(Don't forget to share your creations and tell me if you find an error in the outputs)
Made with 30 images, average image size: 512x512 (Upscaled)
Recommended between 0.8 and 1 network multiplication
Trained on AbyssOrangeMix2-nsfw (I used negative prompts, selected this model because I like it because I had problems with Anything v3 results)
Errors with clothes (colors different from prompt) should be fixed, tell me if you find it recurrently
I'm planning to do some others characters of the series, if you want I prioritize one, ask me and I will see if I can
Description
Made some changes in the embeddings to make it able of using different clothes
Realistic Style still with problems, working to solve that
If you find another problem, let me know and will work on fixing it
FAQ
Comments (3)
Great work, are you still doing these? I would like to try one for Constanze
Hello, I stopped doing LoRAs as google colab banned the use of UIs like Stable Diffusion, so I'm trying to find alternatives on what I can do, until that, I will not be able to continue doing LoRAs, sorry for the problems
@Beinded I see, thank you anyways
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.