ZeroHour
Hugging Face daily paperspublished ()ingested Adheesh Sunil Juvekar, Onkar Kishor Susladkar, Kiet A. Nguyen

One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing

infoAI researchimportance 38
AI summary · glm-5.3-flash

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
ProductsEditVid
AI modelsEditVid
Full article104 words · extracted from huggingface.co · click to collapse

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. The same framework supports instruction-guided and reference-guided edits, including style transfer, attribute modification, object insertion, part-level editing, and subject replacement. On FiVE, EditVid achieves 78.16 FiVE-Acc, compared with 58.95 for the strongest evaluated training-free baseline, while obtaining competitive results on IVEBench. A user study further shows a 51.8\% overall preference for EditVid over 7 competing methods.

Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/papers/2609.04190