vladmandic/sdnext

vladmandic/sdnext has 7,380 GitHub stars and 581 forks. GitHot measured +1 stars in 24 hours and +9 in 7 days. Last checked 2026-11-14 01:32 UTC. Last push 2026-11-13.

这些数字如何统计

7,380 星标 581 复刻 +1 24小时

可以做什么

Generate and edit: Create images or videos from text or images; edit, inpaint, outpaint, refine, detail
Guide generation: Use LoRA, ControlNet, IP-Adapters, and Prompt enhancement
Enhance and process: Caption, Tag, Upscale, Interpolate, Colorize, and adjust images
Work with models: Browse supported models, auto-download from the reference list, or add your own; added models are detected automatically

实测星标增长

24小时: +1
7天: +9
15天: 正在收集历史
1个月: 正在收集历史

各周期内的星标净变化，周期相互重叠，并非每日新增。缺失的测量保持空白。星标代表关注度，不代表软件质量。

关于

SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing

机器学习

README.md

原文

SD.Next

SD.Next is a state-of-the-art open-source web interface for generating and editing images and video with a wide range of diffusion models. Run it on a variety of NVIDIA, AMD, Intel, Apple Silicon, or CPU setups.

Quick links

What you can do

Generate and edit: Create images or videos from text or images; edit, inpaint, outpaint, refine, detail
Guide generation: Use LoRA, ControlNet, IP-Adapters, and Prompt enhancement
Enhance and process: Caption, Tag, Upscale, Interpolate, Colorize, and adjust images
Work with models: Browse supported models, auto-download from the reference list, or add your own; added models are detected automatically
Tune for your hardware: Use SDNQ quantization and attention and CPU/GPU offloading to manage memory
Make it yours: Choose from multiple themes and interface languages, on desktop or mobile
Stay current: The built-in installer manages dependencies and updates

See supported workflows and platform guides for more details.

Screenshots & Video

Supported Workflows

Generate: Text-to-image, image-to-image, text-to-video, and image-to-video.
Edit: Image editing, inpainting, outpainting, detailer, and hires/refine.
Guide: LoRA, ControlNet, IP-Adapters, and prompt enhancement.
Process: Captioning, tagging, upscaling, interpolation, colorization, and filters.
Queue: Schedule tasks or add them to the queue.
Extend workflows with custom scripts and extensions.

Supported AI Models

SD.Next supports a broad and regularly updated range of models. See the supported models and model specifications.

Supported Platforms and Hardware

SD.Next supports a range of hardware, with GPU acceleration and CPU-only execution. Supported platforms include:

nVidia GPUs using CUDA libraries on both Windows and Linux
AMD GPUs using ROCm libraries on both Linux and Windows
AMD GPUs on Windows using ZLUDA libraries
Intel Arc GPUs using OneAPI with IPEX XPU libraries on both Windows and Linux
Any CPU/GPU or device compatible with OpenVINO libraries on both Windows and Linux
Apple M1/M2 on OSX using built-in support in Torch with MPS optimizations

Plus Docker container recipes for: CUDA, ROCm, Intel IPEX and OpenVINO

Getting started

Follow the installation guide for prerequisites and platform-specific setup. For advanced options, see advanced installation and command-line arguments. There is also an installation walkthrough.

[!TIP] For platform-specific instructions, see:
nVidia CUDA | AMD ROCm | Intel Arc XPU | OpenVINO | ZLUDA | MacOS | WSL | Docker

Quick start

[!NOTE] First launch may take time while dependencies are installed
If you run into issues, see troubleshooting and debugging.

Linux or macOS

git clone https://github.com/vladmandic/sdnext
cd sdnext
./webui.sh

Windows Command Prompt

git clone https://github.com/vladmandic/sdnext
cd sdnext
webui.bat (for Windows Command Prompt)
webui.ps1 (for Windows PowerShell)

Windows All-in-One UI

Download the latest exe from SD.Next Launcher Releases - And run it!

[!TIP] The All-in-One UI includes all necessary tools, so you don't need to install anything separately.

Community and Support

Start with the documentation. For feature history and release notes, see the changelog. Ask questions on Discord or GitHub Discussions; report bugs through GitHub Issues.