information

this is a very experimental noobai vpred merge, alot of models were used, but that is the base model as target. it has train difference from lustify implanted into it using subtraction from sdxl base (via perpendicular component), which improves character ??????? and backgrounds.

i used sd-mecha via comfy-mecha for most of this, using many of it's methods like tensor sums, rotate, quotient multiplication etc. and a modified karcher-mean script. (original source)

(the diff from the source is that all tensors are converted to a float type for the calculation and then it converts the final result back to the original data type to maintain model integrity.)

recommended settings

interface: comfyui or reforge

samplers: res_multistep or euler (and their cfg++ variants)

schedulers: either beta or ays+ (alignyoursteps but with sigma set at 0, it's available here)

step count: around 20