search

miccunifi / ladi-vton

[ACM MM 2023] - LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-On
Other
412 stars 56 forks source link

How to get image "image-parse-v3" #37

Open Sorokopudov opened 12 months ago

Sorokopudov commented 12 months ago

To run the inference.py script, you must have at least images in the "cloth", "image", "image-parse-v3", "openpose_json folders" (i use vitonhd dataset) . Everything is clear with the "images", "cloth" and "image". I also learned how to receive "openpose_json" files. But I can't find how to get images for "image-parse-v3"? help me please

ABaldrati commented 11 months ago

Hi @Sorokopudov Thanks for your interest in our work!!

When you download the VitonHD dataset you should have the 'image-parse-v3' folder inside the train/test folder.

Hope this helps, Alberto