This project contains the image-to-multiview diffusion and image-to-normal diffusion models from Unique3D.
pip install git+https://github.com/TingtingLiao/unique3d-diffusion.git
or
git clone https://github.com/TingtingLiao/unique3d-diffuser.git
cd unique3d-diffuser
pip install -e .
Download unique3d models from huggingface.
# image to multi-view image
python3 -m scripts.img2mvimg --ckpt "ckpt/img2mvimg/unet_state_dict.pth" --img "data/belle.jpeg"
# image to multi-view normal
python3 -m scripts.img2normal --ckpt "ckpt/image2normal/unet_state_dict.pth" --img_dir "output/belle/images"
The code is adapted from unique3d. Please consiter cite:
@misc{wu2024unique3d,
title={Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image},
author={Kailu Wu and Fangfu Liu and Zhihan Cai and Runjie Yan and Hanyang Wang and Yating Hu and Yueqi Duan and Kaisheng Ma},
year={2024},
eprint={2405.20343},
archivePrefix={arXiv},
primaryClass={cs.CV}
}