Simple LORA trained on art of an original character of artist Kotoba Noriaki. The model is supposed to generate (with varying success) Karahara Shima, a gloomy girl with burns across the left half of her face and torso.
This is my first attempt at training a LORA so I will definitely try and improve on this once I get a better grip on training.
v1 Release
This model works reasonably well (I think). Only requires the listed activation tag and works best at a weight between 0.8-1.0 (try using 1.0 in most cases, but consider going down to 0.8 if there is some bad interaction with another LORA, which should hopefully be rare).
The burn scars (at least for a weight of 1.0) should work reasonably well now, but if they don't just add another "burn scars" into the prompt (and play around with the tag weight until it looks nice).
Description
I turned down the LORA network dimension to 4 (with an alpha of 2), which seems to have improved the quality of results pretty well.
Results are now fairly consistent with much less need to specify characteristics. However the burn marks may still be somewhat finicky, try adding "burn scars" to your tags and experiment with weights until you like the results. Location of the marks is semi-consistent.
Training info: 7 epochs on 29 images with 10 repetitions each. Learning rate of 5e-4.
I trained a total of 10 epochs, but the later ones would yield worse results presumably due to overcooking.
FAQ
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.