SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device

Yushu Wu, Zhixing Zhang, Yanyu Li, Yanwu Xu, Anil Kag, Yang Sui, Huseyin Coskun, Ke Ma, Aleksei Lebedev, Ju Hu, Dimitris N. Metaxas, Yanzhi Wang, Sergey Tulyakov, Jian Ren; Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), 2025, pp. 2479-2490

Abstract


We have witnessed the unprecedented success of diffusion-based video generation over the past year. Recently proposed models from the community have wielded the power to generate cinematic and high-resolution videos with smooth motions from arbitrary input prompts. However, as a supertask of image generation, video generation models require more computation and are thus hosted mostly on cloud servers, limiting broader adoption among content creators. In this work, we propose a comprehensive acceleration framework to bring the power of the large-scale video diffusion model to the hands of edge users. From the network architecture scope, we initialize from a compact image backbone and search out the design and arrangement of temporal layers to maximize hardware efficiency. In addition, we propose a dedicated adversarial fine-tuning algorithm for our efficient model and reduce the denoising steps to 4. Our model, with only 0.6B parameters, can generate a 5-second video on an iPhone 16 PM within 5 seconds. Compared to server-side models that take minutes on powerful GPUs to generate a single video, we accelerate the generation by magnitudes while delivering on-par quality.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Wu_2025_CVPR, author = {Wu, Yushu and Zhang, Zhixing and Li, Yanyu and Xu, Yanwu and Kag, Anil and Sui, Yang and Coskun, Huseyin and Ma, Ke and Lebedev, Aleksei and Hu, Ju and Metaxas, Dimitris N. and Wang, Yanzhi and Tulyakov, Sergey and Ren, Jian}, title = {SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)}, month = {June}, year = {2025}, pages = {2479-2490} }