| --- |
| 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 | SD2.1 | [mvadapter_t2mv_sd21.safetensors](https://huggingface.co/huanngzh/mv-adapter/resolve/main/mvadapter_t2mv_sd21.safetensors) | | |
| | 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 | SD2.1 | [mvadapter_i2mv_sd21.safetensors](https://huggingface.co/huanngzh/mv-adapter/resolve/main/mvadapter_i2mv_sd21.safetensors) | | |
| | 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 | [mvadapter_tg2mv_sdxl.safetensors](https://huggingface.co/huanngzh/mv-adapter/resolve/main/mvadapter_tg2mv_sdxl.safetensors) | | |
| | Image-Geometry-to-Multiview | SDXL | [mvadapter_ig2mv_sdxl.safetensors](https://huggingface.co/huanngzh/mv-adapter/resolve/main/mvadapter_ig2mv_sdxl.safetensors) | | |
| | 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} |
| } |
| ``` |
