Mobile-VTON: High-Fidelity On-Device Virtual Try-On
Paper • 2603.00947 • Published
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("FlashStight/Mobile-VTON", 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]Mobile-VTON: High-Fidelity On-Device Virtual Try-On
This is the official implementation of the paper Mobile-VTON: High-Fidelity On-Device Virtual Try-On
📄 Paper: https://arxiv.org/abs/2603.00947
🌐 Project Page: https://zhenchenwan.github.io/Mobile-VTON/
💻 Code: https://github.com/tmllab/2026_CVPR_Mobile-VTON
Inference
Please refer to the official repository for inference scripts.
- Downloads last month
- -