VGen

by Alibaba Group

About the model:

an open-source video synthesis codebase developed by the Tongyi Lab

Model type:

Video

Model performance class:

Limited

Link to the model:

https://huggingface.co/ali-vilab/i2vgen-xl

Base models:

i2vgen-xl

End model:

i2vgen-xl

End model license:

Unknown

About the organisation:

Alibaba TongYi Vision Intelligence Lab

Link to the organisation:

https://huggingface.co/ali-vilab

Model release date:

December 2023

Availability

Base Model Data

End User Model Data

WebVid-10M and LAION-400M datasets

https://huggingface.co/ali-vilab/i2vgen-xl

Base Model Weights

https://huggingface.co/ali-vilab/i2vgen-xl/tree/main/models

End User Model Weights

Training Code

Documentation

Code Documentation

Hardware Architecture

Preprint

I2VGen-XL High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models

https://arxiv.org/abs/2311.04145

Paper

37th International Conference on Neural Information Processing Systems

https://dl.acm.org/doi/abs/10.5555/3666122.3666456

Modelcard

https://huggingface.co/ali-vilab/i2vgen-xl

Datasheet

Access

Licenses

MIT 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.