https://huggingface.co/spaces/YupengZhou/StoryDiffusion
StoryDiffusion can create a story by generating consistent images and videos.
Consistent self-attention for character-consistent image generation over long-range sequences.
At least 3 text prompts for the consistent self-attention module needed. At least 5 – 6 text prompts recommend for better layout arrangement.
https://github.com/HVision-NKU/StoryDiffusion
