SD.Next

Stable Diffusion implementation with advanced features

Wiki | Discord | Changelog

This project started as a fork from Automatic1111 WebUI and it grew significantly since then,
but although it diverged considerably, any substantial features to original work is ported to this repository as well.

Top-10 Features

All Individual features are not listed here, instead check ChangeLog for full list of changes.

Optimized processing with latest torch developments
Including built-in support for torch.compile
Support for multiple backends!
original and diffusers
Support for multiple diffusion models!
Stable Diffusion, SD-XL, Kandinsky, DeepFloyd IF, etc.
Fully multiplatform with platform specific autodetection and tuning performed on install
Windows / Linux / MacOS with CPU / nVidia / AMD / IntelArc / DirectML
Improved prompt parser
Enhanced Lora/Locon/Lyco code supporting latest trends in training
Built-in queue management
Advanced metadata caching and handling to speed up operations
Enterprise level logging and hardened API
Modern localization and hints engine
Broad compatibility with extisting extensions ecosystem and new extensions manager
Built in installer with automatic updates and dependency management
Modernized UI (still based on Gradio) with theme support

Backend support

SD.Next supports two main backends: Original and Diffusers which can be switched on-the-fly:

Original: Based on LDM reference implementation and significantly expanded on by A1111
This is the default backend and it is fully compatible with all existing functionality and extensions
Diffusers: Based on new Huggingface Diffusers implementation
It is also the only backend that supports Stable Diffusion XL model
Support for legacy workflows and extensions is limited, but its being expanded
See wiki article for more information

Model support

Additional models will be added as they become available and there is public interest in them

Stable Diffusion 1.x and 2.x including all variants
Stable Diffusion XL
Kandinsky 2.1
DeepFloyd IF
UniDiffusion

Platform support

nVidia GPUs using CUDA libraries on both Windows and Linux
AMD GPUs using ROCm libraries on Linux.
Support will be extended to Windows once AMD releases ROCm for Windows
Any GPU compatibile with DirectX on Windows using DirectML libraries.
This includes support for AMD GPUs that are not supported by native ROCm libraries
Intel Arc GPUs using Intel OneAPI Ipex/XPU libraries
Apple M1/M2 on OSX using built-in support in Torch with MPS optimizations

Install

Install first:
Python & Git
Clone repository
git clone https://github.com/vladmandic/automatic
Run launcher
webui.bat or webui.sh:
- Platform specific wrapper scripts For Windows, Linux and OSX
- Starts launch.py in a Python virtual environment (venv)
- Uses install.py to handle all actual requirements and dependencies

Common Problems

Installation Notes

Server can run without virtual environment,
but it is recommended to use it to avoid library version conflicts with other applications
nVidia/CUDA and AMD/ROCm are auto-detected is present and available,
but for any other use case specify required parameter explicitly or wrong packages may be installed
as installer will assume CPU-only environment
Full startup sequence is logged in sdnext.log, so if you encounter any issues, please check it first

Below is partial list of all available parameters, run webui --help for the full list:

Setup options:
  --use-ipex                       Use Intel OneAPI XPU backend, default: False
  --use-directml                   Use DirectML if no compatible GPU is detected, default: False
  --use-cuda                       Force use nVidia CUDA backend, default: False
  --use-rocm                       Force use AMD ROCm backend, default: False
  --skip-update                    Skip update of extensions and submodules, default: False
  --skip-requirements              Skips checking and installing requirements, default: False
  --skip-extensions                Skips running individual extension installers, default: False
  --skip-git                       Skips running all GIT operations, default: False
  --skip-torch                     Skips running Torch checks, default: False
  --reinstall                      Force reinstallation of all requirements, default: False
  --debug                          Run installer with debug logging, default: False
  --reset                          Reset main repository to latest version, default: False
  --upgrade                        Upgrade main repository to latest version, default: False
  --safe                           Run in safe mode with no user extensions

Notes

Extensions

SD.Next comes with several extensions pre-installed:

Collab

To avoid having this repo rely just on me, I'd love to have additional maintainers with full admin rights. If you're interested, ping me!
In addition to general cross-platform code, desire is to have a lead for each of the main platforms. This should be fully cross-platform, but I would really love to have additional contibutors and/or maintainers to join and help lead the efforts on different platforms.

Goals

The idea behind the fork is to enable latest technologies and advances in text-to-image generation.

Sometimes this is not the same as "as simple as possible to use".

If you are looking an amazing simple-to-use Stable Diffusion tool, I'd suggest InvokeAI specifically due to its automated installer and ease of use.

General goals:

Cross-platform
- Create uniform experience while automatically managing any platform specific differences
Performance
- Enable best possible performance on all platforms
Ease-of-Use
- Automatically handle all requirements, dependencies, flags regardless of platform
- Integrate all best options for uniform out-of-the-box experience without the need to tweak anything manually
Look-and-Feel
- Create modern, intuitive and clean UI
Up-to-Date
- Keep code up to date with latest advanced in text-to-image generation