home models images videos posts articles bounties tools challenges events updates shop

【Art Style】Kyrie Meii Style

Name: 【Art Style】Kyrie Meii Style
Rating: 5 (144 reviews)
Author: zakp

162

1.2k

214

Updated: Oct 5, 2024

style

art style girls 2.5d

Verified: 2 years ago

SafeTensor

Details

Type	LoRA
Stats	786 210
Reviews	Very Positive (103)
Published	Apr 30, 2023
Base Model	SD 1.5
Training	Epochs: 6
Trigger Words	kyrie-style
Hash	AutoV2 A39C7F2AC6

1 File

About this version

zakp

Introduction

A LoRA model trained with ~120 images by Kyrie Meii. The trigger tag is 'kyrie-style'. The 784mb VAEs (NovelAI, Anythingv3, Orangemix, Counterfeit) are recommended. 0.6 ~ 0.8 weights are good. The preview images are generated using 1.6 version (original) YesMix.

Cautions (Must Read)

For anime model,

pls disable 'face restoration' during generating.

Some preview images are generated using 'Hires Fix' and upscaled using 'SD Upscale'. 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.