Stability AI Generative Models
Stability AI’s reference code for SDXL and Stable Video Diffusion.
- Star 数
- 27.3K
- Fork 数
- 3.1K
- 未关闭 Issue
- 338
- 最近提交
- 2025-12-16
数据来自 GitHub API · 更新于 2026-10-15
Stability AI Generative Models 是什么？
Stability AI’s generative-models repository contains the official sampling and training code for SDXL, SDXL-Turbo, Stable Video Diffusion and related models, with Streamlit demos for local testing.
主要功能
- Reference implementations for SDXL and SVD
- Streamlit sampling demos
- Config-driven training code
系统要求
- 平台
- Linux
- 显卡
- NVIDIA
- 显存
- 16 GB+ (more for video)
如何安装 Stability AI Generative Models
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。
Linux
- 1Clone and install.
git clone https://github.com/Stability-AI/generative-models.git cd generative-models python3 -m venv .pt2 source .pt2/bin/activate pip install -r requirements/pt2.txt pip install . - 2Run the sampling demo described in the README.
streamlit run scripts/demo/sampling.py --server.port <port>
优势
- Official reference code
- Includes video diffusion
不足
- Developer-oriented
- Linux-focused
Stability AI Generative Models 替代品对比
| 软件 | Star 数 | 许可证 | 平台 | 显存 |
|---|---|---|---|---|
| Stability AI Generative Models Stability AI’s reference code for SDXL and Stable Video Diffusion. | 27.3K | MIT | 16 GB+ (more for video) | |
| Diffusers Hugging Face’s Python library for diffusion models. | 34.7K | Apache-2.0 | — | |
| 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 | |
| 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) | |
| Fooocus Midjourney-like simplicity for SDXL: type a prompt and press Generate. | 53.4K | GPL-3.0 | 4 GB minimum, 6 GB+ recommended |
相关模型
常见问题
Stability AI Generative Models 免费吗？
是的——Stability AI Generative Models 是开源软件，采用 MIT 许可证。商用前请确认软件及模型权重的许可条款。
Stability AI Generative Models 支持 Windows、Mac 和 Linux 吗？
Stability AI Generative Models 支持：Linux。
运行 Stability AI Generative Models 需要什么配置？
NVIDIA. VRAM: 16 GB+ (more for video)
如何安装 Stability AI Generative Models？
1. Clone and install. 2. Run the sampling demo described in the README.
Stability AI Generative Models 有哪些好的替代品？
常见替代品包括 Diffusers, ComfyUI, Stable Diffusion WebUI (AUTOMATIC1111), Stable Diffusion WebUI Forge，详见本页对比表。
可以不安装、在线使用 Stability AI Generative Models 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。