Project Page | Paper | Code| Data
To address the need for flexible and controllable customizations in virtual try-on systems, we propose IMAGDressing-v1. Specifically, we introduce a garment UNet that captures semantic features from CLIP and texture features from VAE. Our hybrid attention module includes a frozen self-attention and a trainable cross-attention, integrating these features into a frozen denoising UNet to ensure user-controlled editing. We will release a comprehensive dataset, IGv1, with over 200,000 pairs of clothing and dressed images, and establish a standard data assembly pipeline. Furthermore, IMAGDressing-v1 can be combined with extensions like ControlNet, IP-Adapter, T2I-Adapter, and AnimateDiff to enhance diversity and controllability.
IMAGDressing-v1_512.pt 3.5 GBunet/diffusion_pytorch_model.safetensors 3.4 GBimage_encoder/pytorch_model.bin 2.5 GBimage_encoder/model.safetensors 2.5 GBcontrol_v11p_sd15_openpose/diffusion_pytorch_model.bin 1.4 GBcontrol_v11p_sd15_openpose/diffusion_pytorch_model.safetensors 1.4 GBcontrol_v11p_sd15_openpose/diffusion_pytorch_model.fp16.bin 723 MBcontrol_v11p_sd15_openpose/diffusion_pytorch_model.fp16.safetensors 723 MBtext_encoder/model.safetensors 492 MBsd-vae-ft-mse/diffusion_pytorch_model.bin 335 MBsd-vae-ft-mse/diffusion_pytorch_model.safetensors 335 MBip-adapter-faceid-plus_sd15.bin 157 MBHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo camenduru/IMAGDressing ./model-folder