Quality performance metrics of the models

[gtuzi]

Hello,

I'm wondering if the models supported in this project have been evaluated to see if their performance replicates the reported metrics in the original papers (primarily FID and CLIP score for the corresponding datatype), and how the quantized types compare.

Thanks

[stduhpf]

I don't think it has been done already, but if you're willing to do it, this could be valuable contribution, I think.