SD.Next: Advanced Implementation of Stable Diffusion
 
 
 
 
Go to file
Vladimir Mandic 85cf2a81a7 add wiki as submodule 2023-01-15 12:00:37 -05:00
.github Merge pull request #6571 from mezotaken/master 2023-01-09 23:45:49 +03:00
cli add cli 2023-01-14 14:15:47 -05:00
configs decouple from origin 2023-01-05 16:58:00 -05:00
embeddings update 2023-01-08 13:20:44 -05:00
extensions add placeholders 2023-01-06 12:15:25 -05:00
extensions-builtin add cli 2023-01-14 14:15:47 -05:00
html Merge pull request #6055 from brkirch/sub-quad_attn_opt 2023-01-07 12:26:55 +03:00
javascript Fix Aspect Ratio Overlay / AROverlay to work with Inpaint & Sketch 2023-01-14 14:45:08 -08:00
localizations revert exif fix 2023-01-06 11:37:56 -05:00
models update 2023-01-08 13:20:44 -05:00
modules update 2023-01-15 11:56:36 -05:00
outputs add placeholders 2023-01-06 12:15:25 -05:00
q@cf916fd3ad remove 2023-01-15 11:59:30 -05:00
repositories add placeholders 2023-01-06 12:15:25 -05:00
scripts update extensions 2023-01-14 13:06:12 -05:00
test Merge pull request #9 from AUTOMATIC1111/master 2023-01-10 14:53:49 -05:00
train/templates simplyfy filewords 2023-01-11 15:15:30 -05:00
wiki@cf916fd3ad add wiki as submodule 2023-01-15 12:00:37 -05:00
.gitignore update 2023-01-15 11:56:36 -05:00
.gitmodules add wiki as submodule 2023-01-15 12:00:37 -05:00
.pylintrc Add basic Pylint to catch syntax errors on PRs 2022-10-15 16:26:07 +03:00
LICENSE.txt add license file 2023-01-15 09:24:48 +03:00
README.md update 2023-01-15 11:56:36 -05:00
TODO.md update 2023-01-15 11:56:36 -05:00
artists.csv Update artists.csv 2022-10-18 18:11:20 +03:00
automatic.sh update 2023-01-15 11:56:36 -05:00
launch.py Revert detection code 2023-01-14 15:45:07 +01:00
requirements.txt update 2023-01-07 11:10:44 -05:00
requirements_versions.txt update 2023-01-11 13:48:56 -05:00
script.js load hashes from cache for checkpoints that have them 2023-01-14 15:55:40 +03:00
style.css Merge pull request #16 from AUTOMATIC1111/master 2023-01-15 09:39:46 -05:00
ui-config.json update extensions 2023-01-14 13:06:12 -05:00
ui-screenshot.jpg update readme 2023-01-12 11:45:09 -05:00
user.css add extensions 2023-01-09 08:02:38 -05:00
webui.py change hash to sha256 2023-01-14 09:56:59 +03:00
webui.sh update 2023-01-15 09:39:40 -05:00

README.md

Stable Diffusion - Automatic

Heavily opinionated custom fork of https://github.com/AUTOMATIC1111/stable-diffusion-webui


Notes

Fork is as close as up-to-date with origin as time allows
All code changes are merged upstream whenever possible

Fork adds extra functionality:

  • Ships with additional extensions
    e.g. System Info, Steps Animation, etc.
  • Ships with set of CLI tools that rely on SD API for execution:
    e.g. generate, train, bench, etc.
    Full list

Fork does differ in few things:

  • Additional simplified start script

    ./automatic.sh
    Existing webui.sh still exists for fresh installs to auto-install dependencies, etc.

  • Drops compatibility with python 3.7 and requires 3.10
  • Updated Python libraries to latest known compatible versions
    e.g. accelerate, transformers, numpy, etc.
  • Includes opinionated System and Options configuration
    e.g. samplers, upscalers, etc.
  • Includes reskinned UI
    Black and orange dark theme with fixed width options panels and larger previews
  • Includes SD2 configuration files
  • Uses simplified folder structure
    e.g. /train, /outputs/*
  • Modified training templates

Only Python library which is not auto-updated is PyTorch itself as that is very system specific
For some Torch optimizations notes, see Wiki

Fork is compatible with regular PyTorch 1.13 as well as pre-release of PyTorch 2.0
See Wiki for Torch optimization notes


Docs

Everything is in Wiki
Except my current TODO