Can reference images be processed invidually ?

[wzic]

Hi! In the code, it seems that the ref latents are parallelly concatenated with the own latent and being denoised simultaneously ? May I know if it is equivalent to first invidually get the self-attention key and value of each ref invidually, and then concat them together during denoising ?

[dingangui]

yes, you can get the self-attention key and value of each ref invidually first, and then concat them together during denoising, it will save your GPU memory

[wzic]

Thanks