{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/real-time-one-step-diffusion-based-expressive","title":"Real-time One-Step Diffusion-based Expressive Portrait Videos Generation","arxiv_id":"2412.13479","date":"2024-12-18","proceeding":null,"authors":["Hanzhong Guo","Hongwei Yi","Daquan Zhou","Alexander William Bergman","Michael Lingelbach","Yizhou Yu"],"abstract":"Latent diffusion models have made great strides in generating expressive portrait videos with accurate lip-sync and natural motion from a single reference image and audio input. However, these models are far from real-time, often requiring many sampling steps that take minutes to generate even one second of video-significantly limiting practical use. We introduce OSA-LCM (One-Step Avatar Latent Consistency Model), paving the way for real-time diffusion-based avatars. Our method achieves comparable video quality to existing methods but requires only one sampling step, making it more than 10x faster. To accomplish this, we propose a novel avatar discriminator design that guides lip-audio consistency and motion expressiveness to enhance video quality in limited sampling steps. Additionally, we employ a second-stage training architecture using an editing fine-tuned method (EFT), transforming video generation into an editing task during training to effectively address the temporal gap challenge in single-step generation. Experiments demonstrate that OSA-LCM outperforms existing open-source portrait video generation models while operating more efficiently with a single sampling step.","url_abs":"https://arxiv.org/abs/2412.13479v1","url_pdf":"https://arxiv.org/pdf/2412.13479v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"real-time-one-step-diffusion-based-expressive","repo_url":"https://github.com/Guohanzhong/OSA-LCM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.13479","atlas_url":"https://app.syntology.ai/?focus=2412.13479","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}