DCT-Net
DCT-Net copied to clipboard
Official implementation of "DCT-Net: Domain-Calibrated Translation for Portrait Stylization", SIGGRAPH 2022 (TOG); Multi-style cartoonization
Hi, I use anime style model to test celeb dataset. It has some bad cases and artifacts. The pose seems not large. How to solve this? Thanks! @menyifang  
Hi thanks for merging PR for the web demo on Hugging Face https://github.com/menyifang/DCT-Net/pull/14, would you also be interested in adding the model to huggingface, you can see the guide for...
question
In addition to anime, how to convert other cartoon images
2022-08-11 12:29:20,507 - modelscope - WARNING - ('PIPELINES', 'image-portrait-stylization', 'unet-person-image-cartoon') not found in ast index file Traceback (most recent call last): File "run_sdk.py", line 5, in img_cartoon = pipeline(Tasks.image_portrait_stylization, 'damo/cv_unet_person-image-cartoon_compound-models')...
Hi, could you please share the model and inference of 3D cartoon? Thanks! @menyifang
Thank you for your impressive work. Also thank you for sharing the model and code. We believe this work is one of the most important in the field of style...
Thanks for the amazing work. I have tried the 'anime' style model and all of the 'anime' people have very pointed chins, is there any way to modify the pointed...
Hello, Thank you for such amazing work on portrait stylisation. Can you please let us know when it will be released ? Thanks again
Hi, What is the difference between your style representation loss and the surface representation loss of white-box cartoonization?