Kangfu Mei
Kangfu Mei
@ZHUXIUJINChris I am not sure what do you mean by color difference? I just checked the uploaded results and believe they are different images.
Thanks for reminding me. Let me take a look.
Hi @dezle13 , the feature encode is trained with the diffusion loss directly and it is optimized in the first stage and frozen in the second stage.
Hi @atsatvik , could you give more details about how do you get the latent feature map?