StyleSwin
StyleSwin copied to clipboard
microsoft
[CVPR 2022] StyleSwin: Transformer-based GAN for High-resolution Image Generation
Sorry if this is a silly question, but I wanted ask if you could provide and example of how to fine-tune one of your existing models to a new dataset?...
Hi, I was referring to your github and trying to implement the StyleSwin repo. ecountering the following problem: nvcc fatal : Unknown option '-generate-dependencies-with-compile', not sure whast the problem. 
Hi there, I was wondering, can styleswin train like pix2pix? I wanna use vit to do img2img task, Thanks
How long did it take to train 256 * 256 a and 1024*1024 CelebA models. How many GPUs and what model are used？
Hi, there is a call for demos this year for cvpr 2022 https://cvpr2022.thecvf.com/call-demos where a demo can be added to the Hugging Face organization here: https://huggingface.co/cvpr would you be interested...
Thank you authors for sharing the interesting work you have done in deep generative modeling. I have a rather small doubt, this is regarding the command to generate samples. ```...
Thank you for the project. I wanted to know if one has saved the generated images in a directory, how to have them in a grid N*M dimensions for better...
 I don't know if this problem occurred in your build process? Is this due to lack of tRGB module or something else?
Hello, when I trained 400000 iterations, the power failure, how to continue training?
