My RIMIX Style LORA
LORA Based on my model - Ri-mix - [PONY + Illustrious] XL
Settings for CIVITAI On-site Generation
Workflow: Text-to-image Hi-res fix
CFG Scale: 7
Sampler: Euler a
Steps: 30-40
Denoise: 0.35-0.40
My settings for ForgeUI
Generation
Sampling method - Euler a
Schedule type - Automatic
Sampling steps - 30
Dimensions - 768 x 1152
CFG Scale - 6
Highres. fix
Upscaler - None (works for me)
Hires steps - 10
Denoising strength - 0.1
Upscale by - 2
ADetailer
ADetailer detector - Anzhc Face seg 640 v2 y8n.pt / face_yolov8n.pt
Inpaint denoising strength - 0.35
ADetailer steps - 20
ADetailer VAE - sdxl_vae.safetensors
ADetailer sampler - DPM++ 2M
Description
Trained with WAI-NSFW-illustrious-SDXL v11
Note: Thought v3 was over trained made a lite version
Positive and Negative prompt I'm using on ForgeUI.
POS - <lora:Detailer_NoobAI_Incrs_v1:0.75>, masterwork, masterpiece, best quality, dynamic lighting , dynamic pose,, dynamic angle, (lineless:1.2), detailed, depth of field, dynamic lighting, blurry, (cheekbones:0.75),(realistic:1.2)
<lora:zy_illustrious_Realism_Enhancer_v1:0.5> adult, aged up,
NEG - blurry, lowres, worst quality, low quality, bad anatomy, bad hands, jpeg artifacts, signature, watermark, text, logo, artist name, censored, patreon username, (anime:1.2), loli