education, socio-economic status,
nationality, personal appearance, race, religion, or sexual identity
and orientation.
We pledge to act and interact in ways that contribute to an open, welcoming,
diverse, inclusive, and healthy community.
## Our Standards
Examples of behavior that contributes to a positive environment for our
community include:
* Demonstrating empathy and kindness toward other people
* Being respectful of differing opinions, viewpoints, and experiences
* Giving and gracefully accepting constructive feedback
* Accepting responsibility and apologizing to those affected by our mistakes,
and learning from the experience
* Focusing on what is best not just for us as individuals, but for the
overall community
Examples of unacceptable behavior include:
* The use of sexualized language or imagery, and sexual attention or
advances of any kind
* Trolling, insulting or derogatory comments, and personal or political attacks
* Public or private harassment
* Publishing others' private information, such as a physical or email
address, without their explicit permission
* Other conduct which could reasonably be considered inappropriate in a
professional setting
## Enforcement Responsibilities
Community leaders are responsible for clarifying and enforcing our standards of
acceptable behavior and will take appropriate and fair corrective action in
response to any behavior that they deem inappropriate, threatening, offensive,
or harmful.
Community leaders have the right and responsibility to remove, edit, or reject
comments, commits, code, wiki edits, issues, and other contributions that are
not aligned to this Code of Conduct, and will communicate reasons for moderation
decisions when appropriate.
## Scope
This Code of Conduct applies within all community spaces, and also applies when
an individual is officially representing the community in public spaces.
Examples of representing our community include using an official e-mail address,
posting via an official social media account, or acting as an appointed
representative at an online or offline event.
## Enforcement
Instances of abusive, harassing, or otherwise unacceptable behavior
may be reported to the community leaders responsible for enforcement
at https://github.com/invoke-ai/InvokeAI/issues. All complaints will
be reviewed and investigated promptly and fairly.
All community leaders are obligated to respect the privacy and security of the
reporter of any incident.
## Enforcement Guidelines
Community leaders will follow these Community Impact Guidelines in determining
the consequences for any action they deem in violation of this Code of Conduct:
### 1. Correction
**Community Impact**: Use of inappropriate language or other behavior deemed
unprofessional or unwelcome in the community.
**Consequence**: A private, written warning from community leaders, providing
clarity around the nature of the violation and an explanation of why the
behavior was inappropriate. A public apology may be requested.
### 2. Warning
**Community Impact**: A violation through a single incident or series
of actions.
**Consequence**: A warning with consequences for continued behavior. No
interaction with the people involved, including unsolicited interaction with
those enforcing the Code of Conduct, for a specified period of time. This
includes avoiding interactions in community spaces as well as external channels
like social media. Violating these terms may lead to a temporary or
permanent ban.
### 3. Temporary Ban
**Community Impact**: A serious violation of community standards, including
sustained inappropriate behavior.
**Consequence**: A temporary ban from any sort of interaction or public
communication with the community for a specified period of time. No public or
private interaction with the people involved, including unsolicited interaction
with those enforcing the Code of Conduct, is allowed during this period.
Violating these terms may lead to a permanent ban.
### 4. Permanent Ban
**Community Impact**: Demonstrating a pattern of violation of community
standards, including sustained inappropriate behavior, harassment of an
individual, or aggression toward or disparagement of classes of individuals.
**Consequence**: A permanent ban from any sort of public interaction within
the community.
## Attribution
This Code of Conduct is adapted from the [Contributor Covenant][homepage],
version 2.0, available at
https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
Community Impact Guidelines were inspired by [Mozilla's code of conduct
enforcement ladder](https://github.com/mozilla/diversity).
[homepage]: https://www.contributor-covenant.org
For answers to common questions about this code of conduct, see the FAQ at
https://www.contributor-covenant.org/faq. Translations are available at
https://www.contributor-covenant.org/translations.

View File

@@ -1,85 +0,0 @@
<img src="docs/assets/invoke_ai_banner.png" align="center">
Invoke-AI is a community of software developers, researchers, and user
interface experts who have come together on a voluntary basis to build
software tools which support cutting edge AI text-to-image
applications. This community is open to anyone who wishes to
contribute to the effort and has the skill and time to do so.
# Our Values
The InvokeAI team is a diverse community which includes individuals
from various parts of the world and many walks of life. Despite our
differences, we share a number of core values which we ask prospective
contributors to understand and respect. We believe:
1. That Open Source Software is a positive force in the world. We
create software that can be used, reused, and redistributed, without
restrictions, under a straightforward Open Source license (MIT). We
believe that Open Source benefits society as a whole by increasing the
availability of high quality software to all.
2. That those who create software should receive proper attribution
for their creative work. While we support the exchange and reuse of
Open Source Software, we feel strongly that the original authors of a
piece of code should receive credit for their contribution, and we
endeavor to do so whenever possible.
3. That there is moral ambiguity surrounding AI-assisted art. We are
aware of the moral and ethical issues surrounding the release of the
Stable Diffusion model and similar products. We are aware that, due to
the composition of their training sets, current AI-generated image
models are biased against certain ethnic groups, cultural concepts of
beauty, ethnic stereotypes, and gender roles.
1. We recognize the potential for harm to these groups that these biases
represent and trust that future AI models will take steps towards
reducing or eliminating the biases noted above, respect and give due
credit to the artists whose work is sourced, and call on developers
and users to favor these models over the older ones as they become
available.
4. We are deeply committed to ensuring that this technology benefits
everyone, including artists. We see AI art not as a replacement for
the artist, but rather as a tool to empower them. With that
in mind, we are constantly debating how to build systems that put
artists needs first: tools which can be readily integrated into an
artists existing workflows and practices, enhancing their work and
helping them to push it further. Every decision we take as a team,
which includes several artists, aims to build towards that goal.
5. That artificial intelligence can be a force for good in the world,
but must be used responsibly. Artificial intelligence technologies
have the potential to improve society, in everything from cancer care,
to customer service, to creative writing.
1. While we do not believe that software should arbitrarily limit what
users can do with it, we recognize that when used irresponsibly, AI
has the potential to do much harm. Our Discord server is actively
moderated in order to minimize the potential of harm from
user-contributed images. In addition, we ask users of our software to
refrain from using it in any way that would cause mental, emotional or
physical harm to individuals and vulnerable populations including (but
not limited to) women; minors; ethnic minorities; religious groups;
members of LGBTQIA communities; and people with disabilities or
impairments.
2. Note that some of the image generation AI models which the Invoke-AI
toolkit supports carry licensing agreements which impose restrictions
on how the model is used. We ask that our users read and agree to
these terms if they wish to make use of these models. These agreements
are distinct from the MIT license which applies to the InvokeAI
software and source code.
6. That mutual respect is key to a healthy software development
community. Members of the InvokeAI community are expected to treat
each other with respect, beneficence, and empathy. Each of us has a
different background and a unique set of skills. We strive to help
each other grow and gain new skills, and we apportion expectations in
a way that balances the members' time, skillset, and interest
area. Disputes are resolved by open and honest communication.
## Signature
This document has been collectively crafted and approved by the current InvokeAI team members, as of 28 Nov 2022: **lstein** (Lincoln Stein), **blessedcoolant**, **hipsterusername** (Kent Keirsey), **Kyle0654** (Kyle Schouviller), **damian0815**, **mauwii** (Matthias Wild), **Netsvetaev** (Artur Netsvetaev), **psychedelicious**, **tildebyte**, and **keturn**. Although individuals within the group may hold differing views on particular details and/or their implications, we are all in agreement about its fundamental statements, as well as their significance and importance to this project moving forward.

View File

@@ -65,11 +65,14 @@ requests. Be sure to use the provided templates. They will help aid diagnose iss
### Installation
This fork is supported across Linux, Windows and Macintosh. Linux
users can use either an Nvidia-based card (with CUDA support) or an
AMD card (using the ROCm driver). For full installation and upgrade
instructions, please see:
[InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/)
This fork is supported across multiple platforms. You can find individual installation instructions
below.
- #### [Linux](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_LINUX/)
- #### [Windows](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_WINDOWS/)
- #### [Macintosh](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_MAC/)
### Hardware Requirements
@@ -130,6 +133,19 @@ you can try starting `invoke.py` with the `--precision=float32` flag:
### Latest Changes
### v2.1.0 major changes <small>(2 November 2022)</small>
- [Inpainting](https://invoke-ai.github.io/InvokeAI/features/INPAINTING/) support in the WebGUI
- Greatly improved navigation and user experience in the [WebGUI](https://invoke-ai.github.io/InvokeAI/features/WEB/)
- The prompt syntax has been enhanced with [prompt weighting, cross-attention and prompt merging](https://invoke-ai.github.io/InvokeAI/features/PROMPTS/).
- You can now load [multiple models and switch among them quickly](https://docs.google.com/presentation/d/1WywGA1rny7bpFh7CLSdTr4nNpVKdlUeT0Bj0jCsILyU/edit?usp=sharing) without leaving the CLI.
- The installation process (via `scripts/preload_models.py`) now lets you select among several popular [Stable Diffusion models](https://invoke-ai.github.io/InvokeAI/installation/INSTALLING_MODELS/) and downloads and installs them on your behalf. Among other models, this script will install the current Stable Diffusion 1.5 model as well as a StabilityAI variable autoencoder (VAE) which improves face generation.
- Tired of struggling with photoeditors to get the masked region of for inpainting just right? Let the AI make the mask for you using [text masking](https://docs.google.com/presentation/d/1pWoY510hCVjz0M6X9CBbTznZgW2W5BYNKrmZm7B45q8/edit#slide=id.p). This feature allows you to specify the part of the image to paint over using just English-language phrases.
- Tired of seeing the head of your subjects cropped off? Uncrop them in the CLI with the [outcrop feature](https://invoke-ai.github.io/InvokeAI/features/OUTPAINTING/#outcrop).
- Tired of seeing your subject's bodies duplicated or mangled when generating larger-dimension images? Check out the `--hires` option in the CLI, or select the corresponding toggle in the WebGUI.
- We now support textual inversion and fine-tune .bin styles and subjects from the Hugging Face archive of [SD Concepts](https://huggingface.co/sd-concepts-library). Load the .bin file using the `--embedding_path` option. (The next version will support merging and loading of multiple simultaneous models).
<a href="https://invoke-ai.github.io/InvokeAI/CHANGELOG/>Complete Changelog</a>
- 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
@@ -172,22 +188,15 @@ problems and other issues.
# 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. To join, just raise your hand on the InvokeAI
Discord server or discussion board.
If you are unfamiliar with how
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
[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.
We hope you enjoy using our software as much as we enjoy creating it,
and we hope that some of those of you who are reading this will elect
to become part of our community.
Welcome to InvokeAI!
### Contributors
This fork is a combined effort of various people from across the world.

View File

File diff suppressed because it is too large Load Diff

View File

@@ -1,117 +0,0 @@
from PIL import Image, ImageChops
from PIL.Image import Image as ImageType
from typing import Union, Literal
# https://stackoverflow.com/questions/43864101/python-pil-check-if-image-is-transparent
def check_for_any_transparency(img: Union[ImageType, str]) -> bool:
if type(img) is str:
img = Image.open(str)
if img.info.get("transparency", None) is not None:
return True
if img.mode == "P":
transparent = img.info.get("transparency", -1)
for _, index in img.getcolors():
if index == transparent:
return True
elif img.mode == "RGBA":
extrema = img.getextrema()
if extrema[3][0] < 255:
return True
return False
def get_canvas_generation_mode(
init_img: Union[ImageType, str], init_mask: Union[ImageType, str]
) -> Literal["txt2img", "outpainting", "inpainting", "img2img",]:
if type(init_img) is str:
init_img = Image.open(init_img)
if type(init_mask) is str:
init_mask = Image.open(init_mask)
init_img = init_img.convert("RGBA")
# Get alpha from init_img
init_img_alpha = init_img.split()[-1]
init_img_alpha_mask = init_img_alpha.convert("L")
init_img_has_transparency = check_for_any_transparency(init_img)
if init_img_has_transparency:
init_img_is_fully_transparent = (
True if init_img_alpha_mask.getbbox() is None else False
)
"""
Mask images are white in areas where no change should be made, black where changes
should be made.
"""
# Fit the mask to init_img's size and convert it to greyscale
init_mask = init_mask.resize(init_img.size).convert("L")
"""
PIL.Image.getbbox() returns the bounding box of non-zero areas of the image, so we first
invert the mask image so that masked areas are white and other areas black == zero.
getbbox() now tells us if the are any masked areas.
"""
init_mask_bbox = ImageChops.invert(init_mask).getbbox()
init_mask_exists = False if init_mask_bbox is None else True
if init_img_has_transparency:
if init_img_is_fully_transparent:
return "txt2img"
else:
return "outpainting"
else:
if init_mask_exists:
return "inpainting"
else:
return "img2img"
def main():
# Testing
init_img_opaque = "test_images/init-img_opaque.png"
init_img_partial_transparency = "test_images/init-img_partial_transparency.png"
init_img_full_transparency = "test_images/init-img_full_transparency.png"
init_mask_no_mask = "test_images/init-mask_no_mask.png"
init_mask_has_mask = "test_images/init-mask_has_mask.png"
print(
"OPAQUE IMAGE, NO MASK, expect img2img, got ",
get_canvas_generation_mode(init_img_opaque, init_mask_no_mask),
)
print(
"IMAGE WITH TRANSPARENCY, NO MASK, expect outpainting, got ",
get_canvas_generation_mode(
init_img_partial_transparency, init_mask_no_mask
),
)
print(
"FULLY TRANSPARENT IMAGE NO MASK, expect txt2img, got ",
get_canvas_generation_mode(init_img_full_transparency, init_mask_no_mask),
)
print(
"OPAQUE IMAGE, WITH MASK, expect inpainting, got ",
get_canvas_generation_mode(init_img_opaque, init_mask_has_mask),
)
print(
"IMAGE WITH TRANSPARENCY, WITH MASK, expect outpainting, got ",
get_canvas_generation_mode(
init_img_partial_transparency, init_mask_has_mask
),
)
print(
"FULLY TRANSPARENT IMAGE WITH MASK, expect txt2img, got ",
get_canvas_generation_mode(init_img_full_transparency, init_mask_has_mask),
)
if __name__ == "__main__":
main()

Binary file not shown.

Before

Width:  |  Height:  |  Size: 2.7 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 292 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 164 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 9.5 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 3.4 KiB

View File

@@ -1,80 +0,0 @@
stable-diffusion-1.5:
description: The newest Stable Diffusion version 1.5 weight file (4.27 GB)
repo_id: runwayml/stable-diffusion-v1-5
config: v1-inference.yaml
file: v1-5-pruned-emaonly.ckpt
recommended: true
width: 512
height: 512
inpainting-1.5:
description: RunwayML SD 1.5 model optimized for inpainting (4.27 GB)
repo_id: runwayml/stable-diffusion-inpainting
config: v1-inpainting-inference.yaml
file: sd-v1-5-inpainting.ckpt
recommended: True
width: 512
height: 512
ft-mse-improved-autoencoder-840000:
description: StabilityAI improved autoencoder fine-tuned for human faces (recommended; 335 MB)
repo_id: stabilityai/sd-vae-ft-mse-original
config: VAE/default
file: vae-ft-mse-840000-ema-pruned.ckpt
recommended: True
width: 512
height: 512
stable-diffusion-1.4:
description: The original Stable Diffusion version 1.4 weight file (4.27 GB)
repo_id: CompVis/stable-diffusion-v-1-4-original
config: v1-inference.yaml
file: sd-v1-4.ckpt
recommended: False
width: 512
height: 512
waifu-diffusion-1.3:
description: Stable Diffusion 1.4 fine tuned on anime-styled images (4.27)
repo_id: hakurei/waifu-diffusion-v1-3
config: v1-inference.yaml
file: model-epoch09-float32.ckpt
recommended: False
width: 512
height: 512
trinart-2.0:
description: An SD model finetuned with ~40,000 assorted high resolution manga/anime-style pictures (2.13 GB)
repo_id: naclbit/trinart_stable_diffusion_v2
config: v1-inference.yaml
file: trinart2_step95000.ckpt
recommended: False
width: 512
height: 512
trinart_characters-1.0:
description: An SD model finetuned with 19.2M anime/manga style images (2.13 GB)
repo_id: naclbit/trinart_characters_19.2m_stable_diffusion_v1
config: v1-inference.yaml
file: trinart_characters_it4_v1.ckpt
recommended: False
width: 512
height: 512
trinart_vae:
description: Custom autoencoder for trinart_characters
repo_id: naclbit/trinart_characters_19.2m_stable_diffusion_v1
config: VAE/trinart
file: autoencoder_fix_kl-f8-trinart_characters.ckpt
recommended: False
width: 512
height: 512
papercut-1.0:
description: SD 1.5 fine-tuned for papercut art (use "PaperCut" in your prompts) (2.13 GB)
repo_id: Fictiverse/Stable_Diffusion_PaperCut_Model
config: v1-inference.yaml
file: PaperCut_v1.ckpt
recommended: False
width: 512
height: 512
voxel_art-1.0:
description: Stable Diffusion trained on voxel art (use "VoxelArt" in your prompts) (4.27 GB)
repo_id: Fictiverse/Stable_Diffusion_VoxelArt_Model
config: v1-inference.yaml
file: VoxelArt_v1.ckpt
recommended: False
width: 512
height: 512

View File

@@ -7,8 +7,8 @@
# 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
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

View File

@@ -1,803 +0,0 @@
sd-concepts-library/001glitch-core
sd-concepts-library/2814-roth
sd-concepts-library/3d-female-cyborgs
sd-concepts-library/4tnght
sd-concepts-library/80s-anime-ai
sd-concepts-library/80s-anime-ai-being
sd-concepts-library/852style-girl
sd-concepts-library/8bit
sd-concepts-library/8sconception
sd-concepts-library/Aflac-duck
sd-concepts-library/Akitsuki
sd-concepts-library/Atako
sd-concepts-library/Exodus-Styling
sd-concepts-library/RINGAO
sd-concepts-library/a-female-hero-from-the-legend-of-mir
sd-concepts-library/a-hat-kid
sd-concepts-library/a-tale-of-two-empires
sd-concepts-library/aadhav-face
sd-concepts-library/aavegotchi
sd-concepts-library/abby-face
sd-concepts-library/abstract-concepts
sd-concepts-library/accurate-angel
sd-concepts-library/agm-style-nao
sd-concepts-library/aj-fosik
sd-concepts-library/alberto-mielgo
sd-concepts-library/alex-portugal
sd-concepts-library/alex-thumbnail-object-2000-steps
sd-concepts-library/aleyna-tilki
sd-concepts-library/alf
sd-concepts-library/alicebeta
sd-concepts-library/alien-avatar
sd-concepts-library/alisa
sd-concepts-library/all-rings-albuns
sd-concepts-library/altvent
sd-concepts-library/altyn-helmet
sd-concepts-library/amine
sd-concepts-library/amogus
sd-concepts-library/anders-zorn
sd-concepts-library/angus-mcbride-style
sd-concepts-library/animalve3-1500seq
sd-concepts-library/anime-background-style
sd-concepts-library/anime-background-style-v2
sd-concepts-library/anime-boy
sd-concepts-library/anime-girl
sd-concepts-library/anyXtronXredshift
sd-concepts-library/anya-forger
sd-concepts-library/apex-wingman
sd-concepts-library/apulian-rooster-v0-1
sd-concepts-library/arcane-face
sd-concepts-library/arcane-style-jv
sd-concepts-library/arcimboldo-style
sd-concepts-library/armando-reveron-style
sd-concepts-library/armor-concept
sd-concepts-library/arq-render
sd-concepts-library/art-brut
sd-concepts-library/arthur1
sd-concepts-library/artist-yukiko-kanagai
sd-concepts-library/arwijn
sd-concepts-library/ashiok
sd-concepts-library/at-wolf-boy-object
sd-concepts-library/atm-ant
sd-concepts-library/atm-ant-2
sd-concepts-library/axe-tattoo
sd-concepts-library/ayush-spider-spr
sd-concepts-library/azura-from-vibrant-venture
sd-concepts-library/ba-shiroko
sd-concepts-library/babau
sd-concepts-library/babs-bunny
sd-concepts-library/babushork
sd-concepts-library/backrooms
sd-concepts-library/bad_Hub_Hugh
sd-concepts-library/bada-club
sd-concepts-library/baldi
sd-concepts-library/baluchitherian
sd-concepts-library/bamse
sd-concepts-library/bamse-og-kylling
sd-concepts-library/bee
sd-concepts-library/beholder
sd-concepts-library/beldam
sd-concepts-library/belen
sd-concepts-library/bella-goth
sd-concepts-library/belle-delphine
sd-concepts-library/bert-muppet
sd-concepts-library/better-collage3
sd-concepts-library/between2-mt-fade
sd-concepts-library/birb-style
sd-concepts-library/black-and-white-design
sd-concepts-library/black-waifu
sd-concepts-library/bloo
sd-concepts-library/blue-haired-boy
sd-concepts-library/blue-zombie
sd-concepts-library/blue-zombiee
sd-concepts-library/bluebey
sd-concepts-library/bluebey-2
sd-concepts-library/bobs-burgers
sd-concepts-library/boissonnard
sd-concepts-library/bonzi-monkey
sd-concepts-library/borderlands
sd-concepts-library/bored-ape-textual-inversion
sd-concepts-library/boris-anderson
sd-concepts-library/bozo-22
sd-concepts-library/breakcore
sd-concepts-library/brittney-williams-art
sd-concepts-library/bruma
sd-concepts-library/brunnya
sd-concepts-library/buddha-statue
sd-concepts-library/bullvbear
sd-concepts-library/button-eyes
sd-concepts-library/canadian-goose
sd-concepts-library/canary-cap
sd-concepts-library/cancer_style
sd-concepts-library/captain-haddock
sd-concepts-library/captainkirb
sd-concepts-library/car-toy-rk
sd-concepts-library/carasibana
sd-concepts-library/carlitos-el-mago
sd-concepts-library/carrascharacter
sd-concepts-library/cartoona-animals
sd-concepts-library/cat-toy
sd-concepts-library/centaur
sd-concepts-library/cgdonny1
sd-concepts-library/cham
sd-concepts-library/chandra-nalaar
sd-concepts-library/char-con
sd-concepts-library/character-pingu
sd-concepts-library/cheburashka
sd-concepts-library/chen-1
sd-concepts-library/child-zombie
sd-concepts-library/chillpill
sd-concepts-library/chonkfrog
sd-concepts-library/chop
sd-concepts-library/christo-person
sd-concepts-library/chuck-walton
sd-concepts-library/chucky
sd-concepts-library/chungus-poodl-pet
sd-concepts-library/cindlop
sd-concepts-library/collage-cutouts
sd-concepts-library/collage14
sd-concepts-library/collage3
sd-concepts-library/collage3-hubcity
sd-concepts-library/cologne
sd-concepts-library/color-page
sd-concepts-library/colossus
sd-concepts-library/command-and-conquer-remastered-cameos
sd-concepts-library/concept-art
sd-concepts-library/conner-fawcett-style
sd-concepts-library/conway-pirate
sd-concepts-library/coop-himmelblau
sd-concepts-library/coraline
sd-concepts-library/cornell-box
sd-concepts-library/cortana
sd-concepts-library/covid-19-rapid-test
sd-concepts-library/cow-uwu
sd-concepts-library/cowboy
sd-concepts-library/crazy-1
sd-concepts-library/crazy-2
sd-concepts-library/crb-portraits
sd-concepts-library/crb-surrealz
sd-concepts-library/crbart
sd-concepts-library/crested-gecko
sd-concepts-library/crinos-form-garou
sd-concepts-library/cry-baby-style
sd-concepts-library/crybaby-style-2-0
sd-concepts-library/csgo-awp-object
sd-concepts-library/csgo-awp-texture-map
sd-concepts-library/cubex
sd-concepts-library/cumbia-peruana
sd-concepts-library/cute-bear
sd-concepts-library/cute-cat
sd-concepts-library/cute-game-style
sd-concepts-library/cyberpunk-lucy
sd-concepts-library/dabotap
sd-concepts-library/dan-mumford
sd-concepts-library/dan-seagrave-art-style
sd-concepts-library/dark-penguin-pinguinanimations
sd-concepts-library/darkpenguinanimatronic
sd-concepts-library/darkplane
sd-concepts-library/david-firth-artstyle
sd-concepts-library/david-martinez-cyberpunk
sd-concepts-library/david-martinez-edgerunners
sd-concepts-library/david-moreno-architecture
sd-concepts-library/daycare-attendant-sun-fnaf
sd-concepts-library/ddattender
sd-concepts-library/degods
sd-concepts-library/degodsheavy
sd-concepts-library/depthmap
sd-concepts-library/depthmap-style
sd-concepts-library/design
sd-concepts-library/detectivedinosaur1
sd-concepts-library/diaosu-toy
sd-concepts-library/dicoo
sd-concepts-library/dicoo2
sd-concepts-library/dishonored-portrait-styles
sd-concepts-library/disquieting-muses
sd-concepts-library/ditko
sd-concepts-library/dlooak
sd-concepts-library/doc
sd-concepts-library/doener-red-line-art
sd-concepts-library/dog
sd-concepts-library/dog-django
sd-concepts-library/doge-pound
sd-concepts-library/dong-ho
sd-concepts-library/dong-ho2
sd-concepts-library/doose-s-realistic-art-style
sd-concepts-library/dq10-anrushia
sd-concepts-library/dr-livesey
sd-concepts-library/dr-strange
sd-concepts-library/dragonborn
sd-concepts-library/dreamcore
sd-concepts-library/dreamy-painting
sd-concepts-library/drive-scorpion-jacket
sd-concepts-library/dsmuses
sd-concepts-library/dtv-pkmn
sd-concepts-library/dullboy-caricature
sd-concepts-library/duranduran
sd-concepts-library/durer-style
sd-concepts-library/dyoudim-style
sd-concepts-library/early-mishima-kurone
sd-concepts-library/eastward
sd-concepts-library/eddie
sd-concepts-library/edgerunners-style
sd-concepts-library/edgerunners-style-v2
sd-concepts-library/el-salvador-style-style
sd-concepts-library/elegant-flower
sd-concepts-library/elspeth-tirel
sd-concepts-library/eru-chitanda-casual
sd-concepts-library/erwin-olaf-style
sd-concepts-library/ettblackteapot
sd-concepts-library/explosions-cat
sd-concepts-library/eye-of-agamotto
sd-concepts-library/f-22
sd-concepts-library/facadeplace
sd-concepts-library/fairy-tale-painting-style
sd-concepts-library/fairytale
sd-concepts-library/fang-yuan-001
sd-concepts-library/faraon-love-shady
sd-concepts-library/fasina
sd-concepts-library/felps
sd-concepts-library/female-kpop-singer
sd-concepts-library/fergal-cat
sd-concepts-library/filename-2
sd-concepts-library/fileteado-porteno
sd-concepts-library/final-fantasy-logo
sd-concepts-library/fireworks-over-water
sd-concepts-library/fish
sd-concepts-library/flag-ussr
sd-concepts-library/flatic
sd-concepts-library/floral
sd-concepts-library/fluid-acrylic-jellyfish-creatures-style-of-carl-ingram-art
sd-concepts-library/fnf-boyfriend
sd-concepts-library/fold-structure
sd-concepts-library/fox-purple
sd-concepts-library/fractal
sd-concepts-library/fractal-flame
sd-concepts-library/fractal-temple-style
sd-concepts-library/frank-frazetta
sd-concepts-library/franz-unterberger
sd-concepts-library/freddy-fazbear
sd-concepts-library/freefonix-style
sd-concepts-library/furrpopasthetic
sd-concepts-library/fursona
sd-concepts-library/fzk
sd-concepts-library/galaxy-explorer
sd-concepts-library/ganyu-genshin-impact
sd-concepts-library/garcon-the-cat
sd-concepts-library/garfield-pizza-plush
sd-concepts-library/garfield-pizza-plush-v2
sd-concepts-library/gba-fe-class-cards
sd-concepts-library/gba-pokemon-sprites
sd-concepts-library/geggin
sd-concepts-library/ggplot2
sd-concepts-library/ghost-style
sd-concepts-library/ghostproject-men
sd-concepts-library/gibasachan-v0
sd-concepts-library/gim
sd-concepts-library/gio
sd-concepts-library/giygas
sd-concepts-library/glass-pipe
sd-concepts-library/glass-prism-cube
sd-concepts-library/glow-forest
sd-concepts-library/goku
sd-concepts-library/gram-tops
sd-concepts-library/green-blue-shanshui
sd-concepts-library/green-tent
sd-concepts-library/grifter
sd-concepts-library/grisstyle
sd-concepts-library/grit-toy
sd-concepts-library/gt-color-paint-2
sd-concepts-library/gta5-artwork
sd-concepts-library/guttestreker
sd-concepts-library/gymnastics-leotard-v2
sd-concepts-library/half-life-2-dog
sd-concepts-library/handstand
sd-concepts-library/hanfu-anime-style
sd-concepts-library/happy-chaos
sd-concepts-library/happy-person12345
sd-concepts-library/happy-person12345-assets
sd-concepts-library/harley-quinn
sd-concepts-library/harmless-ai-1
sd-concepts-library/harmless-ai-house-style-1
sd-concepts-library/hd-emoji
sd-concepts-library/heather
sd-concepts-library/henjo-techno-show
sd-concepts-library/herge-style
sd-concepts-library/hiten-style-nao
sd-concepts-library/hitokomoru-style-nao
sd-concepts-library/hiyuki-chan
sd-concepts-library/hk-bamboo
sd-concepts-library/hk-betweenislands
sd-concepts-library/hk-bicycle
sd-concepts-library/hk-blackandwhite
sd-concepts-library/hk-breakfast
sd-concepts-library/hk-buses
sd-concepts-library/hk-clouds
sd-concepts-library/hk-goldbuddha
sd-concepts-library/hk-goldenlantern
sd-concepts-library/hk-hkisland
sd-concepts-library/hk-leaves
sd-concepts-library/hk-market
sd-concepts-library/hk-oldcamera
sd-concepts-library/hk-opencamera
sd-concepts-library/hk-peach
sd-concepts-library/hk-phonevax
sd-concepts-library/hk-streetpeople
sd-concepts-library/hk-vintage
sd-concepts-library/hoi4
sd-concepts-library/hoi4-leaders
sd-concepts-library/homestuck-sprite
sd-concepts-library/homestuck-troll
sd-concepts-library/hours-sentry-fade
sd-concepts-library/hours-style
sd-concepts-library/hrgiger-drmacabre
sd-concepts-library/huang-guang-jian
sd-concepts-library/huatli
sd-concepts-library/huayecai820-greyscale
sd-concepts-library/hub-city
sd-concepts-library/hubris-oshri
sd-concepts-library/huckleberry
sd-concepts-library/hydrasuit
sd-concepts-library/i-love-chaos
sd-concepts-library/ibere-thenorio
sd-concepts-library/ic0n
sd-concepts-library/ie-gravestone
sd-concepts-library/ikea-fabler
sd-concepts-library/illustration-style
sd-concepts-library/ilo-kunst
sd-concepts-library/ilya-shkipin
sd-concepts-library/im-poppy
sd-concepts-library/ina-art
sd-concepts-library/indian-watercolor-portraits
sd-concepts-library/indiana
sd-concepts-library/ingmar-bergman
sd-concepts-library/insidewhale
sd-concepts-library/interchanges
sd-concepts-library/inuyama-muneto-style-nao
sd-concepts-library/irasutoya
sd-concepts-library/iridescent-illustration-style
sd-concepts-library/iridescent-photo-style
sd-concepts-library/isabell-schulte-pv-pvii-3000steps
sd-concepts-library/isabell-schulte-pviii-1-image-style
sd-concepts-library/isabell-schulte-pviii-1024px-1500-steps-style
sd-concepts-library/isabell-schulte-pviii-12tiles-3000steps-style
sd-concepts-library/isabell-schulte-pviii-4-tiles-1-lr-3000-steps-style
sd-concepts-library/isabell-schulte-pviii-4-tiles-3-lr-5000-steps-style
sd-concepts-library/isabell-schulte-pviii-4tiles-500steps
sd-concepts-library/isabell-schulte-pviii-4tiles-6000steps
sd-concepts-library/isabell-schulte-pviii-style
sd-concepts-library/isometric-tile-test
sd-concepts-library/jacqueline-the-unicorn
sd-concepts-library/james-web-space-telescope
sd-concepts-library/jamie-hewlett-style
sd-concepts-library/jamiels
sd-concepts-library/jang-sung-rak-style
sd-concepts-library/jetsetdreamcastcovers
sd-concepts-library/jin-kisaragi
sd-concepts-library/jinjoon-lee-they
sd-concepts-library/jm-bergling-monogram
sd-concepts-library/joe-mad
sd-concepts-library/joe-whiteford-art-style
sd-concepts-library/joemad
sd-concepts-library/john-blanche
sd-concepts-library/johnny-silverhand
sd-concepts-library/jojo-bizzare-adventure-manga-lineart
sd-concepts-library/jos-de-kat
sd-concepts-library/junji-ito-artstyle
sd-concepts-library/kaleido
sd-concepts-library/kaneoya-sachiko
sd-concepts-library/kanovt
sd-concepts-library/kanv1
sd-concepts-library/karan-gloomy
sd-concepts-library/karl-s-lzx-1
sd-concepts-library/kasumin
sd-concepts-library/kawaii-colors
sd-concepts-library/kawaii-girl-plus-object
sd-concepts-library/kawaii-girl-plus-style
sd-concepts-library/kawaii-girl-plus-style-v1-1
sd-concepts-library/kay
sd-concepts-library/kaya-ghost-assasin
sd-concepts-library/ki
sd-concepts-library/kinda-sus
sd-concepts-library/kings-quest-agd
sd-concepts-library/kiora
sd-concepts-library/kira-sensei
sd-concepts-library/kirby
sd-concepts-library/klance
sd-concepts-library/kodakvision500t
sd-concepts-library/kogatan-shiny
sd-concepts-library/kogecha
sd-concepts-library/kojima-ayami
sd-concepts-library/koko-dog
sd-concepts-library/kuvshinov
sd-concepts-library/kysa-v-style
sd-concepts-library/laala-character
sd-concepts-library/larrette
sd-concepts-library/lavko
sd-concepts-library/lazytown-stephanie
sd-concepts-library/ldr
sd-concepts-library/ldrs
sd-concepts-library/led-toy
sd-concepts-library/lego-astronaut
sd-concepts-library/leica
sd-concepts-library/leif-jones
sd-concepts-library/lex
sd-concepts-library/liliana
sd-concepts-library/liliana-vess
sd-concepts-library/liminal-spaces-2-0
sd-concepts-library/liminalspaces
sd-concepts-library/line-art
sd-concepts-library/line-style
sd-concepts-library/linnopoke
sd-concepts-library/liquid-light
sd-concepts-library/liqwid-aquafarmer
sd-concepts-library/lizardman
sd-concepts-library/loab-character
sd-concepts-library/loab-style
sd-concepts-library/lofa
sd-concepts-library/logo-with-face-on-shield
sd-concepts-library/lolo
sd-concepts-library/looney-anime
sd-concepts-library/lost-rapper
sd-concepts-library/lphr-style
sd-concepts-library/lucario
sd-concepts-library/lucky-luke
sd-concepts-library/lugal-ki-en
sd-concepts-library/luinv2
sd-concepts-library/lula-13
sd-concepts-library/lumio
sd-concepts-library/lxj-o4
sd-concepts-library/m-geo
sd-concepts-library/m-geoo
sd-concepts-library/madhubani-art
sd-concepts-library/mafalda-character
sd-concepts-library/magic-pengel
sd-concepts-library/malika-favre-art-style
sd-concepts-library/manga-style
sd-concepts-library/marbling-art
sd-concepts-library/margo
sd-concepts-library/marty
sd-concepts-library/marty6
sd-concepts-library/mass
sd-concepts-library/masyanya
sd-concepts-library/masyunya
sd-concepts-library/mate
sd-concepts-library/matthew-stone
sd-concepts-library/mattvidpro
sd-concepts-library/maurice-quentin-de-la-tour-style
sd-concepts-library/maus
sd-concepts-library/max-foley
sd-concepts-library/mayor-richard-irvin
sd-concepts-library/mechasoulall
sd-concepts-library/medazzaland
sd-concepts-library/memnarch-mtg
sd-concepts-library/metagabe
sd-concepts-library/meyoco
sd-concepts-library/meze-audio-elite-headphones
sd-concepts-library/midjourney-style
sd-concepts-library/mikako-method
sd-concepts-library/mikako-methodi2i
sd-concepts-library/miko-3-robot
sd-concepts-library/milady
sd-concepts-library/mildemelwe-style
sd-concepts-library/million-live-akane-15k
sd-concepts-library/million-live-akane-3k
sd-concepts-library/million-live-akane-shifuku-3k
sd-concepts-library/million-live-spade-q-object-3k
sd-concepts-library/million-live-spade-q-style-3k
sd-concepts-library/minecraft-concept-art
sd-concepts-library/mishima-kurone
sd-concepts-library/mizkif
sd-concepts-library/moeb-style
sd-concepts-library/moebius
sd-concepts-library/mokoko
sd-concepts-library/mokoko-seed
sd-concepts-library/monster-girl
sd-concepts-library/monster-toy
sd-concepts-library/monte-novo
sd-concepts-library/moo-moo
sd-concepts-library/morino-hon-style
sd-concepts-library/moxxi
sd-concepts-library/msg
sd-concepts-library/mtg-card
sd-concepts-library/mtl-longsky
sd-concepts-library/mu-sadr
sd-concepts-library/munch-leaks-style
sd-concepts-library/museum-by-coop-himmelblau
sd-concepts-library/muxoyara
sd-concepts-library/my-hero-academia-style
sd-concepts-library/my-mug
sd-concepts-library/mycat
sd-concepts-library/mystical-nature
sd-concepts-library/naf
sd-concepts-library/nahiri
sd-concepts-library/namine-ritsu
sd-concepts-library/naoki-saito
sd-concepts-library/nard-style
sd-concepts-library/naruto
sd-concepts-library/natasha-johnston
sd-concepts-library/nathan-wyatt
sd-concepts-library/naval-portrait
sd-concepts-library/nazuna
sd-concepts-library/nebula
sd-concepts-library/ned-flanders
sd-concepts-library/neon-pastel
sd-concepts-library/new-priests
sd-concepts-library/nic-papercuts
sd-concepts-library/nikodim
sd-concepts-library/nissa-revane
sd-concepts-library/nixeu
sd-concepts-library/noggles
sd-concepts-library/nomad
sd-concepts-library/nouns-glasses
sd-concepts-library/obama-based-on-xi
sd-concepts-library/obama-self-2
sd-concepts-library/og-mox-style
sd-concepts-library/ohisashiburi-style
sd-concepts-library/oleg-kuvaev
sd-concepts-library/olli-olli
sd-concepts-library/on-kawara
sd-concepts-library/one-line-drawing
sd-concepts-library/onepunchman
sd-concepts-library/onzpo
sd-concepts-library/orangejacket
sd-concepts-library/ori
sd-concepts-library/ori-toor
sd-concepts-library/orientalist-art
sd-concepts-library/osaka-jyo
sd-concepts-library/osaka-jyo2
sd-concepts-library/osrsmini2
sd-concepts-library/osrstiny
sd-concepts-library/other-mother
sd-concepts-library/ouroboros
sd-concepts-library/outfit-items
sd-concepts-library/overprettified
sd-concepts-library/owl-house
sd-concepts-library/painted-by-silver-of-999
sd-concepts-library/painted-by-silver-of-999-2
sd-concepts-library/painted-student
sd-concepts-library/painting
sd-concepts-library/pantone-milk
sd-concepts-library/paolo-bonolis
sd-concepts-library/party-girl
sd-concepts-library/pascalsibertin
sd-concepts-library/pastelartstyle
sd-concepts-library/paul-noir
sd-concepts-library/pen-ink-portraits-bennorthen
sd-concepts-library/phan
sd-concepts-library/phan-s-collage
sd-concepts-library/phc
sd-concepts-library/phoenix-01
sd-concepts-library/pineda-david
sd-concepts-library/pink-beast-pastelae-style
sd-concepts-library/pintu
sd-concepts-library/pion-by-august-semionov
sd-concepts-library/piotr-jablonski
sd-concepts-library/pixel-mania
sd-concepts-library/pixel-toy
sd-concepts-library/pjablonski-style
sd-concepts-library/plant-style
sd-concepts-library/plen-ki-mun
sd-concepts-library/pokemon-conquest-sprites
sd-concepts-library/pool-test
sd-concepts-library/poolrooms
sd-concepts-library/poring-ragnarok-online
sd-concepts-library/poutine-dish
sd-concepts-library/princess-knight-art
sd-concepts-library/progress-chip
sd-concepts-library/puerquis-toy
sd-concepts-library/purplefishli
sd-concepts-library/pyramidheadcosplay
sd-concepts-library/qpt-atrium
sd-concepts-library/quiesel
sd-concepts-library/r-crumb-style
sd-concepts-library/rahkshi-bionicle
sd-concepts-library/raichu
sd-concepts-library/rail-scene
sd-concepts-library/rail-scene-style
sd-concepts-library/ralph-mcquarrie
sd-concepts-library/ransom
sd-concepts-library/rayne-weynolds
sd-concepts-library/rcrumb-portraits-style
sd-concepts-library/rd-chaos
sd-concepts-library/rd-paintings
sd-concepts-library/red-glasses
sd-concepts-library/reeducation-camp
sd-concepts-library/reksio-dog
sd-concepts-library/rektguy
sd-concepts-library/remert
sd-concepts-library/renalla
sd-concepts-library/repeat
sd-concepts-library/retro-girl
sd-concepts-library/retro-mecha-rangers
sd-concepts-library/retropixelart-pinguin
sd-concepts-library/rex-deno
sd-concepts-library/rhizomuse-machine-bionic-sculpture
sd-concepts-library/ricar
sd-concepts-library/rickyart
sd-concepts-library/rico-face
sd-concepts-library/riker-doll
sd-concepts-library/rikiart
sd-concepts-library/rikiboy-art
sd-concepts-library/rilakkuma
sd-concepts-library/rishusei-style
sd-concepts-library/rj-palmer
sd-concepts-library/rl-pkmn-test
sd-concepts-library/road-to-ruin
sd-concepts-library/robertnava
sd-concepts-library/roblox-avatar
sd-concepts-library/roy-lichtenstein
sd-concepts-library/ruan-jia
sd-concepts-library/russian
sd-concepts-library/s1m-naoto-ohshima
sd-concepts-library/saheeli-rai
sd-concepts-library/sakimi-style
sd-concepts-library/salmonid
sd-concepts-library/sam-yang
sd-concepts-library/sanguo-guanyu
sd-concepts-library/sas-style
sd-concepts-library/scarlet-witch
sd-concepts-library/schloss-mosigkau
sd-concepts-library/scrap-style
sd-concepts-library/scratch-project
sd-concepts-library/sculptural-style
sd-concepts-library/sd-concepts-library-uma-meme
sd-concepts-library/seamless-ground
sd-concepts-library/selezneva-alisa
sd-concepts-library/sem-mac2n
sd-concepts-library/senneca
sd-concepts-library/seraphimmoonshadow-art
sd-concepts-library/sewerslvt
sd-concepts-library/she-hulk-law-art
sd-concepts-library/she-mask
sd-concepts-library/sherhook-painting
sd-concepts-library/sherhook-painting-v2
sd-concepts-library/shev-linocut
sd-concepts-library/shigure-ui-style
sd-concepts-library/shiny-polyman
sd-concepts-library/shrunken-head
sd-concepts-library/shu-doll
sd-concepts-library/shvoren-style
sd-concepts-library/sims-2-portrait
sd-concepts-library/singsing
sd-concepts-library/singsing-doll
sd-concepts-library/sintez-ico
sd-concepts-library/skyfalls
sd-concepts-library/slm
sd-concepts-library/smarties
sd-concepts-library/smiling-friend-style
sd-concepts-library/smooth-pencils
sd-concepts-library/smurf-style
sd-concepts-library/smw-map
sd-concepts-library/society-finch
sd-concepts-library/sorami-style
sd-concepts-library/spider-gwen
sd-concepts-library/spritual-monsters
sd-concepts-library/stable-diffusion-conceptualizer
sd-concepts-library/star-tours-posters
sd-concepts-library/stardew-valley-pixel-art
sd-concepts-library/starhavenmachinegods
sd-concepts-library/sterling-archer
sd-concepts-library/stretch-re1-robot
sd-concepts-library/stuffed-penguin-toy
sd-concepts-library/style-of-marc-allante
sd-concepts-library/summie-style
sd-concepts-library/sunfish
sd-concepts-library/super-nintendo-cartridge
sd-concepts-library/supitcha-mask
sd-concepts-library/sushi-pixel
sd-concepts-library/swamp-choe-2
sd-concepts-library/t-skrang
sd-concepts-library/takuji-kawano
sd-concepts-library/tamiyo
sd-concepts-library/tangles
sd-concepts-library/tb303
sd-concepts-library/tcirle
sd-concepts-library/teelip-ir-landscape
sd-concepts-library/teferi
sd-concepts-library/tela-lenca
sd-concepts-library/tela-lenca2
sd-concepts-library/terraria-style
sd-concepts-library/tesla-bot
sd-concepts-library/test
sd-concepts-library/test-epson
sd-concepts-library/test2
sd-concepts-library/testing
sd-concepts-library/thalasin
sd-concepts-library/thegeneral
sd-concepts-library/thorneworks
sd-concepts-library/threestooges
sd-concepts-library/thunderdome-cover
sd-concepts-library/thunderdome-covers
sd-concepts-library/ti-junglepunk-v0
sd-concepts-library/tili-concept
sd-concepts-library/titan-robot
sd-concepts-library/tnj
sd-concepts-library/toho-pixel
sd-concepts-library/tomcat
sd-concepts-library/tonal1
sd-concepts-library/tony-diterlizzi-s-planescape-art
sd-concepts-library/towerplace
sd-concepts-library/toy
sd-concepts-library/toy-bonnie-plush
sd-concepts-library/toyota-sera
sd-concepts-library/transmutation-circles
sd-concepts-library/trash-polka-artstyle
sd-concepts-library/travis-bedel
sd-concepts-library/trigger-studio
sd-concepts-library/trust-support
sd-concepts-library/trypophobia
sd-concepts-library/ttte
sd-concepts-library/tubby
sd-concepts-library/tubby-cats
sd-concepts-library/tudisco
sd-concepts-library/turtlepics
sd-concepts-library/type
sd-concepts-library/ugly-sonic
sd-concepts-library/uliana-kudinova
sd-concepts-library/uma
sd-concepts-library/uma-clean-object
sd-concepts-library/uma-meme
sd-concepts-library/uma-meme-style
sd-concepts-library/uma-style-classic
sd-concepts-library/unfinished-building
sd-concepts-library/urivoldemort
sd-concepts-library/uzumaki
sd-concepts-library/valorantstyle
sd-concepts-library/vb-mox
sd-concepts-library/vcr-classique
sd-concepts-library/venice
sd-concepts-library/vespertine
sd-concepts-library/victor-narm
sd-concepts-library/vietstoneking
sd-concepts-library/vivien-reid
sd-concepts-library/vkuoo1
sd-concepts-library/vraska
sd-concepts-library/w3u
sd-concepts-library/walter-wick-photography
sd-concepts-library/warhammer-40k-drawing-style
sd-concepts-library/waterfallshadow
sd-concepts-library/wayne-reynolds-character
sd-concepts-library/wedding
sd-concepts-library/wedding-HandPainted
sd-concepts-library/werebloops
sd-concepts-library/wheatland
sd-concepts-library/wheatland-arknight
sd-concepts-library/wheelchair
sd-concepts-library/wildkat
sd-concepts-library/willy-hd
sd-concepts-library/wire-angels
sd-concepts-library/wish-artist-stile
sd-concepts-library/wlop-style
sd-concepts-library/wojak
sd-concepts-library/wojaks-now
sd-concepts-library/wojaks-now-now-now
sd-concepts-library/xatu
sd-concepts-library/xatu2
sd-concepts-library/xbh
sd-concepts-library/xi
sd-concepts-library/xidiversity
sd-concepts-library/xioboma
sd-concepts-library/xuna
sd-concepts-library/xyz
sd-concepts-library/yb-anime
sd-concepts-library/yerba-mate
sd-concepts-library/yesdelete
sd-concepts-library/yf21
sd-concepts-library/yilanov2
sd-concepts-library/yinit
sd-concepts-library/yoji-shinkawa-style
sd-concepts-library/yolandi-visser
sd-concepts-library/yoshi
sd-concepts-library/youpi2
sd-concepts-library/youtooz-candy
sd-concepts-library/yuji-himukai-style
sd-concepts-library/zaney
sd-concepts-library/zaneypixelz
sd-concepts-library/zdenek-art
sd-concepts-library/zero
sd-concepts-library/zero-bottle
sd-concepts-library/zero-suit-samus
sd-concepts-library/zillertal-can
sd-concepts-library/zizigooloo
sd-concepts-library/zk
sd-concepts-library/zoroark

View File

@@ -30,9 +30,9 @@ model:
target: ldm.modules.embedding_manager.EmbeddingManager
params:
placeholder_strings: ["*"]
initializer_words: ['sculpture']
initializer_words: ['face', 'man', 'photo', 'africanmale']
per_image_tokens: false
num_vectors_per_token: 8
num_vectors_per_token: 1
progressive_words: False
unet_config:

View File

@@ -30,9 +30,9 @@ model:
target: ldm.modules.embedding_manager.EmbeddingManager
params:
placeholder_strings: ["*"]
initializer_words: ['sculpture']
initializer_words: ['face', 'man', 'photo', 'africanmale']
per_image_tokens: false
num_vectors_per_token: 8
num_vectors_per_token: 1
progressive_words: False
unet_config:

View File

@@ -22,7 +22,7 @@ model:
target: ldm.modules.embedding_manager.EmbeddingManager
params:
placeholder_strings: ["*"]
initializer_words: ['sculpture']
initializer_words: ['face', 'man', 'photo', 'africanmale']
per_image_tokens: false
num_vectors_per_token: 6
progressive_words: False

View File

Before

Width:  |  Height:  |  Size: 14 KiB

After

Width:  |  Height:  |  Size: 14 KiB

View File

Before

Width:  |  Height:  |  Size: 466 KiB

After

Width:  |  Height:  |  Size: 466 KiB

View File

Before

Width:  |  Height:  |  Size: 7.4 KiB

After

Width:  |  Height:  |  Size: 7.4 KiB

View File

Before

Width:  |  Height:  |  Size: 539 KiB

After

Width:  |  Height:  |  Size: 539 KiB

View File

Before

Width:  |  Height:  |  Size: 7.6 KiB

After

Width:  |  Height:  |  Size: 7.6 KiB

View File

Before

Width:  |  Height:  |  Size: 450 KiB

After

Width:  |  Height:  |  Size: 450 KiB

View File

Before

Width:  |  Height:  |  Size: 12 KiB

After

Width:  |  Height:  |  Size: 12 KiB

View File

Before

Width:  |  Height:  |  Size: 553 KiB

After

Width:  |  Height:  |  Size: 553 KiB

View File

Before

Width:  |  Height:  |  Size: 12 KiB

After

Width:  |  Height:  |  Size: 12 KiB

View File

Before

Width:  |  Height:  |  Size: 418 KiB

After

Width:  |  Height:  |  Size: 418 KiB

View File

Before

Width:  |  Height:  |  Size: 6.1 KiB

After

Width:  |  Height:  |  Size: 6.1 KiB

View File

Before

Width:  |  Height:  |  Size: 542 KiB

After

Width:  |  Height:  |  Size: 542 KiB

View File

Before

Width:  |  Height:  |  Size: 9.5 KiB

After

Width:  |  Height:  |  Size: 9.5 KiB

View File

Before

Width:  |  Height:  |  Size: 395 KiB

After

Width:  |  Height:  |  Size: 395 KiB

View File

Before

Width:  |  Height:  |  Size: 12 KiB

After

Width:  |  Height:  |  Size: 12 KiB

View File

Before

Width:  |  Height:  |  Size: 465 KiB

After

Width:  |  Height:  |  Size: 465 KiB

View File

Before

Width:  |  Height:  |  Size: 7.8 KiB

After

Width:  |  Height:  |  Size: 7.8 KiB

View File

@@ -1,13 +1,34 @@
FROM ubuntu:22.10
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 ${conda_prefix} \
&& rm -f /miniconda.sh
FROM ubuntu AS invokeai
# use bash
SHELL [ "/bin/bash", "-c" ]
# clean bashrc
RUN echo "" > ~/.bashrc
# Install necesarry packages
RUN apt-get update \
&& apt-get install -y \
--no-install-recommends \
build-essential \
gcc \
git \
libgl1-mesa-glx \
@@ -18,17 +39,36 @@ RUN apt-get update \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/*
# set workdir and copy sources
WORKDIR /invokeai
ARG PIP_REQUIREMENTS=requirements-lin-cuda.txt
COPY . ./environments-and-requirements/${PIP_REQUIREMENTS} ./
# 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
# install requirements and link outputs folder
RUN pip install \
--no-cache-dir \
-r ${PIP_REQUIREMENTS}
# set workdir
WORKDIR /${project_name}
# set Environment, Entrypoint and default CMD
ENV INVOKEAI_ROOT /data
ENTRYPOINT [ "python3", "scripts/invoke.py", "--outdir=/data/outputs" ]
CMD [ "--web", "--host=0.0.0.0" ]
# 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 ${project_name} \
&& python scripts/preload_models.py
# Copy entrypoint and set env
ENV CONDA_PREFIX=${conda_prefix}
ENV PROJECT_NAME=${project_name}
COPY docker-build/entrypoint.sh /
ENTRYPOINT [ "/entrypoint.sh" ]

View File

@@ -1,49 +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
# IMPORTANT: You need to have a token on huggingface.co to be able to download the checkpoints!!!
# configure values by using env when executing build.sh f.e. `env ARCH=aarch64 ./build.sh`
source ./docker-build/env.sh || echo "please run from repository root" || exit 1
source ./docker-build/env.sh \
|| echo "please execute docker-build/build.sh from repository root" \
|| exit 1
pip_requirements=${PIP_REQUIREMENTS:-requirements-lin-cuda.txt}
dockerfile=${INVOKE_DOCKERFILE:-docker-build/Dockerfile}
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 "Dockerfile:\t\t ${dockerfile}"
echo -e "requirements:\t\t ${pip_requirements}"
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="${volumename}" -q)" ]]; then
echo "Volume already exists"
echo
if [[ -z "$(_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="PIP_REQUIREMENTS=${pip_requirements}" \
--file="${dockerfile}" \
--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 run \
--rm \
--platform="$platform" \
--name="$project_name" \
--hostname="$project_name" \
--mount="source=$volumename,target=/data" \
--mount="type=bind,source=$HOME/.huggingface,target=/root/.huggingface" \
--env="HUGGINGFACE_TOKEN=${HUGGINGFACE_TOKEN}" \
--entrypoint="python3" \
"${invokeai_tag}" \
scripts/configure_invokeai.py --yes

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}

View File

@@ -4,7 +4,7 @@ project_name=${PROJECT_NAME:-invokeai}
volumename=${VOLUMENAME:-${project_name}_data}
arch=${ARCH:-x86_64}
platform=${PLATFORM:-Linux/${arch}}
invokeai_tag=${INVOKEAI_TAG:-${project_name}:${arch}}
invokeai_tag=${INVOKEAI_TAG:-${project_name}-${arch}}
export project_name
export volumename

View File

@@ -7,9 +7,9 @@ docker run \
--interactive \
--tty \
--rm \
--platform="$platform" \
--name="$project_name" \
--hostname="$project_name" \
--mount="source=$volumename,target=/data" \
--publish=9090:9090 \
--platform "$platform" \
--name "$project_name" \
--hostname "$project_name" \
--mount source="$volumename",target=/data \
--publish 9090:9090 \
"$invokeai_tag" ${1:+$@}

View File

@@ -4,228 +4,133 @@ title: Changelog
# :octicons-log-16: **Changelog**
## v2.1.0 <small>(2 November 2022)</small>
- update mac instructions to use invokeai for env name by @willwillems in
https://github.com/invoke-ai/InvokeAI/pull/1030
- Update .gitignore by @blessedcoolant in
https://github.com/invoke-ai/InvokeAI/pull/1040
- reintroduce fix for m1 from https://github.com/invoke-ai/InvokeAI/pull/579
missing after merge by @skurovec in
https://github.com/invoke-ai/InvokeAI/pull/1056
- Update Stable_Diffusion_AI_Notebook.ipynb (Take 2) by @ChloeL19 in
https://github.com/invoke-ai/InvokeAI/pull/1060
- Print out the device type which is used by @manzke in
https://github.com/invoke-ai/InvokeAI/pull/1073
- Hires Addition by @hipsterusername in
https://github.com/invoke-ai/InvokeAI/pull/1063
- fix for "1 leaked semaphore objects to clean up at shutdown" on M1 by
@skurovec in https://github.com/invoke-ai/InvokeAI/pull/1081
- Forward dream.py to invoke.py using the same interpreter, add deprecation
warning by @db3000 in https://github.com/invoke-ai/InvokeAI/pull/1077
- fix noisy images at high step counts by @lstein in
https://github.com/invoke-ai/InvokeAI/pull/1086
- Generalize facetool strength argument by @db3000 in
https://github.com/invoke-ai/InvokeAI/pull/1078
- Enable fast switching among models at the invoke> command line by @lstein in
https://github.com/invoke-ai/InvokeAI/pull/1066
- Fix Typo, committed changing ldm environment to invokeai by @jdries3 in
https://github.com/invoke-ai/InvokeAI/pull/1095
- Update generate.py by @unreleased in
https://github.com/invoke-ai/InvokeAI/pull/1109
- Update 'ldm' env to 'invokeai' in troubleshooting steps by @19wolf in
https://github.com/invoke-ai/InvokeAI/pull/1125
- Fixed documentation typos and resolved merge conflicts by @rupeshs in
https://github.com/invoke-ai/InvokeAI/pull/1123
- Fix broken doc links, fix malaprop in the project subtitle by @majick in
https://github.com/invoke-ai/InvokeAI/pull/1131
- Only output facetool parameters if enhancing faces by @db3000 in
https://github.com/invoke-ai/InvokeAI/pull/1119
- Update gitignore to ignore codeformer weights at new location by
@spezialspezial in https://github.com/invoke-ai/InvokeAI/pull/1136
- fix links to point to invoke-ai.github.io #1117 by @mauwii in
https://github.com/invoke-ai/InvokeAI/pull/1143
## v2.1.0 (2 November 2022)
- update mac instructions to use invokeai for env name by @willwillems in https://github.com/invoke-ai/InvokeAI/pull/1030
- Update .gitignore by @blessedcoolant in https://github.com/invoke-ai/InvokeAI/pull/1040
- reintroduce fix for m1 from https://github.com/invoke-ai/InvokeAI/pull/579 missing after merge by @skurovec in https://github.com/invoke-ai/InvokeAI/pull/1056
- Update Stable_Diffusion_AI_Notebook.ipynb (Take 2) by @ChloeL19 in https://github.com/invoke-ai/InvokeAI/pull/1060
- Print out the device type which is used by @manzke in https://github.com/invoke-ai/InvokeAI/pull/1073
- Hires Addition by @hipsterusername in https://github.com/invoke-ai/InvokeAI/pull/1063
- fix for "1 leaked semaphore objects to clean up at shutdown" on M1 by @skurovec in https://github.com/invoke-ai/InvokeAI/pull/1081
- Forward dream.py to invoke.py using the same interpreter, add deprecation warning by @db3000 in https://github.com/invoke-ai/InvokeAI/pull/1077
- fix noisy images at high step counts by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1086
- Generalize facetool strength argument by @db3000 in https://github.com/invoke-ai/InvokeAI/pull/1078
- Enable fast switching among models at the invoke> command line by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1066
- Fix Typo, committed changing ldm environment to invokeai by @jdries3 in https://github.com/invoke-ai/InvokeAI/pull/1095
- Update generate.py by @unreleased in https://github.com/invoke-ai/InvokeAI/pull/1109
- Update 'ldm' env to 'invokeai' in troubleshooting steps by @19wolf in https://github.com/invoke-ai/InvokeAI/pull/1125
- Fixed documentation typos and resolved merge conflicts by @rupeshs in https://github.com/invoke-ai/InvokeAI/pull/1123
- Fix broken doc links, fix malaprop in the project subtitle by @majick in https://github.com/invoke-ai/InvokeAI/pull/1131
- Only output facetool parameters if enhancing faces by @db3000 in https://github.com/invoke-ai/InvokeAI/pull/1119
- Update gitignore to ignore codeformer weights at new location by @spezialspezial in https://github.com/invoke-ai/InvokeAI/pull/1136
- fix links to point to invoke-ai.github.io #1117 by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1143
- Rework-mkdocs by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1144
- add option to CLI and pngwriter that allows user to set PNG compression level
by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1127
- Fix img2img DDIM index out of bound by @wfng92 in
https://github.com/invoke-ai/InvokeAI/pull/1137
- add option to CLI and pngwriter that allows user to set PNG compression level by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1127
- Fix img2img DDIM index out of bound by @wfng92 in https://github.com/invoke-ai/InvokeAI/pull/1137
- Fix gh actions by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1128
- update mac instructions to use invokeai for env name by @willwillems in
https://github.com/invoke-ai/InvokeAI/pull/1030
- Update .gitignore by @blessedcoolant in
https://github.com/invoke-ai/InvokeAI/pull/1040
- reintroduce fix for m1 from https://github.com/invoke-ai/InvokeAI/pull/579
missing after merge by @skurovec in
https://github.com/invoke-ai/InvokeAI/pull/1056
- Update Stable_Diffusion_AI_Notebook.ipynb (Take 2) by @ChloeL19 in
https://github.com/invoke-ai/InvokeAI/pull/1060
- Print out the device type which is used by @manzke in
https://github.com/invoke-ai/InvokeAI/pull/1073
- Hires Addition by @hipsterusername in
https://github.com/invoke-ai/InvokeAI/pull/1063
- fix for "1 leaked semaphore objects to clean up at shutdown" on M1 by
@skurovec in https://github.com/invoke-ai/InvokeAI/pull/1081
- Forward dream.py to invoke.py using the same interpreter, add deprecation
warning by @db3000 in https://github.com/invoke-ai/InvokeAI/pull/1077
- fix noisy images at high step counts by @lstein in
https://github.com/invoke-ai/InvokeAI/pull/1086
- Generalize facetool strength argument by @db3000 in
https://github.com/invoke-ai/InvokeAI/pull/1078
- Enable fast switching among models at the invoke> command line by @lstein in
https://github.com/invoke-ai/InvokeAI/pull/1066
- Fix Typo, committed changing ldm environment to invokeai by @jdries3 in
https://github.com/invoke-ai/InvokeAI/pull/1095
- Fixed documentation typos and resolved merge conflicts by @rupeshs in
https://github.com/invoke-ai/InvokeAI/pull/1123
- Only output facetool parameters if enhancing faces by @db3000 in
https://github.com/invoke-ai/InvokeAI/pull/1119
- add option to CLI and pngwriter that allows user to set PNG compression level
by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1127
- Fix img2img DDIM index out of bound by @wfng92 in
https://github.com/invoke-ai/InvokeAI/pull/1137
- Add text prompt to inpaint mask support by @lstein in
https://github.com/invoke-ai/InvokeAI/pull/1133
- Respect http[s] protocol when making socket.io middleware by @damian0815 in
https://github.com/invoke-ai/InvokeAI/pull/976
- WebUI: Adds Codeformer support by @psychedelicious in
https://github.com/invoke-ai/InvokeAI/pull/1151
- Skips normalizing prompts for web UI metadata by @psychedelicious in
https://github.com/invoke-ai/InvokeAI/pull/1165
- Add Asymmetric Tiling by @carson-katri in
https://github.com/invoke-ai/InvokeAI/pull/1132
- Web UI: Increases max CFG Scale to 200 by @psychedelicious in
https://github.com/invoke-ai/InvokeAI/pull/1172
- Corrects color channels in face restoration; Fixes #1167 by @psychedelicious
in https://github.com/invoke-ai/InvokeAI/pull/1175
- Flips channels using array slicing instead of using OpenCV by @psychedelicious
in https://github.com/invoke-ai/InvokeAI/pull/1178
- Fix typo in docs: s/Formally/Formerly by @noodlebox in
https://github.com/invoke-ai/InvokeAI/pull/1176
- fix clipseg loading problems by @lstein in
https://github.com/invoke-ai/InvokeAI/pull/1177
- Correct color channels in upscale using array slicing by @wfng92 in
https://github.com/invoke-ai/InvokeAI/pull/1181
- Web UI: Filters existing images when adding new images; Fixes #1085 by
@psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1171
- fix a number of bugs in textual inversion by @lstein in
https://github.com/invoke-ai/InvokeAI/pull/1190
- Improve !fetch, add !replay command by @ArDiouscuros in
https://github.com/invoke-ai/InvokeAI/pull/882
- Fix generation of image with s>1000 by @holstvoogd in
https://github.com/invoke-ai/InvokeAI/pull/951
- Web UI: Gallery improvements by @psychedelicious in
https://github.com/invoke-ai/InvokeAI/pull/1198
- update mac instructions to use invokeai for env name by @willwillems in https://github.com/invoke-ai/InvokeAI/pull/1030
- Update .gitignore by @blessedcoolant in https://github.com/invoke-ai/InvokeAI/pull/1040
- reintroduce fix for m1 from https://github.com/invoke-ai/InvokeAI/pull/579 missing after merge by @skurovec in https://github.com/invoke-ai/InvokeAI/pull/1056
- Update Stable_Diffusion_AI_Notebook.ipynb (Take 2) by @ChloeL19 in https://github.com/invoke-ai/InvokeAI/pull/1060
- Print out the device type which is used by @manzke in https://github.com/invoke-ai/InvokeAI/pull/1073
- Hires Addition by @hipsterusername in https://github.com/invoke-ai/InvokeAI/pull/1063
- fix for "1 leaked semaphore objects to clean up at shutdown" on M1 by @skurovec in https://github.com/invoke-ai/InvokeAI/pull/1081
- Forward dream.py to invoke.py using the same interpreter, add deprecation warning by @db3000 in https://github.com/invoke-ai/InvokeAI/pull/1077
- fix noisy images at high step counts by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1086
- Generalize facetool strength argument by @db3000 in https://github.com/invoke-ai/InvokeAI/pull/1078
- Enable fast switching among models at the invoke> command line by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1066
- Fix Typo, committed changing ldm environment to invokeai by @jdries3 in https://github.com/invoke-ai/InvokeAI/pull/1095
- Fixed documentation typos and resolved merge conflicts by @rupeshs in https://github.com/invoke-ai/InvokeAI/pull/1123
- Only output facetool parameters if enhancing faces by @db3000 in https://github.com/invoke-ai/InvokeAI/pull/1119
- add option to CLI and pngwriter that allows user to set PNG compression level by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1127
- Fix img2img DDIM index out of bound by @wfng92 in https://github.com/invoke-ai/InvokeAI/pull/1137
- Add text prompt to inpaint mask support by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1133
- Respect http[s] protocol when making socket.io middleware by @damian0815 in https://github.com/invoke-ai/InvokeAI/pull/976
- WebUI: Adds Codeformer support by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1151
- Skips normalizing prompts for web UI metadata by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1165
- Add Asymmetric Tiling by @carson-katri in https://github.com/invoke-ai/InvokeAI/pull/1132
- Web UI: Increases max CFG Scale to 200 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1172
- Corrects color channels in face restoration; Fixes #1167 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1175
- Flips channels using array slicing instead of using OpenCV by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1178
- Fix typo in docs: s/Formally/Formerly by @noodlebox in https://github.com/invoke-ai/InvokeAI/pull/1176
- fix clipseg loading problems by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1177
- Correct color channels in upscale using array slicing by @wfng92 in https://github.com/invoke-ai/InvokeAI/pull/1181
- Web UI: Filters existing images when adding new images; Fixes #1085 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1171
- fix a number of bugs in textual inversion by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1190
- Improve !fetch, add !replay command by @ArDiouscuros in https://github.com/invoke-ai/InvokeAI/pull/882
- Fix generation of image with s>1000 by @holstvoogd in https://github.com/invoke-ai/InvokeAI/pull/951
- Web UI: Gallery improvements by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1198
- Update CLI.md by @krummrey in https://github.com/invoke-ai/InvokeAI/pull/1211
- outcropping improvements by @lstein in
https://github.com/invoke-ai/InvokeAI/pull/1207
- add support for loading VAE autoencoders by @lstein in
https://github.com/invoke-ai/InvokeAI/pull/1216
- remove duplicate fix_func for MPS by @wfng92 in
https://github.com/invoke-ai/InvokeAI/pull/1210
- Metadata storage and retrieval fixes by @lstein in
https://github.com/invoke-ai/InvokeAI/pull/1204
- nix: add shell.nix file by @Cloudef in
https://github.com/invoke-ai/InvokeAI/pull/1170
- Web UI: Changes vite dist asset paths to relative by @psychedelicious in
https://github.com/invoke-ai/InvokeAI/pull/1185
- Web UI: Removes isDisabled from PromptInput by @psychedelicious in
https://github.com/invoke-ai/InvokeAI/pull/1187
- Allow user to generate images with initial noise as on M1 / mps system by
@ArDiouscuros in https://github.com/invoke-ai/InvokeAI/pull/981
- feat: adding filename format template by @plucked in
https://github.com/invoke-ai/InvokeAI/pull/968
- Web UI: Fixes broken bundle by @psychedelicious in
https://github.com/invoke-ai/InvokeAI/pull/1242
- Support runwayML custom inpainting model by @lstein in
https://github.com/invoke-ai/InvokeAI/pull/1243
- Update IMG2IMG.md by @talitore in
https://github.com/invoke-ai/InvokeAI/pull/1262
- New dockerfile - including a build- and a run- script as well as a GH-Action
by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1233
- cut over from karras to model noise schedule for higher steps by @lstein in
https://github.com/invoke-ai/InvokeAI/pull/1222
- outcropping improvements by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1207
- add support for loading VAE autoencoders by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1216
- remove duplicate fix_func for MPS by @wfng92 in https://github.com/invoke-ai/InvokeAI/pull/1210
- Metadata storage and retrieval fixes by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1204
- nix: add shell.nix file by @Cloudef in https://github.com/invoke-ai/InvokeAI/pull/1170
- Web UI: Changes vite dist asset paths to relative by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1185
- Web UI: Removes isDisabled from PromptInput by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1187
- Allow user to generate images with initial noise as on M1 / mps system by @ArDiouscuros in https://github.com/invoke-ai/InvokeAI/pull/981
- feat: adding filename format template by @plucked in https://github.com/invoke-ai/InvokeAI/pull/968
- Web UI: Fixes broken bundle by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1242
- Support runwayML custom inpainting model by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1243
- Update IMG2IMG.md by @talitore in https://github.com/invoke-ai/InvokeAI/pull/1262
- New dockerfile - including a build- and a run- script as well as a GH-Action by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1233
- cut over from karras to model noise schedule for higher steps by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1222
- Prompt tweaks by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1268
- Outpainting implementation by @Kyle0654 in
https://github.com/invoke-ai/InvokeAI/pull/1251
- fixing aspect ratio on hires by @tjennings in
https://github.com/invoke-ai/InvokeAI/pull/1249
- Fix-build-container-action by @mauwii in
https://github.com/invoke-ai/InvokeAI/pull/1274
- handle all unicode characters by @damian0815 in
https://github.com/invoke-ai/InvokeAI/pull/1276
- adds models.user.yml to .gitignore by @JakeHL in
https://github.com/invoke-ai/InvokeAI/pull/1281
- remove debug branch, set fail-fast to false by @mauwii in
https://github.com/invoke-ai/InvokeAI/pull/1284
- Protect-secrets-on-pr by @mauwii in
https://github.com/invoke-ai/InvokeAI/pull/1285
- Web UI: Adds initial inpainting implementation by @psychedelicious in
https://github.com/invoke-ai/InvokeAI/pull/1225
- fix environment-mac.yml - tested on x64 and arm64 by @mauwii in
https://github.com/invoke-ai/InvokeAI/pull/1289
- Use proper authentication to download model by @mauwii in
https://github.com/invoke-ai/InvokeAI/pull/1287
- Prevent indexing error for mode RGB by @spezialspezial in
https://github.com/invoke-ai/InvokeAI/pull/1294
- Integrate sd-v1-5 model into test matrix (easily expandable), remove
unecesarry caches by @mauwii in
https://github.com/invoke-ai/InvokeAI/pull/1293
- add --no-interactive to preload_models step by @mauwii in
https://github.com/invoke-ai/InvokeAI/pull/1302
- 1-click installer and updater. Uses micromamba to install git and conda into a
contained environment (if necessary) before running the normal installation
script by @cmdr2 in https://github.com/invoke-ai/InvokeAI/pull/1253
- preload_models.py script downloads the weight files by @lstein in
https://github.com/invoke-ai/InvokeAI/pull/1290
- Outpainting implementation by @Kyle0654 in https://github.com/invoke-ai/InvokeAI/pull/1251
- fixing aspect ratio on hires by @tjennings in https://github.com/invoke-ai/InvokeAI/pull/1249
- Fix-build-container-action by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1274
- handle all unicode characters by @damian0815 in https://github.com/invoke-ai/InvokeAI/pull/1276
- adds models.user.yml to .gitignore by @JakeHL in https://github.com/invoke-ai/InvokeAI/pull/1281
- remove debug branch, set fail-fast to false by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1284
- Protect-secrets-on-pr by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1285
- Web UI: Adds initial inpainting implementation by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1225
- fix environment-mac.yml - tested on x64 and arm64 by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1289
- Use proper authentication to download model by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1287
- Prevent indexing error for mode RGB by @spezialspezial in https://github.com/invoke-ai/InvokeAI/pull/1294
- Integrate sd-v1-5 model into test matrix (easily expandable), remove unecesarry caches by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1293
- add --no-interactive to preload_models step by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1302
- 1-click installer and updater. Uses micromamba to install git and conda into a contained environment (if necessary) before running the normal installation script by @cmdr2 in https://github.com/invoke-ai/InvokeAI/pull/1253
- preload_models.py script downloads the weight files by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1290
## v2.0.1 <small>(13 October 2022)</small>
## 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)
- 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)
## v2.0.0 <small>(9 October 2022)</small>
- `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains for
backward compatibility.
- `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 [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:
- 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`.
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)).
([prixt](https://github.com/prixt)).
- Inpainting support.
- Improved web server GUI.
- Lots of code and documentation cleanups.
@@ -233,17 +138,16 @@ title: Changelog
## 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)
([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)
[Kevin Gibbons](https://github.com/bakkot)
- WebUI supports incremental display of in-progress images during generation
[Kevin Gibbons](https://github.com/bakkot)
[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))
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.
- Works on M1 Apple hardware.
@@ -255,59 +159,49 @@ title: Changelog
- Improved file handling, including ability to read prompts from standard input.
(kudos to [Yunsaki](https://github.com/yunsaki)
- The web server is now integrated with the invoke.py script. Invoke by adding
--web to the invoke.py command arguments.
- The web server is now integrated with the invoke.py script. Invoke by adding --web to
the invoke.py command arguments.
- 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.
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.
- You can now swap samplers on the invoke> command line.
[Blessedcoolant](https://github.com/blessedcoolant)
- You can now swap samplers on the invoke> command line. [Blessedcoolant](https://github.com/blessedcoolant)
---
## 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)
- 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.
- 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.
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.
- 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) 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.
- 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)
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.
---
## 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 <small>(24 August 2022)</small>
- A new -v option allows you to generate multiple variants of an initial image
in img2img mode. (kudos to [Oceanswave](https://github.com/Oceanswave).
[ See this discussion in the PR for examples and details on use](https://github.com/lstein/stable-diffusion/pull/71#issuecomment-1226700810))
- Added ability to personalize text to image generation (kudos to
[Oceanswave](https://github.com/Oceanswave) and
[nicolai256](https://github.com/nicolai256))
in img2img mode. (kudos to [Oceanswave](https://github.com/Oceanswave). [
See this discussion in the PR for examples and details on use](https://github.com/lstein/stable-diffusion/pull/71#issuecomment-1226700810))
- Added ability to personalize text to image generation (kudos to [Oceanswave](https://github.com/Oceanswave) and [nicolai256](https://github.com/nicolai256))
- Enabled all of the samplers from k_diffusion
---
## v1.08 <small>(24 August 2022)</small>
- Escape single quotes on the invoke> command before trying to parse. This
avoids parse errors.
- Escape single quotes on the invoke> command before trying to parse. This avoids
parse errors.
- Removed instruction to get Python3.8 as first step in Windows install.
Anaconda3 does it for you.
- Added bounds checks for numeric arguments that could cause crashes.
@@ -317,36 +211,34 @@ title: Changelog
## v1.07 <small>(23 August 2022)</small>
- 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 sort orders are the same.
- 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
sort orders are the same.
---
## v1.06 <small>(23 August 2022)</small>
- 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)
- 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)
---
## v1.05 <small>(22 August 2022 - after the drop)</small>
- Filenames now use the following formats: 000010.95183149.png -- Two files
produced by the same command (e.g. -n2), 000010.26742632.png -- distinguished
by a different seed.
- Filenames now use the following formats:
000010.95183149.png -- Two files produced by the same command (e.g. -n2),
000010.26742632.png -- distinguished by a different seed.
000011.455191342.01.png -- Two files produced by the same command using
000011.455191342.02.png -- a batch size>1 (e.g. -b2). They have the same seed.
000011.4160627868.grid#1-4.png -- a grid of four images (-g); the whole grid
can be regenerated with the indicated key
000011.4160627868.grid#1-4.png -- a grid of four images (-g); the whole grid can
be regenerated with the indicated key
- It should no longer be possible for one image to overwrite another
- You can use the "cd" and "pwd" commands at the invoke> prompt to set and
retrieve the path of the output directory.
- You can use the "cd" and "pwd" commands at the invoke> prompt to set and retrieve
the path of the output directory.
---
@@ -360,28 +252,26 @@ title: Changelog
## v1.03 <small>(22 August 2022)</small>
- The original txt2img and img2img scripts from the CompViz repository have been
moved into a subfolder named "orig_scripts", to reduce confusion.
- The original txt2img and img2img scripts from the CompViz repository have been moved into
a subfolder named "orig_scripts", to reduce confusion.
---
## 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 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. **Please run "conda env update" to load the k_lms
dependencies!!**
- 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,
or an image editor that allows you to explore the full metadata.
**Please run "conda env update" to load the k_lms dependencies!!**
---
## v1.01 <small>(21 August 2022)</small>
- added k_lms sampling. **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 Pass argument --full_precision to invoke.py to get
slower but more accurate image generation
- added k_lms sampling.
**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
Pass argument --full_precision to invoke.py to get slower but more accurate image generation
---

Binary file not shown.

Before

Width:  |  Height:  |  Size: 122 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 128 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 99 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 112 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 107 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 169 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

Binary file not shown.

After

Width:  |  Height:  |  Size: 380 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 372 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 401 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 441 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 451 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.3 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 338 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 271 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 353 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 330 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 439 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 463 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 444 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 468 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 466 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 475 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 429 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 429 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.3 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 477 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 476 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 434 KiB

View File

@@ -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

View File

@@ -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

View File

@@ -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

View File

@@ -1,14 +1,16 @@
---
title: CLI
hide:
- toc
---
# :material-bash: CLI
## **Interactive Command Line Interface**
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.
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.
Unlike the `txt2img.py` and `img2img.py` scripts provided in the original
[CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion) source
@@ -58,9 +60,9 @@ invoke> q
![invoke-py-demo](../assets/dream-py-demo.png)
The `invoke>` prompt's arguments are pretty much identical to those used in the
Discord bot, except you don't need to type `!invoke` (it doesn't hurt if you
do). A significant change is that creation of individual images is now the
default unless `--grid` (`-g`) is given. A full list is given in
Discord bot, except you don't need to type `!invoke` (it doesn't hurt if you do).
A significant change is that creation of individual images is now the default
unless `--grid` (`-g`) is given. A full list is given in
[List of prompt arguments](#list-of-prompt-arguments).
## Arguments
@@ -73,8 +75,7 @@ the location of the model weight files.
These command-line arguments can be passed to `invoke.py` when you first run it
from the Windows, Mac or Linux command line. Some set defaults that can be
overridden on a per-prompt basis (see
[List of prompt arguments](#list-of-prompt-arguments). Others
overridden on a per-prompt basis (see [List of prompt arguments](#list-of-prompt-arguments). Others
| Argument <img width="240" align="right"/> | Shortcut <img width="100" align="right"/> | Default <img width="320" align="right"/> | Description |
| ----------------------------------------- | ----------------------------------------- | ---------------------------------------------- | ---------------------------------------------------------------------------------------------------- |
@@ -84,22 +85,19 @@ overridden on a per-prompt basis (see
| `--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 |
| `--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. |
| `--config <path>` | | `configs/models.yaml` | Configuration file for models and their weights. |
| `--iterations <int>` | `-n<int>` | `1` | How many images to generate per prompt. |
| `--width <int>` | `-W<int>` | `512` | Width of generated image |
| `--height <int>` | `-H<int>` | `512` | Height of generated image | `--steps <int>` | `-s<int>` | `50` | How many steps of refinement to apply |
| `--strength <float>` | `-s<float>` | `0.75` | For img2img: how hard to try to match the prompt to the initial image. Ranges from 0.0-0.99, with higher values replacing the initial image completely. |
| `--fit` | `-F` | `False` | For img2img: scale the init image to fit into the specified -H and -W dimensions |
| `--grid` | `-g` | `False` | Save all image series as a grid rather than individually. |
| `--sampler <sampler>` | `-A<sampler>` | `k_lms` | Sampler to use. Use `-h` to get list of available samplers. |
| `--seamless` | | `False` | Create interesting effects by tiling elements of the image. |
| `--embedding_path <path>` | | `None` | Path to pre-trained embedding manager checkpoints, for custom models |
| `--gfpgan_model_path` | | `experiments/pretrained_models/GFPGANv1.4.pth` | Path to GFPGAN model file. |
| `--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`. |
| `--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 |
@@ -109,7 +107,7 @@ overridden on a per-prompt basis (see
| Argument | Shortcut | Default | Description |
|--------------------|------------|---------------------|--------------|
| `--weights <path>` | | `None` | Path to weights file; use `--model stable-diffusion-1.4` instead |
| `--weights <path>` | | `None` | Pth to weights file; use `--model stable-diffusion-1.4` instead |
| `--laion400m` | `-l` | `False` | Use older LAION400m weights; use `--model=laion400m` instead |
</div>
@@ -122,34 +120,11 @@ overridden on a per-prompt basis (see
You can either double your slashes (ick): `C:\\path\\to\\my\\file`, or
use Linux/Mac style forward slashes (better): `C:/path/to/my/file`.
## The .invokeai initialization file
To start up invoke.py with your preferred settings, place your desired
startup options in a file in your home directory named `.invokeai` The
file should contain the startup options as you would type them on the
command line (`--steps=10 --grid`), one argument per line, or a
mixture of both using any of the accepted command switch formats:
!!! example ""
```bash
--web
--steps=28
--grid
-f 0.6 -C 11.0 -A k_euler_a
```
Note that the initialization file only accepts the command line arguments.
There are additional arguments that you can provide on the `invoke>` command
line (such as `-n` or `--iterations`) that cannot be entered into this file.
Also be alert for empty blank lines at the end of the file, which will cause
an arguments error at startup time.
## List of prompt arguments
After the invoke.py script initializes, it will present you with a `invoke>`
prompt. Here you can enter information to generate images from text
([txt2img](#txt2img)), to embellish an existing image or sketch
After the invoke.py script initializes, it will present you with a
`invoke>` prompt. Here you can enter information to generate images
from text ([txt2img](#txt2img)), to embellish an existing image or sketch
([img2img](#img2img)), or to selectively alter chosen regions of the image
([inpainting](#inpainting)).
@@ -166,59 +141,60 @@ prompt. Here you can enter information to generate images from text
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. |
| `--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 |
| 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. |
| --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 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.
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.
### This is an example of img2img:
```
### This is an example of img2img:
~~~~
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:
In addition to the command-line options recognized by txt2img, img2img
accepts additional options:
| Argument <img width="160" align="right"/> | Shortcut | Default | Description |
| ----------------------------------------- | ----------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
| `--init_img <path>` | `-I<path>` | `None` | Path to the initialization image |
| `--fit` | `-F` | `False` | Scale the image to fit into the specified -H and -W dimensions |
| `--strength <float>` | `-s<float>` | `0.75` | How hard to try to match the prompt to the initial image. Ranges from 0.0-0.99, with higher values replacing the initial image completely. |
| Argument <img width="160" align="right"/> | Shortcut | Default | Description |
|----------------------|-------------|-----------------|--------------|
| `--init_img <path>` | `-I<path>` | `None` | Path to the initialization image |
| `--fit` | `-F` | `False` | Scale the image to fit into the specified -H and -W dimensions |
| `--strength <float>` | `-s<float>` | `0.75` | How hard to try to match the prompt to the initial image. Ranges from 0.0-0.99, with higher values replacing the initial image completely.|
### inpainting
@@ -235,45 +211,41 @@ additional options:
the pixels underneath when you create the transparent areas. See
[Inpainting](./INPAINTING.md) for details.
inpainting accepts all the arguments used for txt2img and img2img, as well as
the --mask (-M) and --text_mask (-tm) arguments:
inpainting accepts all the arguments used for txt2img and img2img, as
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 |
| 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|
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.
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.
`--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:
`--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.
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
```
### Custom Styles and Subjects
You can load and use hundreds of community-contributed Textual
Inversion models just by typing the appropriate trigger phrase. Please
see [Concepts Library](CONCEPTS.md) for more details.
~~~
# Other Commands
@@ -281,26 +253,31 @@ 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.
To postprocess a file using face restoration or upscaling, use the
`!fix` command.
### `!fix`
This command runs a post-processor on a previously-generated image. It takes a
PNG filename or path and applies your choice of the `-U`, `-G`, or `--embiggen`
switches in order to fix faces or upscale. If you provide a filename, the script
will look for it in the current output directory. Otherwise you can provide a
full or partial path to the desired file.
This command runs a post-processor on a previously-generated image. It
takes a PNG filename or path and applies your choice of the `-U`, `-G`, or
`--embiggen` switches in order to fix faces or upscale. If you provide a
filename, the script will look for it in the current output
directory. Otherwise you can provide a full or partial path to the
desired file.
Some examples:
!!! example "Upscale to 4X its original size and fix faces using codeformer"
!!! example ""
Upscale to 4X its original size and fix faces using codeformer:
```bash
invoke> !fix 0000045.4829112.png -G1 -U4 -ft codeformer
```
!!! example "Use the GFPGAN algorithm to fix faces, then upscale to 3X using --embiggen"
!!! example ""
Use the GFPGAN algorithm to fix faces, then upscale to 3X using --embiggen:
```bash
invoke> !fix 0000045.4829112.png -G0.8 -ft gfpgan
@@ -309,27 +286,26 @@ Some examples:
>> GFPGAN - Restoring Faces for image seed:4829112
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.
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.
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
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>
@@ -338,12 +314,13 @@ waifu-diffusion not loaded Waifu Diffusion v1.3
### !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.
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
@@ -383,22 +360,24 @@ waifu-diffusion cached Waifu Diffusion v1.3
### !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.
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).
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
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:
@@ -433,13 +412,12 @@ invoke>
###!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.
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
@@ -462,28 +440,28 @@ OK to import [n]? y
>> 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 ```
=======
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
The CLI provides a series of convenient commands for reviewing previous actions,
retrieving them, modifying them, and re-running them.
The CLI provides a series of convenient commands for reviewing previous
actions, retrieving them, modifying them, and re-running them.
### !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 also writes the
command-line history out to disk, giving you access to the most recent 1000
commands issued.
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
also writes the command-line history out to disk, giving you access to
the most recent 1000 commands issued.
The `!history` command will return a numbered list of all the commands issued
during the session (Windows), or the most recent 1000 commands (Mac|Linux). You
can then repeat a command by using the command `!NNN`, where "NNN" is the
history line number. For example:
The `!history` command will return a numbered list of all the commands
issued during the session (Windows), or the most recent 1000 commands
(Mac|Linux). You can then repeat a command by using the command `!NNN`,
where "NNN" is the history line number. For example:
```bash
invoke> !history
@@ -500,13 +478,14 @@ invoke> watercolor of beautiful woman sitting under tree wearing broad hat and f
### !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 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:
@@ -516,8 +495,8 @@ invoke> !fetch 0000015.8929913.png
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`:
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
@@ -527,12 +506,12 @@ invoke> !fetch outputs\selected-imgs\*.png selected.txt
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.
Note that these commands may behave unexpectedly if given a PNG file that
was not generated by InvokeAI.
### !search <search string>
@@ -546,47 +525,42 @@ invoke> !search surreal
### `!clear`
This clears the search history from memory and disk. Be advised that this
operation is irreversible and does not issue any warnings!
This clears the search history from memory and disk. Be advised that
this operation is irreversible and does not issue any warnings!
## Command-line editing and completion
The command-line offers convenient history tracking, editing, and command
completion.
The command-line offers convenient history tracking, editing, and
command completion.
- To scroll through previous commands and potentially edit/reuse them, use the
++up++ and ++down++ keys.
- To edit the current command, use the ++left++ and ++right++ keys to position
the cursor, and then ++backspace++, ++delete++ or insert characters.
- To move to the very beginning of the command, type ++ctrl+a++ (or
++command+a++ on the Mac)
- To scroll through previous commands and potentially edit/reuse them, use the ++up++ and ++down++ keys.
- To edit the current command, use the ++left++ and ++right++ keys to position the cursor, and then ++backspace++, ++delete++ or insert characters.
- To move to the very beginning of the command, type ++ctrl+a++ (or ++command+a++ on the Mac)
- To move to the end of the command, type ++ctrl+e++.
- To cut a section of the command, position the cursor where you want to start
cutting and type ++ctrl+k++
- To paste a cut section back in, position the cursor where you want to paste,
and type ++ctrl+y++
- To cut a section of the command, position the cursor where you want to start cutting and type ++ctrl+k++
- To paste a cut section back in, position the cursor where you want to paste, and type ++ctrl+y++
Windows users can get similar, but more limited, functionality if they launch
`invoke.py` with the `winpty` program and have the `pyreadline3` library
installed:
Windows users can get similar, but more limited, functionality if they
launch `invoke.py` with the `winpty` program and have the `pyreadline3`
library installed:
```batch
> winpty python scripts\invoke.py
```
On the Mac and Linux platforms, when you exit invoke.py, the last 1000 lines of
your command-line history will be saved. When you restart `invoke.py`, you can
access the saved history using the ++up++ key.
On the Mac and Linux platforms, when you exit invoke.py, the last 1000
lines of your command-line history will be saved. When you restart
`invoke.py`, you can access the saved history using the ++up++ key.
In addition, limited command-line completion is installed. In various contexts,
you can start typing your command and press ++tab++. A list of potential
completions will be presented to you. You can then type a little more, hit
++tab++ again, and eventually autocomplete what you want.
In addition, limited command-line completion is installed. In various
contexts, you can start typing your command and press ++tab++. A list of
potential completions will be presented to you. You can then type a
little more, hit ++tab++ again, and eventually autocomplete what you want.
When specifying file paths using the one-letter shortcuts, the CLI will attempt
to complete pathnames for you. This is most handy for the `-I` (init image) and
`-M` (init mask) paths. To initiate completion, start the path with a slash
(`/`) or `./`. For example:
When specifying file paths using the one-letter shortcuts, the CLI
will attempt to complete pathnames for you. This is most handy for the
`-I` (init image) and `-M` (init mask) paths. To initiate completion, start
the path with a slash (`/`) or `./`. For example:
```bash
invoke> zebra with a mustache -I./test-pictures<TAB>

View File

@@ -1,132 +0,0 @@
---
title: The Hugging Face Concepts Library and Importing Textual Inversion files
---
# :material-file-document: Concepts Library
## Using Textual Inversion Files
Textual inversion (TI) files are small models that customize the output of
Stable Diffusion image generation. They can augment SD with
specialized subjects and artistic styles. They are also known as
"embeds" in the machine learning world.
Each TI file introduces one or more vocabulary terms to the SD
model. These are known in InvokeAI as "triggers." Triggers are often,
but not always, denoted using angle brackets as in
"&lt;trigger-phrase&gt;". The two most common type of TI files that you'll
encounter are `.pt` and `.bin` files, which are produced by different
TI training packages. InvokeAI supports both formats, but its [built-in
TI training system](TEXTUAL_INVERSION.md) produces `.pt`.
The [Hugging Face company](https://huggingface.co/sd-concepts-library)
has amassed a large ligrary of &gt;800 community-contributed TI files
covering a broad range of subjects and styles. InvokeAI has built-in
support for this library which downloads and merges TI files
automatically upon request. You can also install your own or others'
TI files by placing them in a designated directory.
### An Example
Here are a few examples to illustrate how it works. All these images
were generated using the command-line client and the Stable Diffusion
1.5 model:
Japanese gardener
<br>
<img src="../assets/concepts/image1.png">
Japanese gardener &lt;ghibli-face&gt;
<br>
<img src="../assets/concepts/image2.png">
Japanese gardener &lt;hoi4-leaders&gt;
<br>
<img src="../assets/concepts/image3.png">
Japanese gardener &lt;cartoona-animals&gt;
<br>
<img src="../assets/concepts/image4.png">
You can also combine styles and concepts:
A portrait of &lt;alf&gt; in &lt;cartoona-animal&gt; style
<br>
<img src="../assets/concepts/image5.png">
## Using a Hugging Face Concept
Hugging Face TI concepts are downloaded and installed automatically as
you require them. This requires your machine to be connected to the
Internet. To find out what each concept is for, you can browse the
[Hugging Face concepts
library](https://huggingface.co/sd-concepts-library) and look at
examples of what each concept produces.
When you have an idea of a concept you wish to try, go to the
command-line client (CLI) and type a "&lt;" character and the beginning
of the Hugging Face concept name you wish to load. Press the Tab key,
and the CLI will show you all matching concepts. You can also type "&lt;"
and Tab to get a listing of all ~800 concepts, but be prepared to
scroll up to see them all! If there is more than one match you can
continue to type and Tab until the concept is completed.
For example if you type "&lt;x" and Tab, you'll be prompted with the completions:
```
<xatu2> <xatu> <xbh> <xi> <xidiversity> <xioboma> <xuna> <xyz>
```
Now type "id" and press Tab. It will be autocompleted to
"&lt;xidiversity&gt;" because this is a unique match.
Finish your prompt and generate as usual. You may include multiple
concept terms in the prompt.
If you have never used this concept before, you will see a message
that the TI model is being downloaded and installed. After this, the
concept will be saved locally (in the `models/sd-concepts-library`
directory) for future use.
Several steps happen during downloading and
installation, including a scan of the file for malicious code. Should
any errors occur, you will be warned and the concept will fail to
load. Generation will then continue treating the trigger term as a
normal string of characters (e.g. as literal "&lt;ghibli-face&gt;").
Currently auto-installation of concepts is a feature only available on
the command-line client. Support for the WebUI is a work in progress.
## Installing your Own TI Files
You may install any number of `.pt` and `.bin` files simply by copying
them into the `embeddings` directory of the InvokeAI runtime directory
(usually `invokeai` in your home directory). You may create
subdirectories in order to organize the files in any way you wish. Be
careful not to overwrite one file with another. For example, TI files
generated by the Hugging Face toolkit share the named
`learned_embedding.bin`. You can use subdirectories to keep them
distinct.
At startup time, InvokeAI will scan the `embeddings` directory and
load any TI files it finds there. At startup you will see a message
similar to this one:
```
>> Current embedding manager terms: *, <HOI4-Leader>, <princess-knight>
```
Note the "*" trigger term. This is a placeholder term that many early
TI tutorials taught people to use rather than a more descriptive
term. Unfortunately, if you have multiple TI files that all use this
term, only the first one loaded will be triggered by use of the term.
To avoid this problem, you can use the `merge_embeddings.py` script to
merge two or more TI files together. If it encounters a collision of
terms, the script will prompt you to select new terms that do not
collide. See [Textual Inversion](TEXTUAL_INVERSION.md) for details.
## Further Reading
Please see [the repository](https://github.com/rinongal/textual_inversion) and
associated paper for details and limitations.

View File

@@ -85,7 +85,7 @@ increasing size, every tile after the first in a row or column
effectively only covers an extra `1 - overlap_ratio` on each axis. If
the input/`--init_img` is same size as a tile, the ideal (for time)
scaling factors with the default overlap (0.25) are 1.75, 2.5, 3.25,
4.0, etc.
4.0 etc..
`-embiggen_tiles <spaced list of tiles>`
@@ -100,15 +100,6 @@ Tiles are numbered starting with one, and left-to-right,
top-to-bottom. So, if you are generating a 3x3 tiled image, the
middle row would be `4 5 6`.
`-embiggen_strength <strength>`
Another advanced option if you want to experiment with the strength parameter
that embiggen uses when it calls Img2Img. Values range from 0.0 to 1.0
and lower values preserve more of the character of the initial image.
Values that are too high will result in a completely different end image,
while values that are too low will result in an image not dissimilar to one
you would get with ESRGAN upscaling alone. The default value is 0.4.
### Examples
!!! example ""

View File

@@ -6,11 +6,10 @@ title: Image-to-Image
## `img2img`
This script also provides an `img2img` feature that lets you seed your creations
with an initial drawing or photo. This is a really cool feature that tells
stable diffusion to build the prompt on top of the image you provide, preserving
the original's basic shape and layout. To use it, provide the `--init_img`
option as shown here:
This script also provides an `img2img` feature that lets you seed your creations with an initial
drawing or photo. This is a really cool feature that tells stable diffusion to build the prompt on
top of the image you provide, preserving the original's basic shape and layout. To use it, provide
the `--init_img` option as shown here:
```commandline
tree on a hill with a river, nature photograph, national geographic -I./test-pictures/tree-and-river-sketch.png -f 0.85
@@ -19,76 +18,63 @@ tree on a hill with a river, nature photograph, national geographic -I./test-pic
This will take the original image shown here:
<figure markdown>
![original-image](https://user-images.githubusercontent.com/50542132/193946000-c42a96d8-5a74-4f8a-b4c3-5213e6cadcce.png){ width=320 }
<img src="https://user-images.githubusercontent.com/50542132/193946000-c42a96d8-5a74-4f8a-b4c3-5213e6cadcce.png" width=350>
</figure>
and generate a new image based on it as shown here:
<figure markdown>
![generated-image](https://user-images.githubusercontent.com/111189/194135515-53d4c060-e994-4016-8121-7c685e281ac9.png){ width=320 }
<img src="https://user-images.githubusercontent.com/111189/194135515-53d4c060-e994-4016-8121-7c685e281ac9.png" width=350>
</figure>
The `--init_img` (`-I`) option gives the path to the seed picture. `--strength`
(`-f`) controls how much the original will be modified, ranging from `0.0` (keep
the original intact), to `1.0` (ignore the original completely). The default is
`0.75`, and ranges from `0.25-0.90` give interesting results. Other relevant
options include `-C` (classification free guidance scale), and `-s` (steps).
Unlike `txt2img`, adding steps will continuously change the resulting image and
it will not converge.
The `--init_img` (`-I`) option gives the path to the seed picture. `--strength` (`-f`) controls how much
the original will be modified, ranging from `0.0` (keep the original intact), to `1.0` (ignore the
original completely). The default is `0.75`, and ranges from `0.25-0.90` give interesting results.
Other relevant options include `-C` (classification free guidance scale), and `-s` (steps). Unlike `txt2img`,
adding steps will continuously change the resulting image and it will not converge.
You may also pass a `-v<variation_amount>` option to generate `-n<iterations>`
count variants on the original image. This is done by passing the first
generated image back into img2img the requested number of times. It generates
You may also pass a `-v<variation_amount>` option to generate `-n<iterations>` count variants on
the original image. This is done by passing the first generated image
back into img2img the requested number of times. It generates
interesting variants.
Note that the prompt makes a big difference. For example, this slight variation
on the prompt produces a very different image:
Note that the prompt makes a big difference. For example, this slight variation on the prompt produces
a very different image:
<figure markdown>
![](https://user-images.githubusercontent.com/111189/194135220-16b62181-b60c-4248-8989-4834a8fd7fbd.png){ width=320 }
<img src="https://user-images.githubusercontent.com/111189/194135220-16b62181-b60c-4248-8989-4834a8fd7fbd.png" width=350>
<caption markdown>photograph of a tree on a hill with a river</caption>
</figure>
!!! tip
When designing prompts, think about how the images scraped from the internet were
captioned. Very few photographs will be labeled "photograph" or "photorealistic."
They will, however, be captioned with the publication, photographer, camera model,
or film settings.
When designing prompts, think about how the images scraped from the internet were captioned. Very few photographs will
be labeled "photograph" or "photorealistic." They will, however, be captioned with the publication, photographer, camera
model, or film settings.
If the initial image contains transparent regions, then Stable Diffusion will
only draw within the transparent regions, a process called
[`inpainting`](./INPAINTING.md#creating-transparent-regions-for-inpainting).
However, for this to work correctly, the color information underneath the
transparent needs to be preserved, not erased.
If the initial image contains transparent regions, then Stable Diffusion will only draw within the
transparent regions, a process called [`inpainting`](./INPAINTING.md#creating-transparent-regions-for-inpainting). However, for this to work correctly, the color
information underneath the transparent needs to be preserved, not erased.
!!! warning "**IMPORTANT ISSUE** "
!!! 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:
```
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?
The main difference between `img2img` and `prompt2img` is the starting point.
While `prompt2img` always starts with pure gaussian noise and progressively
refines it over the requested number of steps, `img2img` skips some of these
earlier steps (how many it skips is indirectly controlled by the `--strength`
parameter), and uses instead your initial image mixed with gaussian noise as the
starting image.
The main difference between `img2img` and `prompt2img` is the starting point. While `prompt2img` always starts with pure
gaussian noise and progressively refines it over the requested number of steps, `img2img` skips some of these earlier steps
(how many it skips is indirectly controlled by the `--strength` parameter), and uses instead your initial image mixed with gaussian noise as the starting image.
**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:
**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
```
@@ -96,16 +82,9 @@ invoke> "fire" -s10 -W384 -H384 -S1592514025
![latent steps](../assets/img2img/000019.steps.png)
</figure>
Put simply: starting from a frame of fuzz/static, SD finds details in each frame
that it thinks look like "fire" and brings them a little bit more into focus,
gradually scrubbing out the fuzz until a clear image remains.
Put simply: starting from a frame of fuzz/static, SD finds details in each frame that it thinks look like "fire" and brings them a little bit more into focus, gradually scrubbing out the fuzz until a clear image remains.
**When you use `img2img`** some of the earlier steps are cut, and instead an
initial image of your choice is used. But because of how the maths behind Stable
Diffusion works, this image needs to be mixed with just the right amount of
noise (fuzz/static) for where it is being inserted. This is where the strength
parameter comes in. Depending on the set strength, your image will be inserted
into the sequence at the appropriate point, with just the right amount of noise.
**When you use `img2img`** some of the earlier steps are cut, and instead an initial image of your choice is used. But because of how the maths behind Stable Diffusion works, this image needs to be mixed with just the right amount of noise (fuzz/static) for where it is being inserted. This is where the strength parameter comes in. Depending on the set strength, your image will be inserted into the sequence at the appropriate point, with just the right amount of noise.
### A concrete example
@@ -115,9 +94,7 @@ I want SD to draw a fire based on this hand-drawn image:
![drawing of a fireplace](../assets/img2img/fire-drawing.png)
</figure>
Let's only do 10 steps, to make it easier to see what's happening. If strength
is `0.7`, this is what the internal steps the algorithm has to take will look
like:
Let's only do 10 steps, to make it easier to see what's happening. If strength is `0.7`, this is what the internal steps the algorithm has to take will look like:
<figure markdown>
![gravity32](../assets/img2img/000032.steps.gravity.png)
@@ -129,49 +106,33 @@ With strength `0.4`, the steps look more like this:
![gravity30](../assets/img2img/000030.steps.gravity.png)
</figure>
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`:
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](../assets/img2img/000032.step-0.png) | ![step-0](../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) |
| | strength = 0.7 | strength = 0.4 |
| -- | -- | -- |
| 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) |
Both of the outputs look kind of like what I was thinking of. With the strength
higher, my input becomes more vague, _and_ Stable Diffusion has more steps to
refine its output. But it's not really making what I want, which is a picture of
cheery open fire. With the strength lower, my input is more clear, _but_ Stable
Diffusion has less chance to refine itself, so the result ends up inheriting all
the problems of my bad drawing.
Both of the outputs look kind of like what I was thinking of. With the strength higher, my input becomes more vague, *and* Stable Diffusion has more steps to refine its output. But it's not really making what I want, which is a picture of cheery open fire. With the strength lower, my input is more clear, *but* Stable Diffusion has less chance to refine itself, so the result ends up inheriting all the problems of my bad drawing.
If you want to try this out yourself, all of these are using a seed of
`1592514025` with a width/height of `384`, step count `10`, the default sampler
(`k_lms`), and the single-word prompt `"fire"`:
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
After putting this guide together I was curious to see how the difference would
be if I increased the step count to compensate, so that SD could have the same
amount of steps to develop the image regardless of the strength. So I ran the
generation again using the same seed, but this time adapting the step count to
give each generation 20 steps.
After putting this guide together I was curious to see how the difference would be if I increased the step count to compensate, so that SD could have the same amount of steps to develop the image regardless of the strength. So I ran the generation again using the same seed, but this time adapting the step count to give each generation 20 steps.
Here's strength `0.4` (note step count `50`, which is `20 ÷ 0.4` to make sure SD
does `20` steps from my image):
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
```
@@ -179,8 +140,7 @@ invoke> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
![000035.1592514025](../assets/img2img/000035.1592514025.png)
</figure>
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):
and here is strength `0.7` (note step count `30`, which is roughly `20 ÷ 0.7` to make sure SD does `20` steps from my image):
```commandline
invoke> "fire" -s30 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.7
@@ -190,11 +150,7 @@ invoke> "fire" -s30 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.7
![000046.1592514025](../assets/img2img/000046.1592514025.png)
</figure>
In both cases the image is nice and clean and "finished", but because at
strength `0.7` Stable Diffusion has been give so much more freedom to improve on
my badly-drawn flames, they've come out looking much better. You can really see
the difference when looking at the latent steps. There's more noise on the first
image with strength `0.7`:
In both cases the image is nice and clean and "finished", but because at strength `0.7` Stable Diffusion has been give so much more freedom to improve on my badly-drawn flames, they've come out looking much better. You can really see the difference when looking at the latent steps. There's more noise on the first image with strength `0.7`:
<figure markdown>
![gravity46](../assets/img2img/000046.steps.gravity.png)
@@ -206,19 +162,15 @@ than there is for strength `0.4`:
![gravity35](../assets/img2img/000035.steps.gravity.png)
</figure>
and that extra noise gives the algorithm more choices when it is evaluating how
to denoise any particular pixel in the image.
and that extra noise gives the algorithm more choices when it is evaluating how to denoise any particular pixel in the image.
Unfortunately, it seems that `img2img` is very sensitive to the step count.
Here's strength `0.7` with a step count of `29` (SD did 19 steps from my image):
Unfortunately, it seems that `img2img` is very sensitive to the step count. Here's strength `0.7` with a step count of `29` (SD did 19 steps from my image):
<figure markdown>
![gravity45](../assets/img2img/000045.1592514025.png)
</figure>
By comparing the latents we can sort of see that something got interpreted
differently enough on the third or fourth step to lead to a rather different
interpretation of the flames.
By comparing the latents we can sort of see that something got interpreted differently enough on the third or fourth step to lead to a rather different interpretation of the flames.
<figure markdown>
![gravity46](../assets/img2img/000046.steps.gravity.png)
@@ -228,9 +180,4 @@ interpretation of the flames.
![gravity45](../assets/img2img/000045.steps.gravity.png)
</figure>
This is the result of a difference in the de-noising "schedule" - basically the
noise has to be cleaned by a certain degree each step or the model won't
"converge" on the image properly (see
[stable diffusion blog](https://huggingface.co/blog/stable_diffusion) for more
about that). A different step count means a different schedule, which means
things get interpreted slightly differently at every step.
This is the result of a difference in the de-noising "schedule" - basically the noise has to be cleaned by a certain degree each step or the model won't "converge" on the image properly (see [stable diffusion blog](https://huggingface.co/blog/stable_diffusion) for more about that). A different step count means a different schedule, which means things get interpreted slightly differently at every step.

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