taming-transformers
taming-transformers copied to clipboard
CompVis
Taming Transformers for High-Resolution Image Synthesis
Hi, it's a great work！And thanks for releasing the code! But I have a question --how to evaluate on ImageNet? In other words, should I get the FID scores on...
I have a quick question. In the paper, is a separate model trained per-dataset? Or is one model trained for all datasets?
Thanks for this work. I want to know how to make the generated image more like its training data, especially the style?
I would like to know if High-Resolution Image-to-Image Translation is possible using this repo by using a pre-trained model and fine-tuning it on a custom dataset. For example, BERT NLP...
This [example](https://github.com/CompVis/taming-transformers#sampling) throws this error "ImportError: cannot import name '_get_image_size' from 'torchvision.transforms.functional'" Related to [this](https://github.com/pytorch/vision/issues/4328) Fixed by this PR.
Thank you for your great work. I would like to ask a question about your paper. How many epochs does it take to train the sflckr dataset during the first...
In the paper, the authors describe that the recon loss is replaced with perceptual loss. However, in the code, the actual recon loss is L1 (not L2) + perceptual loss....
Hi, this paper claims to be able to produce high-resolution images, yet there is no configuration in the code that can learn images bigger that 256x256. Increasing the resolution to...
Hello, Thanks for the awesome code. I meet a problem when trying to understand how the transformer learns in the third stage. In the segmentation and depth-conditioned generation tasks, we...
