nupurkmr9

Thanks. Can you tell what other hyperparameters need to be changed for FFHQ with config "paper256"?

Hi, thanks for the interest in our code. In case of CLIP network, default discriminator architecture architecture is multi-level, therefore loss_type should be `multilevel_sigmoid_s`. If you want to use `sigmoid_s`...

Hi, Can you provide more details regarding which code you are using for conversion? Would be great if I can replicate the error. If conversion of vision-aided discriminator is not...

Hi, Thanks for your interest in our work. Can you provide more dataset details. Is this similar to FFHQ or its a more artistic style dataset? Also how does the...

Hi, Looks like the augmentation probability of original discriminator is above 1, which is usually when the discriminator is overfitting. Can you post the logs for discriminator loss? Also does...

Hi, Sorry for the delayed response. There was a typo in the above command for training with diffAugment. It should be: `python train.py --outdir=training-runs --data=datasets/face7k.zip --diffaugment=color,translation,cutout --warmup=5e5 --cfg=paper256_2fmap --gpus=2 --kimg=5000...

Hi, in case miniImageNet and tieredImageNet dataset with rotation self-supervision, we train for 400 and 100 epochs. Batch size is kept to 64 and train_aug flag is enabled during backbone...

@rezkanas @shinnosukeono, sorry for the delayed response. I believe the error might be because of float16 training. Without it I am able to train with `--freeze_model="crossattn"` as well. I will...

Hi, Thanks a lot for your interest in our work. Currently we don't have a google colab. But we have a huggingface demo based on diffusers here: [https://huggingface.co/spaces/nupurkmr9/custom-diffusion](https://huggingface.co/spaces/nupurkmr9/custom-diffusion) The minimum...

Hi, This seems like a version issue. Can you comment which version of transformers you are using? I have tested the code with `transformers==4.25.1` and `diffusers==0.10.0.dev0`. I think any version...