Very experimental LoRA that attempts to replicate the style from the chapter covers (see training data or look it up) of the niche manga "Azure and Claude," which I happen to like. It didn't expect it to be good at all but it can produce some amazing results. Decided to post despite me not intending to do so.
MORE INFO IN VERSION NOTES
Notes
Need a lot of color-related keywords to get the style of the training images, but still looks cool without (I suggest low saturation, watercolor, light colors, etc), can look at example images
Works best at strength 0.6-0.8
Info
Trained with AbyssOrangeMix2 (SFW)
Image Set: 10
Training Resolution: 512x512
1- النموذج المعاد النشر هو فقط لأغراض التعلم والتبادل والمشاركة، حقوق النشر والتفسير النهائي تعود للمبدع الأصلي.
2- إذا رغب المبدع الأصلي للنموذج في استلام نموذجه، يرجى التواصل مع موظفي SeaArt AI عبر القنوات الرسمية للتوثيق والاعتماد. نحن نلتزم بحماية حقوق كل مبدع. انقر للاستلام
