In DiffSynth Studio, we can use AnimateDiff and SVD to generate videos. However, these models usually generate terrible contents. We do not recommend users to use these models, until a more powerful video model emerges.

Example 7: Text to Video

Generate a video using a Stable Diffusion model and an AnimateDiff model. We can break the limitation of number of frames! See sd_text_to_video.py.

https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/8f556355-4079-4445-9b48-e9da77699437