{"ID":2836458,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.21475","arxiv_id":"2511.21475","title":"MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devices","abstract":"Recently, video generation has witnessed rapid advancements, drawing increasing attention to image-to-video (I2V) synthesis on mobile devices. However, the substantial computational complexity and slow generation speed of diffusion models pose significant challenges for real-time, high-resolution video generation on resource-constrained mobile devices. In this work, we propose MobileI2V, a 270M lightweight diffusion model for real-time image-to-video generation on mobile devices. The core lies in: (1) We analyzed the performance of linear attention modules and softmax attention modules on mobile devices, and proposed a linear hybrid architecture denoiser that balances generation efficiency and quality. (2) We design a time-step distillation strategy that compresses the I2V sampling steps from more than 20 to only two without significant quality loss, resulting in a 10-fold increase in generation speed. (3) We apply mobile-specific attention optimizations that yield a 2-fold speed-up for attention operations during on-device inference. MobileI2V enables, for the first time, fast 720p image-to-video generation on mobile devices, with quality comparable to existing models. Under one-step conditions, the generation speed of each frame of 720p video is less than 100 ms. Our code is available at: https://github.com/hustvl/MobileI2V.","short_abstract":"Recently, video generation has witnessed rapid advancements, drawing increasing attention to image-to-video (I2V) synthesis on mobile devices. However, the substantial computational complexity and slow generation speed of diffusion models pose significant challenges for real-time, high-resolution video generation on re...","url_abs":"https://arxiv.org/abs/2511.21475","url_pdf":"https://arxiv.org/pdf/2511.21475v1","authors":"[\"Shuai Zhang\",\"Bao Tang\",\"Siyuan Yu\",\"Yueting Zhu\",\"Jingfeng Yao\",\"Ya Zou\",\"Shanglin Yuan\",\"Li Yu\",\"Wenyu Liu\",\"Xinggang Wang\"]","published":"2025-11-26T15:09:02Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":606601,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2836458,"paper_url":"https://arxiv.org/abs/2511.21475","paper_title":"MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devices","repo_url":"https://github.com/hustvl/MobileI2V","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}