Instruction-based video editing is commonly built on video-pretrained generative backbones: a video diffusion transformer is adapted, at considerable cost, to condition on a source video and an editing instruction. In this report we explore a different route and show that a strong instruction-based image editing model...
Yun-Peng Bai, Yossi Gandelsman, Michael Gharbi et al.· 3 citations
The proposed DuSPiT uses a compact base branch for efficient global reasoning and a parallel, high-capacity pixel branch, organized into subpatch groups, to preserve detailed appearance, with the two branches interacting through cross-attention.
Yunpeng Bai, Yossi Gandelsman, Michael Gharbi· arXiv.org· 0 citations
This work revisits the role of positional encoding in video diffusion transformers and shows that it provides a useful spatial bias for geometry-aware control, and introduces a geometry-aware cross-attention mechanism that enables target video latent tokens to attend to structured context tokens derived from reference...
