Style - Hitomaru/人丸

Details

Download Files

Model description

Trained on NoobAI V-Prediction.
Trigger word

h1t0maru

Recommended strength is 0.8 on NoobAI; using 1.0 may make the image too blurry.

Due to the selection of regularization images, I found some tags may cause lora be less effective, for example "azur lane". If you notice any other tags, please tell me and I will adjust regularization images for the next train.

V2

  • Switch to LoKr training.

  • Added trigger word.

  • Added Regularization images.

  • Removed old images; added latest curated samples.

  • Model size reduced.

V1

  • Trained on Noob V-Prediction

  • No triger word

  • LoRA

Images made by this model

No Images Found.