Sign In

takeshima_eku_style

54

379

260

20

Updated: Aug 9, 2025

style

Verified:

SafeTensor

Type

LoRA

Stats

177

193

109

Reviews

Published

Aug 9, 2025

Base Model

Illustrious

Training

Steps: 1,600
Epochs: 10

Usage Tips

Clip Skip: 2
Strength: 0.8

Trigger Words

t4k3sh1m4_3ku_style

Hash

AutoV2
59E93F0A36
default creator card background decoration
123qu's Avatar

123qu

v1.5: trigger word changed to t4k3sh1m4_3ku_style

make the model slightly less wonky with some type of images, but it is still better to post processing those images for better quality

v1.0

trigger word: takeshima_eku_style

known problem:

  • when creating full_body character (head to toes, standing, direct view), you would get really bad face, this was due to biased training data, please manually fix by using hi-res fix, or cutout and upscale to img2img, or any other method (refer to the last example) turned out the original model also isn't really good with this particular type of image, so a lora wouldn't be able to change that

  • big_breasts tag destroyed the shading style, for whatever reason lol