Open-source software

Tutorials

Stable Diffusion web UI

  • In
  • Read Time10 mins

Share your love

Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input, cultivates autonomous freedom to produce incredible imagery, empowers billions of people to create stunning art within seconds.

Stable Diffusion is a deep learning model that generates images from text descriptions. The model is considered to be a part of the ongoing AI spring, which refers to the rapid development of artificial intelligence technologies.

Stable Diffusion

Stable Diffusion is a deep learning, text-to-image model released in 2022 based on diffusion techniques. It is considered to be a part of the ongoing AI spring.

It is primarily used to generate detailed images conditioned on text descriptions, though it can also be applied to other tasks such as inpainting, outpainting, and generating image-to-image translations guided by a text prompt.[3] It was developed by researchers from the CompVis Group at Ludwig Maximilian University of Munich and Runway with a compute donation by Stability AI and training data from non-profit organizations.[4][5][6][7]

Stable Diffusion is a latent diffusion model, a kind of deep generative artificial neural network. Its code and model weights have been open sourced,[8] and it can run on most consumer hardware equipped with a modest GPU with at least 4 GB VRAM. This marked a departure from previous proprietary text-to-image models such as DALL-E and Midjourney which were accessible only via cloud services.

What is Web UI?

Web User Interface or “Web UI” refers to all the elements of a website that visitors can interact with. In other words, it’s everything on a website that isn’t the content itself. This includes things like the site navigation, buttons, form elements, and any other interactive element.

A well-designed Web UI is important for a number of reasons. First, it makes your website more user-friendly and easier to navigate. Additionally, a good web interface will also be more visually appealing to users, which can help keep them engaged with your site. Finally, by optimizing your site’s Web UI you can improve its overall performance and loading times, which is crucial for maintaining user interest.

A browser interface based on Gradio library for Stable Diffusion.

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 (or Command+Up or Command+Down if you’re on a MacOS) 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 separate 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 dimensions must be a multiple of 8 rather than 64
  • Now with a license!
  • Reorder elements in the UI from settings screen
  • Segmind Stable Diffusion support

Installation and Running

Make sure the required dependencies are met and follow the instructions available for:

Alternatively, use online services (like Google Colab):

Installation on Windows 10/11 with NVidia-GPUs using release package

  1. Download sd.webui.zip from v1.0.0-pre and extract its contents.
  2. Run update.bat.
  3. Run run.bat.

For more details see Install-and-Run-on-NVidia-GPUs

Automatic Installation on Windows

  1. Install Python 3.10.6 (Newer version of Python does not support torch), 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. 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 libgl1 libglib2.0-0
# Red Hat-based:
sudo dnf install wget git python3 gperftools-libs libglvnd-glx 
# openSUSE-based:
sudo zypper install wget git python3 libtcmalloc4 libglvnd
# Arch-based:
sudo pacman -S wget git python3
  1. Navigate to the directory you would like the webui to be installed and execute the following command:
wget -q https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh
  1. Run webui.sh.
  2. Check webui-user.sh for options.

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.

For the purposes of getting Google and other search engines to crawl the wiki, here’s a link to the (not for humans) crawlable wiki.

Credits

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

Project Address

Tags
Share your love
Thomas Wang
Thomas Wang
Articles: 10

Related Posts

Leave a Reply

Your email address will not be published. Required fields are marked *