onlyv

Stable Diffusion fine-tuning problem

4

During fine-tuning for depth estimateaion conditioned on input image, how to deal with the text prompt required in the original pre_trained text-to-image Stable Diffusion model?

A question about CAM attention map

4

 In this picture, why IL and IH share the same attention map generated by Mask extractor when IL and IH are unpaired.

Question about training set up.

1

Are the reference image and GT image during training from the same image of CelebA?

Question about training.

2

If the pseudo labels predicted by the teacher model are inaccurate, how does the student model obtain the correct information from the unlabeled data? Why does the student model outperform...

Before fine-tuning, the result is black

1

Before fine-tuning, the result is black. After fine-tuning, the result is still balck

How to solve this problem