Stable Diffusion web UI for Intel Arc with Intel Extension for Pytorch

This version is a little buggy, if you are a Windows user you can try the DirectML version here or here. 中文自述文件戳这里

Requirements

• Linux 64 bit / WSL2
• You should follow the Intel Installation Guide to complete the installation of IPEX. Or consult ArcNotes.txt.
• Intel Arc A770/A750
• Python 3.10

A simple guide to install Intel Packages

0. Upgrade WSLg

If you are using WSL2, then you first need to run in powershell

wsl --update

1. Install Intel® oneAPI Base Toolkit

You only need to install Intel® oneAPI DPC++ Compiler (DPCPP_ROOT as its installation path) And Intel® oneAPI Math Kernel Library (oneMKL) (MKL_ROOT as its installation path)

wget https://registrationcenter-download.intel.com/akdlm/irc_nas/19079/l_BaseKit_p_2023.0.0.25537.sh
sudo sh ./l_BaseKit_p_2023.0.0.25537.sh

Default installation location {ONEAPI_ROOT} is /opt/intel/oneapi for root account, ${HOME}/intel/oneapi for other accounts. Generally, DPCPP_ROOT is {ONEAPI_ROOT}/compiler/latest, MKL_ROOT is {ONEAPI_ROOT}/mkl/latest. (Required below before each start-up.)

source /opt/intel/oneapi/setvars.sh

2. Install run-time packages

(Some users have reported that these packages are too old in the apt repository, so please use the manual installation.)
sudo apt install intel-opencl-icd intel-level-zero-gpu level-zero intel-media-va-driver-non-free libmfx1
Or you can do this:

mkdir neo
cd neo
wget https://github.com/intel/intel-graphics-compiler/releases/download/igc-1.0.12504.5/intel-igc-core_1.0.12504.5_amd64.deb
wget https://github.com/intel/intel-graphics-compiler/releases/download/igc-1.0.12504.5/intel-igc-opencl_1.0.12504.5_amd64.deb
wget https://github.com/intel/compute-runtime/releases/download/22.43.24595.30/intel-level-zero-gpu-dbgsym_1.3.24595.30_amd64.ddeb
wget https://github.com/intel/compute-runtime/releases/download/22.43.24595.30/intel-level-zero-gpu_1.3.24595.30_amd64.deb
wget https://github.com/intel/compute-runtime/releases/download/22.43.24595.30/intel-opencl-icd-dbgsym_22.43.24595.30_amd64.ddeb
wget https://github.com/intel/compute-runtime/releases/download/22.43.24595.30/intel-opencl-icd_22.43.24595.30_amd64.deb
wget https://github.com/intel/compute-runtime/releases/download/22.43.24595.30/libigdgmm12_22.3.0_amd64.deb
sudo dpkg -i *.deb
cd ..

3. verify GPU visibility with sycl-ls

sycl-ls

[opencl:acc:0] Intel(R) FPGA Emulation Platform for OpenCL(TM), Intel(R) FPGA Emulation Device 1.2 [2022.15.12.0.01_081451]
[opencl:cpu:1] Intel(R) OpenCL, Intel(R) Core(TM) i5-9600KF CPU @ 3.70GHz 3.0 [2022.15.12.0.01_081451]
[opencl:gpu:2] Intel(R) OpenCL HD Graphics, Intel(R) Graphics [0x56a0] 3.0 [22.43.24595.30]
[ext_oneapi_level_zero:gpu:0] Intel(R) Level-Zero, Intel(R) Graphics [0x56a0] 1.3 [1.3.24595]     <----- Check if this exists.

Setup

• Just run webui.sh
• Please verify that the Intel version (rather than +cu117) of Pytorch was installed when you ran the previous step.
• Put your models in /home/<your username>/stable-diffusion-webui/models/Stable-diffusion
• Once configured, you should stop webui.sh and copy & paste this repository to /home/<your username>/stable-diffusion-webui, overwriting its contents. (Or you can modify the installation location in webui.sh. Also, you can just put this repository in that location before everything starts.）
• Run again webui.sh and enjoy it!

Test

25 seconds on Intel Arc A770 16GB with anything-v4.0 for 150 steps.

Known Issues

• When a black screen or other phenomenon occurs, please add: --skip-torch-cuda-test --disable-nan-check in webui-user.sh
• Or just try more.
• Positive prompt please greater than 75 words.
• The number of inference steps should be greater than 50 steps or even more.

Readme of the Original Version

A browser interface based on Gradio library for Stable Diffusion.

Features

Detailed feature showcase with images:

• Original txt2img and img2img modes
• One click install and run script (but you still must install python and git)
• Outpainting
• Inpainting
• Color Sketch
• Prompt Matrix
• Stable Diffusion Upscale
• Attention, specify parts of text that the model should pay more attention to
  • a man in a ((tuxedo)) - will pay more attention to tuxedo
  • a man in a (tuxedo:1.21) - alternative syntax
  • select text and press ctrl+up or ctrl+down to automatically adjust attention to selected text (code contributed by anonymous user)
• Loopback, run img2img processing multiple times
• X/Y/Z plot, a way to draw a 3 dimensional plot of images with different parameters
• Textual Inversion
  • have as many embeddings as you want and use any names you like for them
  • use multiple embeddings with different numbers of vectors per token
  • works with half precision floating point numbers
  • train embeddings on 8GB (also reports of 6GB working)
• Extras tab with:
  • GFPGAN, neural network that fixes faces
  • CodeFormer, face restoration tool as an alternative to GFPGAN
  • RealESRGAN, neural network upscaler
  • ESRGAN, neural network upscaler with a lot of third party models
  • SwinIR and Swin2SR(see here), neural network upscalers
  • LDSR, Latent diffusion super resolution upscaling
• Resizing aspect ratio options
• Sampling method selection
  • Adjust sampler eta values (noise multiplier)
  • More advanced noise setting options
• Interrupt processing at any time
• 4GB video card support (also reports of 2GB working)
• Correct seeds for batches
• Live prompt token length validation
• Generation parameters
  • parameters you used to generate images are saved with that image
  • in PNG chunks for PNG, in EXIF for JPEG
  • can drag the image to PNG info tab to restore generation parameters and automatically copy them into UI
  • can be disabled in settings
  • drag and drop an image/text-parameters to promptbox
• Read Generation Parameters Button, loads parameters in promptbox to UI
• Settings page
• Running arbitrary python code from UI (must run with --allow-code to enable)
• Mouseover hints for most UI elements
• Possible to change defaults/mix/max/step values for UI elements via text config
• Tiling support, a checkbox to create images that can be tiled like textures
• Progress bar and live image generation preview
  • Can use a separate neural network to produce previews with almost none VRAM or compute requirement
• Negative prompt, an extra text field that allows you to list what you don't want to see in generated image
• Styles, a way to save part of prompt and easily apply them via dropdown later
• Variations, a way to generate same image but with tiny differences
• Seed resizing, a way to generate same image but at slightly different resolution
• CLIP interrogator, a button that tries to guess prompt from an image
• Prompt Editing, a way to change prompt mid-generation, say to start making a watermelon and switch to anime girl midway
• Batch Processing, process a group of files using img2img
• Img2img Alternative, reverse Euler method of cross attention control
• Highres Fix, a convenience option to produce high resolution pictures in one click without usual distortions
• Reloading checkpoints on the fly
• Checkpoint Merger, a tab that allows you to merge up to 3 checkpoints into one
• Custom scripts with many extensions from community
• Composable-Diffusion, a way to use multiple prompts at once
  • separate prompts using uppercase AND
  • also supports weights for prompts: a cat :1.2 AND a dog AND a penguin :2.2
• No token limit for prompts (original stable diffusion lets you use up to 75 tokens)
• DeepDanbooru integration, creates danbooru style tags for anime prompts
• xformers, major speed increase for select cards: (add --xformers to commandline args)
• via extension: History tab: view, direct and delete images conveniently within the UI
• Generate forever option
• Training tab
  • hypernetworks and embeddings options
  • Preprocessing images: cropping, mirroring, autotagging using BLIP or deepdanbooru (for anime)
• Clip skip
• Hypernetworks
• Loras (same as Hypernetworks but more pretty)
• A sparate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt.
• Can select to load a different VAE from settings screen
• Estimated completion time in progress bar
• API
• Support for dedicated inpainting model by RunwayML.
• via extension: Aesthetic Gradients, a way to generate images with a specific aesthetic by using clip images embeds (implementation of https://github.com/vicgalle/stable-diffusion-aesthetic-gradients)
• Stable Diffusion 2.0 support - see wiki for instructions
• Alt-Diffusion support - see wiki for instructions
• Now without any bad letters!
• Load checkpoints in safetensors format
• Eased resolution restriction: generated image's domension must be a multiple of 8 rather than 64
• Now with a license!
• Reorder elements in the UI from settings screen

Installation and Running

Make sure the required dependencies are met and follow the instructions available for both NVidia (recommended) and AMD GPUs.

Alternatively, use online services (like Google Colab):

• List of Online Services

Automatic Installation on Windows

1. Install Python 3.10.6, checking "Add Python to PATH"
2. Install git.
3. Download the stable-diffusion-webui repository, for example by running git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git.
4. Place stable diffusion checkpoint (model.ckpt) in the models/Stable-diffusion directory (see dependencies for where to get it).
5. Run webui-user.bat from Windows Explorer as normal, non-administrator, user.

Automatic Installation on Linux

1. Install the dependencies:

# Debian-based:
sudo apt install wget git python3 python3-venv
# Red Hat-based:
sudo dnf install wget git python3
# Arch-based:
sudo pacman -S wget git python3

2. To install in /home/$(whoami)/stable-diffusion-webui/, run:

bash <(wget -qO- https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh)

Installation on Apple Silicon

Find the instructions here.

Contributing

Here's how to add code to this repo: Contributing

Documentation

The documentation was moved from this README over to the project's wiki.

Credits

Licenses for borrowed code can be found in Settings -> Licenses screen, and also in html/licenses.html file.

• Stable Diffusion - https://github.com/CompVis/stable-diffusion, https://github.com/CompVis/taming-transformers
• k-diffusion - https://github.com/crowsonkb/k-diffusion.git
• GFPGAN - https://github.com/TencentARC/GFPGAN.git
• CodeFormer - https://github.com/sczhou/CodeFormer
• ESRGAN - https://github.com/xinntao/ESRGAN
• SwinIR - https://github.com/JingyunLiang/SwinIR
• Swin2SR - https://github.com/mv-lab/swin2sr
• LDSR - https://github.com/Hafiidz/latent-diffusion
• MiDaS - https://github.com/isl-org/MiDaS
• Ideas for optimizations - https://github.com/basujindal/stable-diffusion
• Cross Attention layer optimization - Doggettx - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing.
• Cross Attention layer optimization - InvokeAI, lstein - https://github.com/invoke-ai/InvokeAI (originally http://github.com/lstein/stable-diffusion)
• Sub-quadratic Cross Attention layer optimization - Alex Birch (Birch-san/diffusers#1), Amin Rezaei (https://github.com/AminRezaei0x443/memory-efficient-attention)
• Textual Inversion - Rinon Gal - https://github.com/rinongal/textual_inversion (we're not using his code, but we are using his ideas).
• Idea for SD upscale - https://github.com/jquesnelle/txt2imghd
• Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot
• CLIP interrogator idea and borrowing some code - https://github.com/pharmapsychotic/clip-interrogator
• Idea for Composable Diffusion - https://github.com/energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch
• xformers - https://github.com/facebookresearch/xformers
• DeepDanbooru - interrogator for anime diffusers https://github.com/KichangKim/DeepDanbooru
• Sampling in float32 precision from a float16 UNet - marunine for the idea, Birch-san for the example Diffusers implementation (https://github.com/Birch-san/diffusers-play/tree/92feee6)
• Instruct pix2pix - Tim Brooks (star), Aleksander Holynski (star), Alexei A. Efros (no star) - https://github.com/timothybrooks/instruct-pix2pix
• Security advice - RyotaK
• Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
• (You)