TryOffAnyone: Tiled Cloth Generation from a Dressed Person
Paper • 2412.08573 • Published • 2
Image-to-Image
Diffusers
Safetensors
diffusion
virtual try-on
virtual try-off
image generation
fashion
e-commerce
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("ixarchakos/tryOffAnyone", dtype=torch.bfloat16, device_map="cuda")
prompt = "Turn this cat into a dog"
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
image = pipe(image=input_image, prompt=prompt).images[0]TryOffAnyone
The models proposed in the paper "TryOffAnyone: Tiled Cloth Generation from a Dressed Person" [paper_arxiv] [github]:
Citation
If you find this repository useful in your research, please consider giving a star ⭐ and a citation:
@misc{xarchakos2024tryoffanyonetiledclothgeneration,
title={TryOffAnyone: Tiled Cloth Generation from a Dressed Person},
author={Ioannis Xarchakos and Theodoros Koukopoulos},
year={2024},
eprint={2412.08573},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2412.08573},
}
- Downloads last month
- 67