Open tazlin opened 11 months ago
Or this https://gist.github.com/laksjdjf/487a28ceda7f0853094933d2e138e3c6
Update: this is now built into ComfyUI as PatchModelAddDownscale node https://github.com/comfyanonymous/ComfyUI/commit/bd07ad1861949007139de7dd5c6bcdb77426919c
Currently hires fix runs an initial image job at the number of input steps. If the user requests 30 steps, the worker generates a 30 step image latent with the resolution of the smallest side pinned to 512 (and the longer side, if the sizes don't match, is set so the aspect ratio is respected). The worker then runs that image latent using the same number of steps (e.g., 30 as in this example) at the final resolution.
Some thoughts on improvements: