StableV2V: Stablizing Shape Consistency in Video-to-Video Editing

submited by

Style Pass

2024-11-22 15:00:06

[2024 Nov. 21th] We have updated the Gradio demo at our GitHub repository. Feel free to try it out following the instructions in our document! [2024 Nov. 20th] We have updated DAVIS-Edit at our HuggingFace dataset repo, and uploaded all the required model weights of StableV2V at our HuggingFace model repo. [2024 Nov. 19th] Our arXiv paper is released. [2024 Nov. 18th] We update the codebase of StableV2V at our GitHub repository. [2024 Nov. 17th] Project page of StableV2V is updated.

StableV2V presents a novel paradigm to perform video editing in a shape-consistent manner, especially handling the editing scenarios when user prompts cause significant shape changes to the edited contents.

Besides, StableV2V shows superior flexibility in handling a wide series of down-stream applications, considering various user prompts from different modalities.