---
title: champ
canonical_url: "https://www.modelscope.cn/models/fudan-generative-vision/champ"
md_url: "https://www.modelscope.cn/models/fudan-generative-vision/champ.md"
repository: fudan-generative-vision/champ
last_updated: 2026-08-03
license: apache-2.0
parameters: 83.7M
tensor_type:
  - F32
library_name:
  - safetensors
  - diffusers
  - pytorch
frameworks:
  - pytorch
downloads: 1042
stars: 0
tags:
  - champ
---

# champ

> champ - fudan-generative-vision 在 ModelScope 开源的模型。Repository: fudan-generative-ai/champ Paper: https://arxiv.org/abs/2403.14781

fudan-generative-vision/champ 是 ModelScope 魔搭社区上的 83.7M 参数机器学习模型，采用 apache-2.0 许可。

- **Repository**: fudan-generative-vision/champ
- **License**: apache-2.0
- **Parameters**: 83.7M
- **Tags**: champ
- **Downloads**: 1042
- **Stars**: 0
- **Last updated**: 2026-08-03

Source: https://www.modelscope.cn/models/fudan-generative-vision/champ

---

# Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** [fudan-generative-ai/champ](https://github.com/fudan-generative-vision/champ)
- **Paper:** [https://arxiv.org/abs/2403.14781](https://arxiv.org/abs/2403.14781)

# Directory Structure

```shell
./PROJECT_ROOT/
|-- champ   # Champ Model
|   |-- denoising_unet.pth
|   |-- guidance_encoder_depth.pth
|   |-- guidance_encoder_dwpose.pth
|   |-- guidance_encoder_normal.pth
|   |-- guidance_encoder_semantic_map.pth
|   |-- reference_unet.pth
|   `-- motion_module.pth
|-- image_encoder
|   |-- config.json
|   `-- pytorch_model.bin
|-- sd-vae-ft-mse
|   |-- config.json
|   |-- diffusion_pytorch_model.bin
|   `-- diffusion_pytorch_model.safetensors
`-- stable-diffusion-v1-5
    |-- feature_extractor
    |   `-- preprocessor_config.json
    |-- model_index.json
    |-- unet
    |   |-- config.json
    |   `-- diffusion_pytorch_model.bin
    `-- v1-inference.yaml
```

# Reference

Thanks to the following projects and authors:

* [1] [runwayml](https://huggingface.co/runwayml). [Stable Diffusion v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5).
* [2] [stabilityai](https://huggingface.co/stabilityai). [sd-vae-ft-mse](https://huggingface.co/stabilityai/sd-vae-ft-mse)
* [3] [bdsqlsz](https://huggingface.co/bdsqlsz). [image_encoder](https://huggingface.co/bdsqlsz/image_encoder)