This is a Xiaomi su7 lora based on XL model training

Recommended parameters:

Model: sd_xl_base_1.0.safetensors

Steps: 25-35,

Sampler: DPM++ 2M Karras

Weight: 0.6-0.8

Enable Refiner

Model: sd_xl_refiner_1.0.safetensors 0.8

Trigger word: misu7

Positive:

misu7,Best quality,4k,ultra details,canon,film still,red color,side view,cyberpunk style,speeding through city The streets, "lora: misu7_lora_sdxl - 000003:0.6 >,

Negative:

(worst quality, low quality:1.4), lowres, text, (nsfw:1.3), (normal quality:2), watermark, cropped,