This is the official code of the project, Soundini: Sound-Guided Diffusion for Natural Video Editing. Given video, you can modifiy the appearance of video solely based on audio. We leverage two types of the pre-trained models, DDPMs and CLIP (sound-aligned).
kuai-lab/soundini-official
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.