Open demegire opened 2 years ago
It would be good to at least get a reply what the reason is for not publishing the training code. If it is not intended to be shared - fair enough. But it would be great to know....
Meanwhile did anyone figure out how to train?
No I just wanted to clean it up first before releasing it and then never got around to it... ^^;;
It is similar to my CIFAR-10 training notebook (https://colab.research.google.com/drive/1rKa8P8Sg1C8q2fzyiM4WMWpZ6sq86423) except PyTorch Lightning/distributed data parallel.
No I just wanted to clean it up first before releasing it and then never got around to it... ^^;;
We would appreciate the dirty code too! It is better than nothing after all. In fact I could try to clean the code myself and merge it here if you published it. Thank you for your great contributions to the AI-Art community btw
Is there a way to train custom diffusion models?