---
license: apache-2.0
pipeline_tag: text-to-image
library_name: diffusion-single-file
tags:
- Image-to-Image
---

# MV-Adapter Model Card

<div align="center">

[**Project Page**](https://huanngzh.github.io/MV-Adapter-Page/) **|** [**Paper (ArXiv)**](https://arxiv.org/abs/2412.03632) **|** [**Paper (HF)**](https://hf.co/papers/2412.03632) **|** [**Code**](https://github.com/huanngzh/MV-Adapter) **|** [**Gradio demo**](https://huggingface.co/spaces/VAST-AI/MV-Adapter-I2MV-SDXL)

Create High-fidelity Multi-view Images with Various Base T2I Models and Various Conditions.
</div>

## Introduction
MV-Adapter is a creative productivity tool that seamlessly transfer text-to-image models to multi-view generators.

Highlights:
- 768x768 multi-view images
- work well with personalized models (e.g. DreamShaper, Animagine), LCM, ControlNet
- support text or image to multi-view (reconstruct 3D thereafter), or with geometry guidance for 3D texture generation
- arbitrary view generation

## Examples

<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/6375d136dee28348a9c63cbf/P7ywma2xFX-_SfEj1cJmY.mp4"></video>

## Model Details
|            Model            | Base Model |                                                         HF Weights                                                         |                                                                   Demo Link                                                                   |
| :-------------------------: | :--------: | :------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------: |
|      Text-to-Multiview      |    SDXL    | [mvadapter_t2mv_sdxl.safetensors](https://huggingface.co/huanngzh/mv-adapter/resolve/main/mvadapter_t2mv_sdxl.safetensors) | [General](https://huggingface.co/spaces/VAST-AI/MV-Adapter-T2MV-SDXL) / [Anime](https://huggingface.co/spaces/huanngzh/MV-Adapter-T2MV-Anime) |
|     Image-to-Multiview      |    SDXL    | [mvadapter_i2mv_sdxl.safetensors](https://huggingface.co/huanngzh/mv-adapter/resolve/main/mvadapter_t2mv_sdxl.safetensors) |                                      [Demo](https://huggingface.co/spaces/VAST-AI/MV-Adapter-I2MV-SDXL)                                       |
| Text-Geometry-to-Multiview  |    SDXL    |                                                                                                                            |                                                                                                                                               |
| Image-Geometry-to-Multiview |    SDXL    |                                                                                                                            |                                                                                                                                               |
|  Image-to-Arbitrary-Views   |    SDXL    |                                                                                                                            |                                                                                            

## Usage

Refer to our [Github repository](https://github.com/huanngzh/MV-Adapter).

## Citation
If you find this work helpful, please consider citing our paper:
```bibtex
@article{huang2024mvadapter,
  title={MV-Adapter: Multi-view Consistent Image Generation Made Easy},
  author={Huang, Zehuan and Guo, Yuanchen and Wang, Haoran and Yi, Ran and Ma, Lizhuang and Cao, Yan-Pei and Sheng, Lu},
  journal={arXiv preprint arXiv:2412.03632},
  year={2024}
}
```