D-ART Artist Style LoRA (Noob Vpred)

MUCH larger dataset (85 images) - first autotagged and then manually checked, removing unnecessary tags/adding missing tags to images as needed.

ALL watermarks removed from training images (yes, ALL. Thanks IOpaint!)

pre-downscaled images before training using custom image downscaling script

• sd-scripts does this already, but I wanted to achieve a higher downscale quality, using a script that downscales the images using a combination of Lanczos (40 %) and LSID (60%) algorithm by blending images from both algorithms together at mentioned percentages.

  • LSID from paper: https://arxiv.org/abs/2510.24334

using edm instead of minsnr for timestep correction/training

final lora model is a 50/50 blend of epoch 25 and epoch 35, using the lora-merger in sd-scripts.

resized lora using this script, with a threshold of 2.85, shaving off 30-35 MBs and reducing overfitting:

• https://github.com/elias-gaeros/resize_lora