video-virtual-try-on

diffusion model baesd video-virtual-try-on

NOTE: This is a personal experimental project. The code has not been properly organized (updated according to personal circumstances), there is no ready-to-use demo. Thanks to ladi-vton, DisCo for the inspiration, and any related discussions are welcome.

Instructions

• Improved 3D denoising UNet, improved face reconstruction performance and temporal consistency, using VVT dataset, fine-tuning based on stable-diffusion-2-inpainting
• Preprocessing dataset based on Densepose, Human-Parsing. The processed files will be uploaded soon
• Based on a pre-trained self-developed clothing deformation model, images of the warped clothing will also be released. The deformation model can be replaced by the existing graph virtual try-on deformation model

Release Plan

• Test results visualization
• Code for model
• Trained checkpoint
• [] Warping model
• [] Code for training
• [] Code for evaluation script (dataset, full pipeline)

Model checkpoint

• UNet
• Vision Encoder Projector