Tag
LongCat-Video is a 13.6B parameter video generation model based on Diffusion Transformer, supporting text-to-video, image-to-video, and video-continuation tasks with efficient long video generation using coarse-to-fine and block sparse attention.
Meituan releases LongCat-Video, a 13.6B parameter foundational video generation model unifying text-to-video, image-to-video, and video-continuation tasks with efficient long video generation, block sparse attention, and multi-reward GRPO-based RLHF.