Stable Diffusion web UI
Go to file
2022-09-24 18:26:54 -07:00
.github Update FUNDING.yml 2022-09-22 12:41:59 +01:00
.idea Added gitignore 2022-08-29 00:41:17 +01:00
configs Added missing options on the config file. 2022-09-24 05:14:36 -07:00
data Repo merge (#712) 2022-09-06 23:50:14 +01:00
docs remove old doc files 2022-09-23 00:35:35 +03:00
frontend Fix css (#1303) 2022-09-24 22:58:50 +03:00
images Add NSFW filter to avoid unexpected (#955) 2022-09-11 12:32:36 +03:00
ldm move scale multiplication (#1232) 2022-09-20 02:10:46 +03:00
models Repo merge (#712) 2022-09-06 23:50:14 +01:00
optimizedSD Repo merge (#712) 2022-09-06 23:50:14 +01:00
scripts Merge branch 'dev' into img2img-esrgan-fix 2022-09-24 18:26:54 -07:00
_config.yml dark theme 2022-09-19 01:05:46 +03:00
.dockerignore Audit dependencies and revise Docker environment specification 2022-09-20 00:21:54 -07:00
.env_docker.example Streamline Docker Quickstart Experience (#1261) 2022-09-22 12:46:40 +01:00
.gitattributes Repo merge (#712) 2022-09-06 23:50:14 +01:00
.gitignore Fixed missing frontend/dist folder. 2022-09-20 21:45:16 -07:00
build_docker.sh Streamline Docker Quickstart Experience (#1261) 2022-09-22 12:46:40 +01:00
CONTRIBUTING.md add contribution guide 2022-09-19 01:05:46 +03:00
docker-compose.yml Streamline Docker Quickstart Experience (#1261) 2022-09-22 12:46:40 +01:00
docker-reset.sh Audit dependencies and revise Docker environment specification 2022-09-20 00:21:54 -07:00
Dockerfile Audit dependencies and revise Docker environment specification 2022-09-20 00:21:54 -07:00
entrypoint.sh Audit dependencies and revise Docker environment specification 2022-09-20 00:21:54 -07:00
environment.yaml Upgraded the streamlit dependency to version 1.13.0 2022-09-24 18:09:28 -07:00
ext_requirements.txt Audit dependencies and revise Docker environment specification 2022-09-20 00:21:54 -07:00
LICENSE Create LICENSE 2022-08-29 12:16:23 +01:00
README.md Update README.md 2022-09-22 10:44:11 +01:00
requirements.txt Audit dependencies and revise Docker environment specification 2022-09-20 00:21:54 -07:00
sd_requirements.txt Audit dependencies and revise Docker environment specification 2022-09-20 00:21:54 -07:00
setup.py refactor: sort out dependencies 2022-09-11 04:33:43 +03:00
Stable_Diffusion_v1_Model_Card.md Repo merge (#712) 2022-09-06 23:50:14 +01:00
ui_requirements.txt Audit dependencies and revise Docker environment specification 2022-09-20 00:21:54 -07:00
webui-streamlit.cmd environment update from .cmd 2022-09-16 11:12:15 +01:00
webui.cmd Fixed webui.cmd crash when having () in path. #1276 (#1279) 2022-09-23 10:14:20 +01:00
webui.sh Added ability to auto-download sd concepts repo 2022-09-21 06:06:06 -04:00

Web based UI for Stable Diffusion by sd-webui

Visit sd-webui's Discord Server Discord Server

Installation instructions for Windows, Linux

Want to ask a question or request a feature?

Come to our Discord Server or use Discussions.

Documentation

Documentaion is located here

Want to contribute?

Check the Contribution Guide

sd-webui is

Gradio

Features

Screenshots

Streamlit

Features

Screenshots


Stable Diffusion was made possible thanks to a collaboration with Stability AI and Runway and builds upon our previous work:

High-Resolution Image Synthesis with Latent Diffusion Models
Robin Rombach*, Andreas Blattmann*, Dominik Lorenz, Patrick Esser, Björn Ommer

CVPR '22 Oral

which is available on GitHub. PDF at arXiv. Please also visit our Project page.

Stable Diffusion is a latent text-to-image diffusion model. Thanks to a generous compute donation from Stability AI and support from LAION, we were able to train a Latent Diffusion Model on 512x512 images from a subset of the LAION-5B database. Similar to Google's Imagen, this model uses a frozen CLIP ViT-L/14 text encoder to condition the model on text prompts. With its 860M UNet and 123M text encoder, the model is relatively lightweight and runs on a GPU with at least 10GB VRAM. See this section below and the model card.

Stable Diffusion v1 refers to a specific configuration of the model architecture that uses a downsampling-factor 8 autoencoder with an 860M UNet and CLIP ViT-L/14 text encoder for the diffusion model. The model was pretrained on 256x256 images and then finetuned on 512x512 images.

*Note: Stable Diffusion v1 is a general text-to-image diffusion model and therefore mirrors biases and (mis-)conceptions that are present in its training data. Details on the training procedure and data, as well as the intended use of the model can be found in the corresponding model card.

BibTeX

@misc{rombach2021highresolution,
      title={High-Resolution Image Synthesis with Latent Diffusion Models}, 
      author={Robin Rombach and Andreas Blattmann and Dominik Lorenz and Patrick Esser and Björn Ommer},
      year={2021},
      eprint={2112.10752},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}