If I want to use wget to download the pretrained model of cin transformer，link is https://app.koofr.net/links/90cbd5aa-ef70-4f5e-99bc-f12e5a89380e how can I get the url. I tried to right click the link to download, but failed. The error I got was "HTTP request sent, waiting response... 400 Bad Requ...

When I trying use imageNet/transformer, I got this error. and I check that there is no decode function in Labelator class. Labelator class is located at "taming/modules/util/Labelator" @pesser @rromb @tgisaturday @rom1504 @carmocca

Do I see properly that my Nvidia free memory is 451MiB? If true than why pytorch still raise Exception "out of memory"? torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 1.39 GiB (GPU 0; 6.00 GiB total capacity; 4.04 GiB already allocated; 478.00 MiB free; 4.15 GiB reserved in total...

Is there any pretrained stage 2 model for VQGAN available? As far as I can see, the table of pretrained models offers stage 1 models only.

I tried training my own module, but the quantization stage always collapsed into trivial solution, i.e. all features are indexed to the same entry, I use all the same training procedure, has anyone come across this issues? or it is just me configuring something wrong?

`ImportError Traceback (most recent call last) in 7 sys.path.append(".") 8 sys.path.append('./taming-transformers') ----> 9 from taming.models import vqgan # checking correct import from taming 1 frames /content/taming-transformers/main.py in 10 from pytorch_light...

Hello, First of all, awesome work and awesome repo! Thanks for having shared your pre-trained models! For VQGAN OpenImages (f=8), 256 and VQGAN OpenImages (f=8), 16384, the provided zip files only contain model checkpoints. Could you please share the configs as well? Thank you in advance for your re...

Hi, I would like to know whether you could provide code or show the resources for sampling with classifier guidance on ImageNet using ResNet model? This would be very helpful thanks!

Hi compvis group, thanks for your overwheming work and i'd love to deploy your method into my project. However, i found there is no learning rate scheduler(lr scheduler) was used for training. More precisely, the ./taming/models/vqgan.py, VQGAN.configure_optimizer only returns two optimizers. And se...

thank you for making this code public. I want to train vqgan from scrach, but error like the one of below python3 main.py --base configs/imagenet_vqgan.yaml -t True --gpus 0,1,2,3,4,5,6,7 Traceback (most recent call last): File "/usr/local/lib/python3.8/dist-packages/torch/multiprocessing/spawn.p...