Image-to-Image
Diffusers
ONNX
Safetensors
StableDiffusionXLInpaintPipeline
stable-diffusion-xl
inpainting
virtual try-on
Instructions to use efdev/IDM-VTON with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use efdev/IDM-VTON with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import AutoPipelineForInpainting from diffusers.utils import load_image # switch to "mps" for apple devices pipe = AutoPipelineForInpainting.from_pretrained("efdev/IDM-VTON", dtype=torch.float16, device_map="cuda") img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png" mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png" image = load_image(img_url).resize((1024, 1024)) mask_image = load_image(mask_url).resize((1024, 1024)) prompt = "a tiger sitting on a park bench" generator = torch.Generator(device="cuda").manual_seed(0) image = pipe( prompt=prompt, image=image, mask_image=mask_image, guidance_scale=8.0, num_inference_steps=20, # steps between 15 and 30 work well for us strength=0.99, # make sure to use `strength` below 1.0 generator=generator, ).images[0] - Notebooks
- Google Colab
- Kaggle
Download assets/teaser2.png from efdev/IDM-VTON: direct link, hf CLI and curl.
- Browser
- Download file 9.02 MB
-
https://huggingface.co/efdev/IDM-VTON/resolve/main/assets/teaser2.png
- Command line
-
hf download hf://efdev/IDM-VTON/assets/teaser2.png
-
curl -L -o teaser2.png https://huggingface.co/efdev/IDM-VTON/resolve/main/assets/teaser2.png
9.02 MB

- Xet hash:
- 56b8a9d5090934dd5b58f38d2a47aff0e133e7575e2de58c49a775c51790d18a
- Size of remote file:
- 9.02 MB
- SHA256:
- 4a2c3522cb7805407f437f1639418166477f334cbef739e06947b5dfc68a1968
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.