(More reliable LoRA model of this character below the description)

Version 0.5

• Trained with 20 pictures mainly screenshot from the official game and some official art.

• I think because lack of background in the dataset made this model generated random background sometimes, so it's recommended to use "(simple background:0.8, plain background:0.8, white background:0.8)" to reduce the random/abstract background.

• Info about the prompt, model, sampler etc. are in the image above.

Version 1.0

• Soon