All Sample image are made Base SDXL_1.0 with Hi-res fix only - ( No refiner )

This Loras make images more aesthetic, detailled .

Two versions : xl_more_art-full-beta2 (more artistic/creative) & xl_real_beta1 (more photorealistic)

Please help me :

Add to your collection and share your creations here !

This Lora make images more creative, aesthetic, detailled.

• weight 0.7 is a good value for cfg scale >= 7

• weight 0.8-1.0 are a good values for cfg scale 5.5-7.0

• weight 0.1-0.3 is a good value for small changes

Trained with 8 epochs on 14k steps

Artistic image are used to train this lora