项目简介
LongCat-Video 是美团开源的 13.6B 视频生成基础模型，在单一架构中统一支持文生视频、图生视频与视频续写任务。通过由粗到细的生成策略和块稀疏注意力，可高效生成数分钟长的高质量视频且无色彩漂移，并采用多奖励 GRPO 强化学习优化。其 Avatar 版本还支持音频驱动的数字人动画生成。
README 预览
# LongCat-Video\n\n\n \n\n\n\n\n\n \n \n \n \n\n\n \n \n \n \n \n\n\n \n \n \n \n\n \n\n\n## Model Introduction\nWe introduce LongCat-Video, a foundational video generation model with 13.6B parameters, delivering strong performance across *Text-to-Video*, *Image-to-Video*, and *Video-Continuation* generation tasks. It particularly excels in efficient and high-quality long video generation, representing our first step toward world models.\n\n### Key Features\n- 🌟 **Unified architecture for multiple tasks**: LongCat-Video unifies *Text-to-Video*, *Image-to-Video*, and *Video-Continuation* tasks within a single video generation framework. It natively supports all these tasks with a single model and consistently delivers strong performance across each individual task.\n- 🌟 **Long video generation**: LongCat-Video is natively pretrained on *Video-Continuation* tasks, enabling it to produce minutes-long videos without color drifting or quality degradation.\n- 🌟 **Efficient inference**: LongCat-Video generates $720p$, $30fps$ videos within minutes by employing a coarse-to-fine generation strategy along both the temporal and spatial axes. Block Sparse Attention further enhances efficiency, particularly at high resolutions\n- 🌟 **Strong performance with multi-reward RLHF**: Powered by multi-reward Group Relative Policy Optimization (GRPO), comprehensive evaluations on both internal and public benchmarks demonstrate that LongCat-Video achieves performance comparable to leading open-source video generation models as well as the latest commercial solutions.\n\nFor more detail, please refer to the comprehensive [***LongCat-Video Technical Report***](https://arxiv.org/abs/2510.22200).\n\n## 🎥 Teaser Video\n\n\n \n\n\n## 🔥 Latest News!!\n- May 21, 2026: 🚀 We release [***LongCat-Video-Avatar-1.5***](https://meigen-ai.github.io/LongCat-Video-Avatar-1.5-Page/), an upgraded open-source framework for audio-driven human video generation. v1.5 replaces Wav2Vec2
常见问题 (1)
操作指南LongCat-Video-Avatar 1.5 基础模型是否包含 GRPO 训练，以及如何运行非 DMD 基线推理？
操作指南
LongCat-Video-Avatar 1.5 基础模型是否包含 GRPO 训练，以及如何运行非 DMD 基线推理？是的。已发布的 base_model 和 base_model_int8 权重是合并后的检查点，已经包含了 GRPO (RLHF) 训练阶段。lora/dmd_lora.safetensors 文件只是一个在*非 GRPO* 基础版本上训练的 DMD2 加速适配器——它提供的是步数蒸馏，而不是 GRPO 带来的质量改进。
要评估 v1.5 的非 DMD 基线质量，请在不加 --use_distill 的情况下运行 avatar-v1.5，并将推理步数设置为 40，同时使用默认的调度器/配置。当使用 --use_distill（DMD）时，8 步就足够了，并且根据维护者的说法，DMD 蒸馏的设置在稳定性上优于非蒸馏基线。