クリスマスフェルンさん2
ささきのこ
用戶LoRA
white_breath
Hey all I'm in a bit of a rush right now. This might work with sdxl. But I'm almost certain it will work with pdxl. So I'm just labeling it with pdxl for right now. Chris
This LoRA is trained using game assets from the F&C game "White Breath ~ with faint hope~". The character artist is Takashi Hashimoto who later on worked on "Yosuka No Sora" hence similar art style. (his prior works "Pia Carrot e yokoso 3" and subsequence works have different art style). This model tends to create blurry output. I'm suspecting that it's caused by low-resolution source files. Should I upscale the source image with things like ESRGAN before training the model? let me know in the comments.