Views
No views yet
fp16 weights on huggingface:1# dependency
2pip install -r requirements.txt
3
4# xformers is required! please refer to https://github.com/facebookresearch/xformers
5pip install ninja
6pip install -v -U git+https://github.com/facebookresearch/xformers.git@main#egg=xformers1python run_mvdream.py "a cute owl"
2python run_imagedream.py data/anya_rgba.png1# download original ckpt (we only support the SD 2.1 version)
2mkdir models
3cd models
4wget https://huggingface.co/MVDream/MVDream/resolve/main/sd-v2.1-base-4view.pt
5wget https://raw.githubusercontent.com/bytedance/MVDream/main/mvdream/configs/sd-v2-base.yaml
6cd ..
7
8# convert
9python convert_mvdream_to_diffusers.py --checkpoint_path models/sd-v2.1-base-4view.pt --dump_path ./weights_mvdream --original_config_file models/sd-v2-base.yaml --half --to_safetensors --test1# download original ckpt (we only support the pixel-controller version)
2cd models
3wget https://huggingface.co/Peng-Wang/ImageDream/resolve/main/sd-v2.1-base-4view-ipmv.pt
4wget https://raw.githubusercontent.com/bytedance/ImageDream/main/extern/ImageDream/imagedream/configs/sd_v2_base_ipmv.yaml
5cd ..
6
7# convert
8python convert_mvdream_to_diffusers.py --checkpoint_path models/sd-v2.1-base-4view-ipmv.pt --dump_path ./weights_imagedream --original_config_file models/sd_v2_base_ipmv.yaml --half --to_safetensors --test1@article{shi2023MVDream,
2 author = {Shi, Yichun and Wang, Peng and Ye, Jianglong and Mai, Long and Li, Kejie and Yang, Xiao},
3 title = {MVDream: Multi-view Diffusion for 3D Generation},
4 journal = {arXiv:2308.16512},
5 year = {2023},
6}
7@article{wang2023imagedream,
8 title={ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation},
9 author={Wang, Peng and Shi, Yichun},
10 journal={arXiv preprint arXiv:2312.02201},
11 year={2023}
12}