vlad.andronik

Hi, I have problems with understanding how to get some demos on my noisy audios with your model. You have multiple branches with different codes, in docs you refer to...

Pretrained model

4

Hi, @yangbisheng2009, Do you mind publishing the pre-trained model for results reproducing? Looking forward to hearing from you. Vladyslav

Is it possible that there is no explicit initialization for the created models? I cannot find it in UGATIT.py file or anywhere else. I would be grateful if you refer...

Thank you for your contribution, I learned much from it. But there is a thing that I can not come up with. There is a code in optimize method in...

Old method bug

33

Trying old method with default settings, got this error: ``` usage: train_dreambooth.py [-h] --pretrained_model_name_or_path PRETRAINED_MODEL_NAME_OR_PATH [--tokenizer_name TOKENIZER_NAME] --instance_data_dir INSTANCE_DATA_DIR [--class_data_dir CLASS_DATA_DIR] [--instance_prompt INSTANCE_PROMPT] [--class_prompt CLASS_PROMPT] [--with_prior_preservation] [--prior_loss_weight PRIOR_LOSS_WEIGHT] [--num_class_images NUM_CLASS_IMAGES]...

Data to reproduce the results

8

I can't get good results fine-tuning on faces, maybe there is a bug there, would be good to have data to reproduce your results from Readme with your training settings

Weight files take up too much disk space

5

Trying to run your demo, but getting No space left on device error, while loading the model, it takes more than 60GB of memory, on your HF it seems like...

In your examples I see a method for better ID fidelity, but do not understand fully how to reproduce it. If you could tell more about it or share other...