Frame In-N-Out: Unbounded Controllable Image-to-Video Generation

Boyang Wang, Xuweiyi Chen, Matheus, Cheng

Frame In-N-Out: Unbounded Controllable Image-to-Video Generation: 16 upvotes on Hugging Face Daily Papers, #25 of 76 papers on 2025-05-28. Day-by-day upvote history.

Controllability, temporal coherence, and detail synthesis remain the most critical challenges in video generation. In this paper, we focus on a commonly used yet underexplored cinematic technique known as Frame In and Frame Out. Specifically, starting from image-to-video generation, users can control the objects in the image to naturally leave the scene or provide breaking new identity references to enter the scene, guided by user-specified motion trajectory. To support this task, we introduce a new dataset curated semi-automatically, a comprehensive evaluation protocol targeting this setting, and an efficient identity-preserving motion-controllable video Diffusion Transformer architecture. Our evaluation shows that our proposed approach significantly outperforms existing baselines.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.