Sign In

【Art Style】Hyulla Style

836
4k
14.9k
28
Updated: Oct 5, 2024
styleart stylegirlsanime style
Verified:
SafeTensor
Type
LyCORIS
Stats
3,051
5,644
Reviews
Published
Apr 5, 2023
Base Model
SD 1.5
Training
Epochs: 8
Trigger Words
hyulla
shiny skin
Hash
AutoV2
070C62A4AD
ZA
zakp

2023/4/6 update

Just update preview images.

2023/4/5 update

Upload Lycoris version (smaller file size). v1.0 version is conventional LoRA model.

Introduction

A conventional LoRA model trained with ~70 images by Hyulla. The trigger tag is ‘hyulla’. 0.6 ~ 0.8 weights are good. The preview images are generated using 1.6 version (original) YesMix.

Cautions (Must Read)

  • Some preview images are generated using hires fix. Thus, if you wanna generate the preview images, pls download the original preview images and analyze them using 'PNG INFO' in webui to get all generating information.

  • The maximum of generating resolution should not exceed 1024 theoretically, otherwise extra/deformed head/limbs will be waiting for you :). Try to use 'hires fix' to prevent this problem and help to generate higher-resolution images.

  • For 784mb VAEs (NovelAI, Anythingv3, Orangemix, Counterfeit) users, make sure add '--no-half-vae' in command line of webui to prevent generating black images. See voldy's log for the details of edit method. For high-performance GPU, make sure 'medvram' and 'lowvram' mode are disabled.