---
title: Yume-I2V-540P
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Yume-I2V-540P"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Yume-I2V-540P.md"
repository: AI-ModelScope/Yume-I2V-540P
last_updated: 2025-07-30
license: apache-2.0
pipeline_tag: image-to-video
tasks:
  - image-to-video
parameters: 17.1B
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 155
stars: 0
---

# Yume-I2V-540P

> Yume-I2V-540P - AI-ModelScope 在 ModelScope 开源的模型。Yume: An Interactive World Generation Model

AI-ModelScope/Yume-I2V-540P 是 ModelScope 魔搭社区上的 17.1B 参数image-to-video模型，采用 apache-2.0 许可。

- **Repository**: AI-ModelScope/Yume-I2V-540P
- **License**: apache-2.0
- **Tasks**: image-to-video
- **Parameters**: 17.1B
- **Downloads**: 155
- **Stars**: 0
- **Last updated**: 2025-07-30

Source: https://www.modelscope.cn/models/AI-ModelScope/Yume-I2V-540P

---

# Yume: An Interactive World Generation Model

This is a preview version of the Yume model, an interactive world generation model, presented in the paper [Yume: An Interactive World Generation Model](https://huggingface.co/papers/2507.17744).

Yume aims to create an interactive, realistic, and dynamic world from an input image, allowing exploration and control.

Project Page: [https://stdstu12.github.io/YUME-Project/](https://stdstu12.github.io/YUME-Project/)\
GitHub Repository: [https://github.com/stdstu12/YUME](https://github.com/stdstu12/YUME)

## Usage

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