Agathe Auproux : Realistic version: v1.0: AgatheAup_v1_SD15.safetensors

Trained on the epiCPhotoGasm-Z model and should therefore be used with this model for perfect use.

I'm looking for photographic rendering only, I'm not interested in 3D or 2D rendering. So my Lora will probably never be trained on base model versions.

• I only recommend using After Detailer when used without glasses

• Trigger token is ohwxap

• Can be used at an intensity of 1.0 but I always prefer to stay at 0.9

• Don't forget to add asian, in negatives prompts, even though she has Asian features, the AI tend to mistakenly thinks she's really Asian

Info about train settings :

• LoRA trained with a dataset of 120 images / 8 repeats / 20 epoch with batch size at 2.

• Mixed and save precision = bf16

• Optimizer = AdamW 

• Resolution = 768x768px