Hello everyone,

today I upload some character-Model of a requested... well lets call it a "h-comic". The name of the Character is pythia and there will be two model Versions of her: One anime style and the other one realistic.

Model used for realistic: realismIllustriousBy_v50FP16.safetensors.

Also, use "Stable_Yogis_Illustrious_Negatives-neg" (in the Negative prompt) and "Stable_Yogis_Illustrious_Positives" (in the text2img prompt). I’m not sure if it’s mandatory, but I used it because the base model’s page recommends it.

Warning: I never did realistic models before! I hope it will met you expectation, but I am not very sure to be honest. Furthermore, both models are somewhat "noisy" since the training pics contains much noise (e.g. male characters, disembodied limps etc.). Also, you might want to use negative like "blurry, blurry background, blurry forground"

Prompt: look at "Trigger Words" on the right side 👉

Changelog: look at "About this Version" on the right side 👉

quality tags I use:

oekaki, anime coloring, anime screencap, masterpiece, best quality, amazing quality

My Settings (forge)*:

*note, the example images only use high-res fix.

Checkpoint: waiNSFWIllustrious_v150

Sampler: Euler a

Scheduler: Automatic

Samplings Steps: 30 - at least use more than 15! I often see people generate with 8 steps. This it not enough xD (I mean, you should generate you pics the way you want, but the results should be better with more steps)

Hires.fix: R-ERSGAN 4x+Anime6B, 20 Hires steps, Denoising Strength: 0.3-0.5

Extensions (nice to have for little more Details):

Adetailer (highly recommended)

CFGRescale Integrated (forge)

SDXL Styles (anime)

CD Tuner

Detail Daemon

DynamicThresholding

FreeU

SelfAttentionGuidance