did the thing. still experimental
i suggest using 12 steps with the turbo lora i use.
further testing on civitai generator, the difference in quality is insane. i really do suggest using comfyui 4mp for best results for the hi res lora. the v1.0 version does well in low resolutions.
The hires lora can be used up to 1.50 strength or probably more. The images i did with fineview checkpoint model, i used 1.50
Description
I decided to release this early, still experimental, but looks good so far.
I suggest using 4mp resolution. This was trained on 2048 res. not sure how this would affect lower resolutions. surely better right? Probably the first to push moss to this level at high resolution. It all depends on your prompting skills now. Have fun!
I suggest using 12 steps.
Note: generating through civitai wont be as good as using comfyui at 4mp resolution. all my images were generated at 4mp
The hires lora can be used up to 1.50 strength or probably more. The images i did with fine view checkpoint model, i used 1.50














