First Frame Is the Place to Go for Video Content Customization

Jingxi Chen, LZX, Zhichao Liu, Guangyao Shi, Xiyang Wu, Fuxiao Liu, Cornelia Fermuller, Brandon Y. Feng, Yiannis Aloimonos

First Frame Is the Place to Go for Video Content Customization: 54 upvotes on Hugging Face Daily Papers, #4 of 22 papers on 2025-11-21. Day-by-day upvote history.

What role does the first frame play in video generation models? Traditionally, it's viewed as the spatial-temporal starting point of a video, merely a seed for subsequent animation. In this work, we reveal a fundamentally different perspective: video models implicitly treat the first frame as a conceptual memory buffer that stores visual entities for later reuse during generation. Leveraging this insight, we show that it's possible to achieve robust and generalized video content customization in diverse scenarios, using only 20-50 training examples without architectural changes or large-scale finetuning. This unveils a powerful, overlooked capability of video generation models for reference-based video customization.

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.