MaTe3D: Mask-guided Text-based 3D-aware Portrait Editing
Paper • 2312.06947 • Published
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Ellis/MaTe3D", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]MaTe3D Pretrained Models
[ArXiv] MaTe3D: Mask-guided Text-based 3D-aware Portrait Editing
Kangneng Zhou, Daiheng Gao, Xuan Wang, Jie Zhang, Peng Zhang, Xusen Sun, Longhao Zhang, Shiqi Yang, Bang Zhang, Liefeng Bo, Yaxing Wang, Yaxing Wang, Ming-Ming Cheng
Pretrained Generator on FFHQ Mask
Pretrained Generator on CatMask-HQ
Pretrained ControlNet on FFHQ Mask
Pretrained ControlNet on CatMask-HQ
Contact
Citation
If you find this project helpful to your research, please consider citing:
@article{zhou2023mate3d,
title = {MaTe3D: Mask-guided Text-based 3D-aware Portrait Editing},
author = {Kangneng Zhou, Daiheng Gao, Xuan Wang, Jie Zhang, Peng Zhang, Xusen Sun, Longhao Zhang, Shiqi Yang, Bang Zhang, Liefeng Bo, Yaxing Wang, Ming-Ming Cheng},
journal = {arXiv preprint arXiv:2312.06947},
website = {https://montaellis.github.io/mate-3d/},
year = {2023}}
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support