Find tools › Open-source projects › Images, video & voice

LongCat-Video

Open-source project · by meituan-longcat

A large local AI model for generating videos, continuing clips, and animating talking avatars from text and audio.

Some setupWell known

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Generate videos from text descriptions
  • Animate talking characters from audio
  • Extend existing video clips

How to start

  1. Clone the repository and set up a Python conda environment

  2. Install PyTorch, FlashAttention-2, and other listed package requirements

  3. Download the model weights using the Hugging Face command-line tool

  4. Run single-GPU or multi-GPU inference scripts for your task

Good to know. Requires high-end NVIDIA GPUs with significant VRAM to run local inference.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: MITYou are allowed to use it under these terms.
  • Last updated 2026-11-15

More detail

LongCat-Video is a foundational video generation model with 13.6B parameters that supports text-to-video, image-to-video, video-continuation, and audio-driven character animation.

It lets researchers and developers generate high-resolution, long-form videos and audio-driven avatar animations locally on powerful hardware.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-10-03. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map