---
title: Yume-5B-720P
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Yume-5B-720P"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Yume-5B-720P.md"
repository: AI-ModelScope/Yume-5B-720P
last_updated: 2026-01-07
license: apache-2.0
pipeline_tag: image-to-video
tasks:
  - image-to-video
model_type:
  - ti2v
parameters: 5.2B
tensor_type:
  - F32
library_name:
  - safetensors
  - diffusers
  - pytorch
frameworks:
  - Pytorch
downloads: 108
stars: 0
tags:
  - Text-to-Video
  - Image-to-Video
  - "Diffusion Video Model"
  - "World Model"
---

# Yume-5B-720P

> Yume-5B-720P - AI-ModelScope 在 ModelScope 开源的模型。Yume-1.5: A Text-Controlled Interactive World Generation Model

AI-ModelScope/Yume-5B-720P 是 ModelScope 魔搭社区上的 5.2B 参数image-to-video模型，采用 apache-2.0 许可。

- **Repository**: AI-ModelScope/Yume-5B-720P
- **License**: apache-2.0
- **Tasks**: image-to-video
- **Parameters**: 5.2B
- **Tags**: Text-to-Video, Image-to-Video, Diffusion Video Model, World Model
- **Downloads**: 108
- **Stars**: 0
- **Last updated**: 2026-01-07

Source: https://www.modelscope.cn/models/AI-ModelScope/Yume-5B-720P

---

# Yume-1.5: A Text-Controlled Interactive World Generation Model

Yume-1.5 is a framework designed to generate realistic, interactive, and continuous worlds from a single image or text prompt. It supports keyboard-based exploration of the generated environments through a framework that integrates context compression and real-time streaming acceleration.



- [**Paper (Yume-1.5)**](https://huggingface.co/papers/2512.22096)
- [**Paper (Yume-1.0)**](https://huggingface.co/papers/2507.17744)
- [**Project Page**](https://stdstu12.github.io/YUME-Project/)
- [**GitHub Repository**](https://github.com/stdstu12/YUME)

## Features
- **Long-video generation**: Unified context compression with linear attention.
- **Real-time acceleration**: Powered by bidirectional attention distillation.
- **Text-controlled events**: Method for generating specific world events via text prompts.

## Usage

For detailed installation and setup instructions, please refer to the [GitHub repository](https://github.com/stdstu12/YUME). 

### Inference Example
To perform image-to-video generation using the provided scripts:

```bash
# Generate videos from images in the specified directory
bash scripts/inference/sample_jpg.sh --jpg_dir="./jpg" --caption_path="./caption.txt"
```

## Citation

If you use Yume for your research, please cite the following:

```bibtex
@article{mao2025yume,
  title={Yume: An Interactive World Generation Model},
  author={Mao, Xiaofeng and Lin, Shaoheng and Li, Zhen and Li, Chuanhao and Peng, Wenshuo and He, Tong and Pang, Jiangmiao and Chi, Mingmin and Qiao, Yu and Zhang, Kaipeng},
  journal={arXiv preprint arXiv:2507.17744},
  year={2025}
}
@article{mao2025yume,
  title={Yume-1.5: A Text-Controlled Interactive World Generation Model},
  author={Mao, Xiaofeng and Li, Zhen and Li, Chuanhao and Xu, Xiaojie and Ying, Kaining and He, Tong and Pang, Jiangmiao and Qiao, Yu and Zhang, Kaipeng},
  journal={arXiv preprint arXiv:2512.22096},
  year={2025}
}
```