---
title: makeanything
canonical_url: "https://www.modelscope.cn/models/showlab/makeanything"
md_url: "https://www.modelscope.cn/models/showlab/makeanything.md"
repository: showlab/makeanything
last_updated: 2025-05-30
license: mit
parameters: 57.3B
tensor_type:
  - BF16
  - F8_E4M3
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 409
stars: 0
---

# makeanything

> makeanything - showlab 在 ModelScope 开源的模型。MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation

showlab/makeanything 是 ModelScope 魔搭社区上的 57.3B 参数机器学习模型，采用 mit 许可。

- **Repository**: showlab/makeanything
- **License**: mit
- **Parameters**: 57.3B
- **Downloads**: 409
- **Stars**: 0
- **Last updated**: 2025-05-30

Source: https://www.modelscope.cn/models/showlab/makeanything

---

# MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation

For detailed instructions on how to use the models and train them, please visit our [GitHub repository](https://github.com/showlab/MakeAnything).

## Citation
```
@inproceedings{
    Song2025MakeAnythingHD,
    title={MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation},
    author={Yiren Song and Cheng Liu and Mike Zheng Shou},
    year={2025},
    url={https://api.semanticscholar.org/CorpusID:276107845}
}
```