{"id":73484,"modelId":15415,"name":"v5.9","createdAt":"2023-05-17T19:15:28.700Z","updatedAt":"2023-05-17T19:19:07.230Z","trainedWords":["penis","testicles"],"baseModel":"SD 1.5","earlyAccessTimeFrame":0,"description":"
Generate using a weight of 0.4-1 like this: <lora:GirlyPenisv509:0.65>
This version is better at doing the different concepts. But I'm still trying to improve it!
Weight higher than 0.65 have a strong effect on art style so keep that in mind!!!
How I archived my generations:
txt2img: DPM++ SDE Karras with 20 steps,512x512(can go up to 768 for wide or tall), Restore faces on (using CodeFormer weight 1.0 in Settings), Hires-fix on, to 1024x1024 (double original size) with your preferred upscaler and Denoise 0.5, CFG 7. Then send to img2img!
img2img: DPM++ SED Karras with 20 steps, Restore faces on (CodeFormer weight 1), rescale to 1536x1536, CFG 7, Denoise between 0.3-0.7 (based on how much you want to improve the image), SAME PROMPT! Send to extras when happy with img2img/inpaint results.
extras: Scale to x3 (final will be 4608x4608, I suggest going lower, I did x3 just for the samples here) Upscaler 1 - FatalAnime 4x, Upscaler 2 - SwinIR 4x with 0.10 visibility, GFPGAN 0.10 visibility, CodeFormer 0.10 visibility.