TalTaiber

> Hello, what's wrong with code that comes out with negative values？ Just a guess, since the author did not repond: Higher SSIM corresponds to greater similarity between the two...

The easiest way to do this when training is inside your custom dataset class (notice that this repo doesn't come with its own training code, so you'll have to write...

This example might help you with some tricks to significantly reduce VRAM costs for training: https://github.com/ShivamShrirao/diffusers/tree/main/examples/dreambooth Also, this might help: https://huggingface.co/docs/transformers/perf_train_gpu_many