Wangwon Lee
Wangwon Lee
Hi, there. I found some bug of 'preprocess_input' function when i used the function with tf.data. ## What is this PR? :mag: This issue was occured when we use the...
Hi, there. thank you for your nice work. I use linux and windows both. (usually use linux for development and sometimes use windows for the other reason) When I store...
Hi, thank you for nice work. It's great research to make high resolution face texture. In my case, result set(diffuseMap, roughnessMap, specularMap, envMap) is too difficult to use (compare than...
hi. thank you for your work. When I run inference code, I meet some error It may because checkpoint's key names and model's key names is different did anyone solve...
Hi, thank you for your nice work. I'm making stable diffusion webui extension by facer project. ([link](https://github.com/BbChip0103/sd-webui-facer)) Using stable diffusion and controllnet, masking is really important. A lot of people...
regarding #6 When we use driving video which have not 256 size, the video will be cropped to 256X256 size (not resizing) So I fixed this issue. Now driving video...
Hi, thank you for your research. MCNET make realiable result compare than other face animation models. I like it. Do you have any plan to share 512 size model? If...
Hi, there. Thank you for the interesting research. That inspires me. As I know, in order to acquire LSFM model, I have to request the model first. But the '[https://xip.uclb.com/product/LSFM](https://xip.uclb.com/product/LSFM)'...
Hi. Thank you for your great work. How much faster than original sadtalker?
Hi. I usually use '--alpha_mask' option in the 'dev' branch. If i use this option, text_encoder learning curve is disappear in the tensorboard.  without '--alpha_mask' option, text_encoder training seems...