DiffSynth-Studio/examples/ExVideo/README.md

ExVideo

ExVideo is a post-tuning technique aimed at enhancing the capability of video generation models. We have extended Stable Video Diffusion to achieve the generation of long videos up to 128 frames.

• Project Page
• Source Code
• Technical report
• Extended models
  • HuggingFace
  • ModelScope

Example: Text-to-video via extended Stable Video Diffusion

Generate a video using a text-to-image model and our image-to-video model. See ExVideo_svd.py.

https://github.com/modelscope/DiffSynth-Studio/assets/35051019/d97f6aa9-8064-4b5b-9d49-ed6001bb9acc