>>102590742>>102603263>in the previewthat's the mismatch
I'm talking doing a full denoise in just 5 steps
also, I'm using CFGStar (not CFGZeroStar) which makes a diff
(I use FreSca as well but that is a more subtle effect)
>good way to upscale0.25 or 0.3 with euler_a at 10 steps has been good enough for me, any specific reason to go higher denoise?
>Captcha: TAMG0the machine wants me to eat eggs lmao