Recommended Settings(VAE is baked in):
Res: 832*1216 (For Portrait, but any SDXL Res will work fine)
Sampler: DPM++ 2M SDE
Steps: 30-40
CFG: 3-6 (less is a bit more realistic)
Negative: Start with no negative, and add afterwards the Stuff you don´t wanna see in that image.
VAE is already Baked In
HiRes: 4xNMKD-Siax_200k with 15 Steps and 0.3 Denoise + 1.5 Upscale
Used version 12 as the base for training to bring it back into photorealism. Trained another NSFW set on SDXL (using Booru tags). Then trained the same NSFW set again, this time using the great Lustify Model by Coyotte as the base.
Both NSFW sets were then merged into the trained photorealism model (0.15 ratio for the trained SDXL NSFW set and 0.1 ratio for the trained Lustify set)
Both NSFW sets were then merged into the trained photorealism model (0.15 ratio for the trained SDXL NSFW set and 0.1 ratio for the trained Lustify set)