Realistic Illustration style model (UPDATED 6/18/25)
Lora based on this model - Ri-mix - Style LORA
Settings for Civitai Generator
My POS and NEG prompt helps
CFG Scale - 5-7
Sampler - Euler a / DPM++ 2M Karras
Steps - 40-50
Denoise - 0.5
____
Process for a better result
Text-to-image Highres fix >>> Image-to-image Face fix >>> Upscale x2
HMU for if you have better settings
My settings for ForgeUI
Generation
Sampling method - Euler a
Schedule type - Automatic
Sampling steps - 20
Dimensions - 768 x 1152
CFG Scale - 6
Highres. fix
Upscaler - None (works for me)
Hires steps - 10
Denoising strength - 0.1
Upscale by - 1.5
ADetailer
ADetailer detector - Anzhc Face seg ??0 v2 y8n.pt / face_yolov8n.pt
Inpaint denoising strength - 0.35
ADetailer steps - 20
ADetailer VAE - sdxl_vae.safetensors
ADetailer sampler - DPM++ 2M
Description
Positive and Negative prompt I'm using on ForgeUI works on on-site generation as well
POS - masterwork, masterpiece, best quality, detailed, depth of field, high detail, very aesthetic, 8k, dynamic pose, depth of field, dynamic angle, adult, aged up
NEG - lowres, worst quality, low quality, bad ???????, bad hands, jpeg artifacts, signature, watermark, text, logo, artist name, extra digits, censored, patreon username, loli