ReNO

ReNO copied to clipboard

Aesthetic score

1

I'm curious about how the aesthetic scores of the generated images from the paper were calculated. Is it possible to share the code? Thanks!

jsonBackup

SD-2.1

3

Very excellent job, if you migrate him to 50-step SD-2-1, can you work well?

zhou431496

Does ReNO work with SDXL inpainting model?

1

Hi there, Thank you for open sourcing your wonderful work. I am just curious, if ReNO would work with SDXL Inpainting pipeline? Thanks

khurramkhalil

Does he support ControlNet and IP Adapter

libai-lab

About Loss Function

1

Hi, I have a question about the loss function choice. As I see, you have used dot product for similarity of features. Did you experiment using L1, L2 MSE, others...

Oguzhanercan

Loss almost does not change

8

Hi, I am trying to experience different losses. I Have implement a face similarity loss and disabled all of other losses. But The loss almost does not changed (%1 decreased)....

Oguzhanercan