Fot best outputs:

Sampler: DPM++ 2M Karras

Steps: 20, cfg 5 ~ 7, CLIP skip 2.

VAE: kl-f8-anime2_fp16.safetensors

LoRa "more_details" with weight 0.4 in the pos (included in the galleries)

Common neg for humans: "desaturated, (3 arms), (3 legs), ng_deepnegative_v1_75t, (badhandv4:1.2), (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, ((monochrome)), ((grayscale)) watermark, bad-hands-5", embeddings ng_deepnegative_v1_75t, badhandv4 and bad-hands-5 included in the galleries.

This model is the "somber" version of MajicMix Lux. It focuses on the shadows and darkness rather than light plays.