PDXL Ver
I think it need a little more work, but is pretty good for now! I know what the problem is and for now "simple background" in the negatives is a good enough fix.
This is probably my favorite art style so if you get any good gens please share!
SD 1.5 Ver
Finally got around to fixing this LoRA. Hopefully people like it!
Why doesn't my output look like yours?
Check the negatives in my examples. Do you have those embeds?
I used !ADetailer because it's just a set and forget quality bump.
The images were genned at 512x768 then upscaled 1.5 times using 8x_NMKD-Superscale_150000_G with denoising 0.45. You can find it with a quick Google. Note that this upscaler is non-deterministic from my testing so your images may vary slightly. (Check the bottom of this post for info on the cover image.)
Settings and Training:
Trained on Anything v3
Genned on Anything v4.5
LoRA weight 0.8
Description
Uploading another old model. This model is based on the artist Harada Takehito who is perhaps most famous for his work on the Disgaea series. As such this model will recreate some of the more prominent characters from the series (Etna and Flonne primarily). I do plan to one day update this model to potentially recognize more of Harada's characters.
For fun I prompted some Touhou characters for the demo images too. Not much else to say other than the model was trained on Anything v3. The demo images are from Anything v4.5. Also, I typically run the LoRA at about 0.8.
Enjoy! Let me know if there are any specific Disgaea characters you want that this LoRA can't make.