alibaba/Tora
A trajectory-oriented Diffusion Transformer model for high-quality text-to-video and image-to-video generation.
Not currently ranked — collecting fresh signals.
star history
Tora is a video generation model based on Diffusion Transformer architecture, published at CVPR 2025. It enables text-to-video and image-to-video generation with trajectory control mechanisms. The model is available on both ModelScope and HuggingFace with implementations supporting SAT and Diffusers frameworks.
Frequently asked
- What is alibaba/Tora?
- A trajectory-oriented Diffusion Transformer model for high-quality text-to-video and image-to-video generation.
- Is Tora open source?
- Yes — alibaba/Tora is open source, released under the Apache-2.0 license.
- What language is Tora written in?
- alibaba/Tora is primarily written in Python.
- How popular is Tora?
- alibaba/Tora has 1.2k stars on GitHub.
- Where can I find Tora?
- alibaba/Tora is on GitHub at https://github.com/alibaba/Tora.