VideoCrafter: video generator — what it does and what you need to run it

VideoCrafter is a set of open-source models for generating video from a text description or a starting image. The tool was created by Tencent AI Lab and is aimed at researchers and developers who want to experiment with diffusion video models with access to the source code.

What it does

• Text-to-video generation. The model creates a short video based on a text description.
• Image-to-video generation. You can feed a static image as input and get an animated scene.
• Working with diffusion models. The authors describe VideoCrafter2 as a solution aimed at overcoming data limitations for high-quality video diffusion models.

What you need to run it

• Platform. The code is written in Python. Running it requires an environment with Python and the relevant libraries.
• Hardware. The authors do not specify exact minimum requirements for VRAM or system RAM. Since these are diffusion models, running locally requires a discrete GPU with sufficient VRAM.
• License. The code is open source, but the license is non-standard — the authors recommend checking the terms of use manually in the repository.
• Repository. The source code is available at github.com/AILab-CVC/VideoCrafter. The latest code change was recorded on January 9, 2026.

Who it is for

VideoCrafter is primarily intended for researchers and developers familiar with the Python ecosystem and diffusion models. The tool will be useful for those who need open source code for fine-tuning, modification, or studying the architecture of generative video models. It is not designed for out-of-the-box consumer use without programming skills. Also, keep the non-standard license in mind if you plan commercial use.

The project page with additional information is available at ailab-cvc.github.io/videocrafter2/. The latest release at the time of repository analysis is VideoCrafter1, while the authors describe work on the second version.