One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing
Researchers introduce EditVid, a training-free video editing framework scoring 78.16 FiVE-Acc versus 58.95 for the strongest comparable baseline.
EditVid is a unified training-free framework for diverse instruction-guided and subject-guided video editing. It combines sparse causal memory for local coherence, correspondence-based post-attention token injection for long-range identity preservation, and soft latent blending for edit locality. On the FiVE benchmark it reaches 78.16 FiVE-Acc against 58.95 for the strongest evaluated training-free baseline, with competitive results on IVEBench. A user study showed 51.8% overall preference for EditVid over 7 competing methods.
- Combines sparse causal memory, post-attention token injection, and soft latent blending
- Scores 78.16 FiVE-Acc versus 58.95 for the best training-free baseline
- Supports style transfer, object insertion, part-level editing, and subject replacement
- User study shows 51.8% preference over 7 competing methods
From the original article
1 min read at huggingface.co
Video editing spans diverse editing paradigms, yet achieving high-quality instruction-guided and subject-guided editing within a single unified framework remains challenging. We introduce EditVid, a training-free framework combining sparse causal memory for local coherence, correspondence-based post-attention token injection for long-range identity preservation, and soft latent blending for edit locality.
By Adheesh Sunil Juvekar, Onkar Kishor Susladkar, Kiet A. Nguyen · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.