Closed fanchunpeng closed 2 years ago
Provided pre training model Dior_ 64 get the above effect, it's not the best model, is it? I want to adjust the resolution and definition higher. I just feel that the resolution of 256x176 is relatively low. I hope to improve it to 512x352. Do you have any suggestions?
Since we only support and test on 256x176, if you want good result on 512x352, maybe you should check those HD virtual try-on work on and combine them with our recurrent pipeline together.
Would it be hard to retrain the model for higher resolutions?
The results of demo output are as follows:
Hello, how to improve the above effect?
The semantic model adopted has no mask information of the neck. What do you suggest to do with the neck mask?
The code distinguishes hair from hat, which is set as background information. Would it be better to combine hat and hair information?
The resolution of the result is low and the image quality is not clear. Is there any magnification to improve the resolution?
From the test results, the face information is inconsistent; Is it recommended to add facial information when changing hair?