Sign In

KantanMIX XLIllustrious noobai

67
347
16
Updated: Dec 13, 2024
base modelanime
Verified:
SafeTensor
Type
Checkpoint Merge
Stats
347
Reviews
Published
Dec 13, 2024
Base Model
Illustrious
Usage Tips
Clip Skip: 1
Hash
AutoV2
514D57CD1E

KantanMIX XLIllustrious noobai v15 vaked VAE

いつも使用していたモデルが使用出来なくなった為、自分が使いやすい様に簡単にマージした物です

他の方には使いにくいかもしれません

The model I usually use is no longer available, so I simply merged it to make it easier for me to use. It may be difficult for others to use.

***************************************************

Base Model

L_A_X様

noobaiXLNAIXL_epsilonPred11Version (55%)

https://civitai.com/models/833294?modelVersionId=1116447

Weighted sum

rqdwdw様

obsessionIllustrious_v10 (22.5%)

https://civitai.com/models/820208?modelVersionId=917170

WAI0731様

WAI-NSFW-illustrious_v7 (22.5%)

https://civitai.com/models/827184?modelVersionId=1068947

vaked VAE

https://huggingface.co/stabilityai/sdxl-vae/tree/main

***************************************************

******Quality Prompt******

masterpiece,best quality,good quality,newest,

******Negative prompts******

lowres, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, old, oldest

*********************************************

Euler a か DPM++ 2M ステップ20~30

CFGスケール 5.5~7

高解像度補助:R-ESRGAN 4x+ Anime6B,倍率1.5倍、ステップ5~15、デノイジングストレングス0.5~0.6

ADetailerを使用しface_yolov8nで顔修正を行っています。

LORA recommended weight: 0.8~1.0,

Euler a or DPM++ 2M  Step 20~30

CFG Scale 5.5~7

High resolution auxiliary: R-ESRGAN 4x+ Anime6B, 1.5x magnification, step 5~15,Denoising strength 0.5~0.6

I am using ADtailer to modify the face with face_yolov8n.

*********************************************

"ADetailer"

(インストールは自己責任でお願いします)(Please install at your own risk.)

顔の詳細を修正する追加機能

Additional features to correct facial details

https://github.com/Bing-su/adetailer