{"ID":2879965,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.15761","arxiv_id":"2508.15761","title":"Waver: Wave Your Way to Lifelike Video Generation","abstract":"We present Waver, a high-performance foundation model for unified image and video generation. Waver can directly generate videos with durations ranging from 5 to 10 seconds at a native resolution of 720p, which are subsequently upscaled to 1080p. The model simultaneously supports text-to-video (T2V), image-to-video (I2V), and text-to-image (T2I) generation within a single, integrated framework. We introduce a Hybrid Stream DiT architecture to enhance modality alignment and accelerate training convergence. To ensure training data quality, we establish a comprehensive data curation pipeline and manually annotate and train an MLLM-based video quality model to filter for the highest-quality samples. Furthermore, we provide detailed training and inference recipes to facilitate the generation of high-quality videos. Building on these contributions, Waver excels at capturing complex motion, achieving superior motion amplitude and temporal consistency in video synthesis. Notably, it ranks among the Top 3 on both the T2V and I2V leaderboards at Artificial Analysis (data as of 2025-07-30 10:00 GMT+8), consistently outperforming existing open-source models and matching or surpassing state-of-the-art commercial solutions. We hope this technical report will help the community more efficiently train high-quality video generation models and accelerate progress in video generation technologies. Official page: https://github.com/FoundationVision/Waver.","short_abstract":"We present Waver, a high-performance foundation model for unified image and video generation. Waver can directly generate videos with durations ranging from 5 to 10 seconds at a native resolution of 720p, which are subsequently upscaled to 1080p. The model simultaneously supports text-to-video (T2V), image-to-video (I2...","url_abs":"https://arxiv.org/abs/2508.15761","url_pdf":"https://arxiv.org/pdf/2508.15761v2","authors":"[\"Yifu Zhang\",\"Hao Yang\",\"Yuqi Zhang\",\"Yifei Hu\",\"Fengda Zhu\",\"Chuang Lin\",\"Xiaofeng Mei\",\"Yi Jiang\",\"Bingyue Peng\",\"Zehuan Yuan\"]","published":"2025-08-21T17:56:10Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\"]","has_code":false,"code_links":[{"ID":610644,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2879965,"paper_url":"https://arxiv.org/abs/2508.15761","paper_title":"Waver: Wave Your Way to Lifelike Video Generation","repo_url":"https://github.com/FoundationVision/Waver","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}