HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning <div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/APvq0OIYDis?rel=1" start="0"></iframe></div> ✨ Key FeaturesHuMo is a unified, human-centric video generation framework designed to produce high-quality, fine-grained, and controllable human videos from multimodal inputs—including text, images, and audio. It supports strong text prompt following, consistent subject preservation, synchronized audio-driven motion.<ul><li>​​VideoGen from Text-Image​​ - Customize character appearance, clothing, makeup, props, and scenes using text prompts combined with reference images.</li><li>​​VideoGen from Text-Audio​​ - Generate audio-synchronized videos solely from text and audio inputs, removing the need for image references and enabling greater creative freedom.</li><li>​​VideoGen from Text-Image-Audio​​ - Achieve the higher level of customization and control by combining text, image, and audio guidance. </li></ul>Examples and models from the following sources reuploaded for your convenience here: <a target="_blank" rel="ugc" href="https://huggingface.co/bytedance-research/HuMo">https://huggingface.co/bytedance-research/HuMo</a> <a target="_blank" rel="ugc" href="https://github.com/Phantom-video/HuMo">https://github.com/Phantom-video/HuMo</a> Compatible with both 480P and 720P resolutions. 720P inference will achieve much better quality.

Files with SHA256: 51837c1ce0ef38d973a81aca6aea4a528d1385708025d6645748ecbb649a631c