meituan-longcat/LongCat-Video

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

7665 stars · 1361 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

LongCat-Video is a 13.6B-parameter foundational video generation model from Meituan that unifies text-to-video, image-to-video, and video-continuation tasks in a single framework. The repository provides inference code, model weights on Hugging Face, and tooling for efficient long video generation.

Use cases

• generate videos from text prompts
• turn an image into a video
• extend a video clip with continuation
• generate minutes-long videos without quality drift
• run video generation on gpu efficiently
• research video generation models

When to choose

• you need a unified open model for text-to-video, image-to-video, and video continuation
• you want long-form video generation with minimal quality degradation
• you need MIT-licensed model weights for research or product prototyping

When to avoid

• you lack high-end GPU hardware for 13.6B-parameter inference
• you need lightweight or real-time video generation
• you only need video editing rather than generation

Facets

library · maturity active

video-processing machine-learning deep-learning llm-inference artificial-intelligence deep-learning media python video-generation text-to-video image-to-video video-continuation diffusion-model world-model huggingface model-weights video gpu linux docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="meituan-longcat/LongCat-Video")