bcmi / DCI-VTON-Virtual-Try-On

[ACM Multimedia 2023] Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow.
https://arxiv.org/abs/2308.06101
MIT License
387 stars 56 forks source link

Custom Image #16

Closed Deepak2405 closed 11 months ago

Deepak2405 commented 11 months ago

Hi, thank you for the code. Could you let us know how to test for a custom image. What are the requirements and what changes we need to make in the code?

Limbor commented 11 months ago

Hi, you should fisrt do some preprocessing on the custom data referring to https://github.com/sangyun884/HR-VITON/issues/45#issue-1515217009. After this, you can refer to the dataset and inference related codes of the warping module and diffusion model in our code to process these data.