Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity
698 Commits 274 Branches 239 Tags 397 MiB
TypeScript 59.1%
Python 40.3%
Shell 0.3%
d176fb07cd
Go to file
Mihail Dumitrescu d176fb07cd Replace --full_precision with --precision that works even if not specified 
Allowed values are 'auto', 'float32', 'autocast', 'float16'. If not specified or 'auto' a working precision is automatically selected based on the torch device.
Context: #526
Deprecated --full_precision / -F

Tested on both cuda and cpu by calling scripts/dream.py without arguments and checked the auto configuration worked. With --precision=auto/float32/autocast/float16 it performs as expected, either working or failing with a reasonable error. Also checked Img2Img.
2022-09-20 17:08:00 -04:00
.dev_scripts Replace --full_precision with --precision that works even if not specified 2022-09-20 17:08:00 -04:00
.github Replace --full_precision with --precision that works even if not specified 2022-09-20 17:08:00 -04:00
assets stable diffusion 2022-08-10 16:30:49 +02:00
backend Fixes cascading bugs 2022-09-21 00:44:57 +10:00
configs upped max_steps in v1-finetune.yaml and fixed TI docs to address #493 2022-09-11 16:20:14 -04:00
data stable diffusion 2022-08-10 16:30:49 +02:00
docs Replace --full_precision with --precision that works even if not specified 2022-09-20 17:08:00 -04:00
frontend change WebGUI title to InvokeAI 2022-09-20 16:14:33 -04:00
ldm Replace --full_precision with --precision that works even if not specified 2022-09-20 17:08:00 -04:00
models add configs for training unconditional/class-conditional ldms 2021-12-22 15:57:23 +01:00
notebooks TOIL(pip): Refactor pip requirements across the board (#531) 2022-09-14 07:01:58 -04:00
scripts Replace --full_precision with --precision that works even if not specified 2022-09-20 17:08:00 -04:00
server Replace --full_precision with --precision that works even if not specified 2022-09-20 17:08:00 -04:00
static small legacy web appearance tweaks 2022-09-17 02:44:07 -04:00
tests respect --outdir again; fix issue #628 2022-09-16 19:58:45 -04:00
.gitattributes Update .gitattributes 2022-08-29 16:58:41 -05:00
.gitignore Implement CodeFormer Face Restoration (#669) 2022-09-18 15:01:05 -04:00
.gitmodules remove src directory, which is gumming up conda installs; addresses issue #77 2022-08-25 10:43:05 -04:00
.prettierrc.yaml Mkdocs-material (#575) 2022-09-15 10:53:41 -04:00
environment-mac.yaml Update environment-mac.yaml 2022-09-20 16:38:28 -04:00
environment.yaml Merge remote-tracking branch 'upstream/development' into development 2022-09-18 18:44:40 +10:00
LICENSE added assertion checks for out-of-bound arguments; added various copyright and license agreement files 2022-08-24 09:22:27 -04:00
LICENSE-ModelWeights.txt added assertion checks for out-of-bound arguments; added various copyright and license agreement files 2022-08-24 09:22:27 -04:00
main.py Use cuda only when available in main.py. (#567) 2022-09-15 07:41:24 -04:00
mkdocs.yml Mkdocs-material (#575) 2022-09-15 10:53:41 -04:00
pyproject.toml feat(ci): add pyproject.toml with blue config 2022-09-20 16:27:15 -04:00
README.md Replace --full_precision with --precision that works even if not specified 2022-09-20 17:08:00 -04:00
requirements-lin-AMD.txt TOIL(pip): Refactor pip requirements across the board (#531) 2022-09-14 07:01:58 -04:00
requirements-lin-win-colab-CUDA.txt TOIL(pip): Refactor pip requirements across the board (#531) 2022-09-14 07:01:58 -04:00
requirements-mac-MPS-CPU.txt fix(install): unpinned 'protobuf' breaks macOS installs (#596) 2022-09-16 07:39:23 -04:00
requirements-mkdocs.txt Mkdocs-material (#575) 2022-09-15 10:53:41 -04:00
requirements.txt Support color correction for img2img and inpainting (#613) 2022-09-18 09:47:57 -04:00
setup.py TOIL(pip): Refactor pip requirements across the board (#531) 2022-09-14 07:01:58 -04:00
Stable_Diffusion_v1_Model_Card.md stable diffusion 2022-08-10 16:30:49 +02:00

README.md

Stable Diffusion Dream Script

project logo

Stable Diffusion Dream Script

discord badge

latest release badge github stars badge github forks badge

CI checks on main badge CI checks on dev badge latest commit to dev badge

github open issues badge github open prs badge

This is a fork of CompVis/stable-diffusion, the open source text-to-image generator. It provides a streamlined process with various new features and options to aid the image generation process. It runs on Windows, Mac and Linux machines, and runs on GPU cards with as little as 4 GB or RAM.

Note: This fork is rapidly evolving. Please use the Issues tab to report bugs and make feature requests. Be sure to use the provided templates. They will help aid diagnose issues faster.

Table of Contents

  1. Installation
  2. Hardware Requirements
  3. Features
  4. Latest Changes
  5. Troubleshooting
  6. Contributing
  7. Contributors
  8. Support
  9. Further Reading

Installation

This fork is supported across multiple platforms. You can find individual installation instructions below.

Hardware Requirements

System

You wil need one of the following:

  • An NVIDIA-based graphics card with 4 GB or more VRAM memory.
  • An Apple computer with an M1 chip.

Memory

  • At least 12 GB Main Memory RAM.

Disk

  • At least 6 GB of free disk space for the machine learning model, Python, and all its dependencies.

Note

Precision is auto configured based on the device. If however you encounter errors like 'expected type Float but found Half' or 'not implemented for Half' you can try starting dream.py with the --precision=float32 flag:

(ldm) ~/stable-diffusion$ python scripts/dream.py --precision=float32

Features

Major Features

Other Features

Latest Changes

  • vNEXT (TODO 2022)

    • Deprecated --full_precision / -F. Simply omit it and dream.py will auto configure. To switch away from auto use the new flag like --precision=float32.

  • v1.14 (11 September 2022)

    • Memory optimizations for small-RAM cards. 512x512 now possible on 4 GB GPUs.
    • Full support for Apple hardware with M1 or M2 chips.
    • Add "seamless mode" for circular tiling of image. Generates beautiful effects. (prixt).
    • Inpainting support.
    • Improved web server GUI.
    • Lots of code and documentation cleanups.

  • v1.13 (3 September 2022

    • Support image variations (see VARIATIONS (Kevin Gibbons and many contributors and reviewers)
    • Supports a Google Colab notebook for a standalone server running on Google hardware Arturo Mendivil
    • WebUI supports GFPGAN/ESRGAN facial reconstruction and upscaling Kevin Gibbons
    • WebUI supports incremental display of in-progress images during generation Kevin Gibbons
    • A new configuration file scheme that allows new models (including upcoming stable-diffusion-v1.5) to be added without altering the code. (David Wager)
    • Can specify --grid on dream.py command line as the default.
    • Miscellaneous internal bug and stability fixes.
    • Works on M1 Apple hardware.
    • Multiple bug fixes.

For older changelogs, please visit the CHANGELOG.

Troubleshooting

Please check out our Q&A to get solutions for common installation 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. If you are unfamiliar with how to contribute to GitHub projects, here is a Getting Started Guide.

A full set of contribution guidelines, along with templates, are in progress, but for now the most important thing is to make your pull request against the "development" branch, and not against "main". This will help keep public breakage to a minimum and will allow you to propose more radical changes.

Contributors

This fork is a combined effort of various people from across the world. Check out the list of all these amazing people. We thank them for their time, hard work and effort.

Support

For support, please use this repository's GitHub Issues tracking service. Feel free to send me an email if you use and like the script.

Original portions of the software are Copyright (c) 2020 Lincoln D. Stein

Further Reading

Please see the original README for more information on this software and underlying algorithm, located in the file README-CompViz.md.