It's trickier than I thought it would be.
Here are a few in Degar style I made after training for 2,500 steps. I'd love to hear what you think of them. To my (untrained) eye, they seem a little too defined, perhaps?
Here are a few in Degar style I made after training for 2,500 steps. I'd love to hear what you think of them. To my (untrained) eye, they seem a little too defined, perhaps?
A possible solution may be to incorporate artificial images in the training data. So, create an initial LoRA with the original Degas images and generate 500 images. From those generated images, pick the ones that most resemble Degas. Add those to the training set and train again. Repeat until (hopefully) it learns the correct style.
Whatever they're doing at Midjourney is still impressive. No training needed and a better result.