2025/04/17 by Lvmin Zhang, Zhang, Lvmin, Shengqu Cai +7 · 34 citations
Computer Science · #Advanced Data Compression Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image and Video Quality Assessment #Video Coding and Compression Technologies
paper · pdf · doi:10.48550/arxiv.2504.12626
openalex publication_date 2025/04/17 · openalex created_date 2025/10/17 · openalex updated_date 2026/07/31
We present a neural network structure, FramePack, to train next-frame (or next-frame-section) prediction models for video generation. FramePack compresses input frame contexts with frame-wise importance so that more frames can be encoded within a fixed context length, with more important frames having longer contexts. The frame importance can be measured using time proximity, feature similarity, or hybrid metrics. The packing method allows for inference with thousands of frames and training with relatively large batch sizes. We also present drift prevention methods to address observation bias (error accumulation), including early-established endpoints, adjusted sampling orders, and discrete history representation. Ablation studies validate the effectiveness of the anti-drifting methods in both single-directional video streaming and bi-directional video generation. Finally, we show that existing video diffusion models can be finetuned with FramePack, and analyze the differences between different packing schedules.