I loved the iDOLM@STER MILLION LIVE & NIPPAN collab PR cards… so I made LoRAs on them!
I found out there was a full body image for these. (I removed the background myself and then added a white background with a teal outline, and then upscaled it since the original was too small)
Due to the dataset really being 10 copies of the same image, it will generate mostly the same thing... same pose, same face, same facial expression, same manga books being carried... even the hand pinching her glasses. Since it's a smaller view however, it won't look that great.
If you want more freedom when generating, it's better to use it at a lower weight.
