You can use it with any model trained in 1.4 or 1.5, even 2.0 512x. A while back I made a 3D model of Undyne from Undertale, this is the Lora based on it. The 3D model has been available for free and lots of people have made wonderful renders and animations with it. Keyword is Wo262Undyne. Woman or Undyne may also work for more generic results, or by adjusting the lora's weight. Please give it a try and push it to the limits, show me where it breaks and share where it could be improved. Thank you

Wo!262's Undyne

You can use it with any model trained in 1.4 or 1.5, even 2.0 512x. Merge of two LoRAs trained over basic SD1.4, on the same images and parameters with different amount of training steps. Averages to 30 steps/image over 90 training set images, half of them being crops of her face.This improves over my previous tests by converging on the face more easily on 20 samples. It used to take 100 samples to converge. Her face is the hardest part due to its unusual cartoonish nature, so I tried skewing the training data towards her face, but now it's more heavily biased towards portraits. It's also biased against clothing so use clothing keywords when needed. When doing fullbody, face inpainting is highly recommended. Also, back shots are hard because it always tries to portray her from the front, leading to bad anatomy.

Files with SHA256: 85da147add0ef18b71040d6aea0995d0da4ec13cb49a08f3153712e157871183