SD.Next
All-in-one WebUI supporting dozens of diffusion models and every GPU backend.
- Star 数
- 7.4K
- Fork 数
- 584
- 未关闭 Issue
- 59
- 最近提交
- 2026-10-14
数据来自 GitHub API · 更新于 2026-10-15
SD.Next 是什么?
SD.Next began as a fork of the A1111 WebUI and grew into a separate project built on Diffusers. It supports a very wide range of image and video models and backends — CUDA, ROCm, Intel IPEX, DirectML, OpenVINO and Apple MPS — with a modern UI.
主要功能
- Supports many model families via Diffusers
- Broad hardware support including Intel Arc and AMD on Windows
- Built-in model downloader and queue
- Extensive documentation wiki
系统要求
- 平台
- Windows · Linux · macOS · Docker
- 显卡
- NVIDIA, AMD, Intel Arc, Apple Silicon or CPU (OpenVINO)
- 显存
- 4 GB+ depending on model
- 内存
- 16 GB+
如何安装 SD.Next
根据项目 README 整理。开源项目更新很快,请以 GitHub 页面上的最新说明为准。
All platforms
- 1Clone the repository.
git clone https://github.com/vladmandic/sdnext cd sdnext - 2Run webui.bat (Windows) or ./webui.sh (Linux/macOS). Add --debug to see detailed setup logs.
优势
- Widest hardware support
- Fast model adoption
- Active development
不足
- Many options can overwhelm beginners
- Smaller community than A1111/ComfyUI
SD.Next 替代品对比
| 软件 | Star 数 | 许可证 | 平台 | 显存 |
|---|---|---|---|---|
| SD.Next All-in-one WebUI supporting dozens of diffusion models and every GPU backend. | 7.4K | Apache-2.0 | 4 GB+ depending on model | |
| Stable Diffusion WebUI Forge A faster, leaner fork of the A1111 WebUI with FLUX support. | 13.1K | AGPL-3.0 | 6 GB+ (FLUX NF4/GGUF variants run on 6–8 GB) | |
| ComfyUI Node-based interface for diffusion models — images, video and audio. | 137.6K | GPL-3.0 | 4 GB minimum for SD1.5; 12 GB+ recommended for FLUX and video models | |
| Stable Diffusion WebUI (AUTOMATIC1111) The classic browser UI for Stable Diffusion with a massive extension ecosystem. | 165.1K | AGPL-3.0 | 4 GB minimum (with --medvram/--lowvram), 8 GB+ recommended | |
| Fooocus Midjourney-like simplicity for SDXL: type a prompt and press Generate. | 53.4K | GPL-3.0 | 4 GB minimum, 6 GB+ recommended | |
| InvokeAI Professional creative engine with a unified canvas for Stable Diffusion and FLUX. | 28.6K | Apache-2.0 | 4 GB for SD1.5, 8 GB for SDXL, 10 GB+ for FLUX |
相关模型
常见问题
SD.Next 免费吗?
是的——SD.Next 是开源软件,采用 Apache-2.0 许可证。商用前请确认软件及模型权重的许可条款。
SD.Next 支持 Windows、Mac 和 Linux 吗?
SD.Next 支持:Windows, Linux, macOS, Docker。
运行 SD.Next 需要什么配置?
NVIDIA, AMD, Intel Arc, Apple Silicon or CPU (OpenVINO). VRAM: 4 GB+ depending on model. RAM: 16 GB+
如何安装 SD.Next?
1. Clone the repository. 2. Run webui.bat (Windows) or ./webui.sh (Linux/macOS). Add --debug to see detailed setup logs.
SD.Next 有哪些好的替代品?
常见替代品包括 Stable Diffusion WebUI Forge, ComfyUI, Stable Diffusion WebUI (AUTOMATIC1111), Fooocus,详见本页对比表。
可以不安装、在线使用 SD.Next 吗?
如果只想要结果,AiLoft 可在浏览器中运行 GPT Image 2.5、Nano Banana Pro 等顶级图像模型,无需显卡和配置。
不想安装?直接在浏览器里生成图片
无需显卡、驱动或 Python。在线使用 GPT Image 2.5 和 Nano Banana Pro,并排对比效果。