The lora model is refined on the basis of 墨幽人造人 v1010,the size of the training base map is 768*768
Positive prompt:absurdres, highres, ultra detailed, (1 young beautiful girl, solo:1.1),realistic,hair ornament, black hair,cowboy shot, hair stick, chinese clothes, dress, looking at viewer, standing, brown eyes, sash, jewelry,blue dress,A fairytale land where magical creatures live and thrive
Parameter selection Steps: 30, Sampler: DPM++ SDE Karras, CFG scale: 7, R-ESRGAN 4X+ Anime6B for HD repair,LORA weights are recommended to be 0.7 to 1, and a weight of 0.85 is sufficient.