DiffSynth Studio is a Diffusion engine. We have restructured architectures including Text Encoder, UNet, VAE, among others, maintaining compatibility with models from the open-source community while enhancing computational performance. We provide many interesting features. Enjoy the magic of Diffusion models!
DiffSynth Studio 是一个扩散引擎。我们重构了文本编码器、UNet、VAE等架构，保持与开源社区模型的兼容性，同时增强计算性能。我们提供许多有趣的功能。享受扩散模型的魔力！
Until now, DiffSynth Studio has supported the following models:
到目前为止，DiffSynth Studio已经支持以下模型：
- ExVideo
- Stable Video Diffusion 稳定的视频扩散
- Hunyuan-DiT 浑源-DiT
- RIFE
- ESRGAN
- Ip-Adapter IP适配器
- AnimateDiff 动画差异
- ControlNet 控制网
- Stable Diffusion XL 稳定扩散XL
- Stable Diffusion 稳定扩散