Trained with 250 images on PonyDiffusionV6. The samples were generated with AutismMix.

Trigger: andava_style

Recommended settings:

• Sampler: DPM++ 2M Karras / Euler a - 25-30 steps

• CFG: 7

• Resolution: 1024*1024, 832*1280, 1280*1024

• Lora weight: 0.8

• HighRes: 4x_NMKD-Siax_200k, upscale by 1.5x, 20 steps, 0.35 denoising

• Clip skip: 2