Step-Video

by StepFun

About the model:

Video generation model by StepFun.

Model type:

Video

Model performance class:

Limited

Link to the model:

https://huggingface.co/stepfun-ai/stepvideo-ti2v

Base models:

StepVideo-T2V

End model:

StepVideo-TI2V

End model license:

MIT License

About the organisation:

StepFun, a Chinese AI company.

Link to the organisation:

https://www.stepfun.com/

Model release date:

February 2025

Availability

Base Model Data

No dataset found.

End User Model Data

No dataset found.

Base Model Weights

Weights made available through HuggingFace.

https://huggingface.co/stepfun-ai/stepvideo-t2v

End User Model Weights

Weights made available through HuggingFace.

https://huggingface.co/stepfun-ai/stepvideo-ti2v

Training Code

Github available, however does not contain training code.

https://github.com/stepfun-ai/Step-Video-TI2V https://github.com/stepfun-ai/Step-Video-T2V

Documentation

Code Documentation

No training code, so no documentation.

Hardware Architecture

Detailed hardware architecture information provided in paper.

https://arxiv.org/pdf/2502.10248

Preprint

Preprints made available through arXiv.

https://arxiv.org/pdf/2502.10248 https://arxiv.org/pdf/2503.11251

Paper

No peer-reviewed paper found.

Modelcard

Model card contains minimal information.

https://huggingface.co/stepfun-ai/stepvideo-ti2v

Datasheet

No datasheet found.

Access

Licenses

MIT License, an OSI-approved license.

https://github.com/stepfun-ai/Step-Video-TI2V/blob/main/LICENSE

Is this information not up to date?

Contribute here ->

Supported by the Centre for Language Studies and the Dutch Research Council. Website design & development © 2024 by BSTN. This version of the index generated 09 April 2026, website content last updated 11 March 2026.