Członkostwo PixAI
PixAI
PixAI
Generate
Sign in
Strona główna
Generowanie
Modele
Studio
NEW
Konkurs
Utwórz z Mio.2
Skrzynka narzędziowa
NEW
Guide

SDXL

Mol_Keun Mix

#Furry

Twórz

  • Generator obrazów AI
  • Generator animacji AI
  • Skrzynka narzędziowa
  • Generatory tematyczne
  • Trenuj LoRA
  • Agent Mio.2
  • Studio

Odkrywaj

  • Popularne tagi
  • Ranking
  • Rynek Modeli
  • Konkurs
  • Aktualności

O nas

  • Guide
  • Jak używać PixAI
  • Tsubaki.2
  • Poznaj Mio
  • Zasady treści

Cennik i pomoc

  • Członkostwo
  • Pakiety kredytów
  • Kontakt

Aplikacja mobilna

  • Pobierz aplikację PixAI
  • App Store
  • Google Play
© 2026 PixAI
  • Regulamin
  • Polityka prywatności
  • Polityka praw autorskich
  • Attributions
  • Ustawa o Określonych Transakcjach Handlowych
Mol_Keun Mix - AI Model cover image
Przesłano
25 sie 2025, 18:47
Użycia
6.1k
Opinie
Doskonały  (1)
Kroki próbkowania

30

Metoda próbkowania

DPM++ 2M SDE Karras

Skala CFG

4

Niepożądane

worst quality, low quality, lowres, off-topic, old, early, signature, watermark, censored, not furry, humanoid face, humanoid feet, humanoid ears, humanoid hands, chibi inset, character doll

Uprawnienia
  • Allow image generation & sharing
  • Zezwól użytkownikom pobierać Twój model
  • Zastosowania komercyjne

Recommended LoRAs

Background Enhancer [SDXL] - AI Model cover image

User LoRA

Background Enhancer [SDXL]
6.71k
ModelBoosterXL - AI Model cover image

User LoRA

ModelBoosterXL
25.09k
Detailed anime style - SDXL_pony - AI Model cover image

User LoRA

Detailed anime style - SDXL_pony
12.10k
Detail Tweaker XL - AI Model cover image

User LoRA

Detail Tweaker XL
8.10k

Opis

https://civitai.com/models/135477?modelVersionId=1861912

[DeepNavy] I worked on removing the noise that used to appear around the eyes and nose in previous versions. As a result, there are quite a few differences from the original DeepBlue model, but I feel that this version understands prompts much better. You can now use the Euler a sampler without getting any of that noise.

Recommended Parameters:

Sampler: Euler a

CFG Scale: 3 – 5

Steps: 20 – 30

Clip Skip : 2

[DeepBlue] This is a merged model using a different base model instead of the original(V1~V3) model. I tried to keep the feel as similar as possible, but since the model and LoRAs are entirely different, I adjusted the weights one by one during the merge.

Recommended Parameters:

Sampler: DPM++_2M_SDE

CFG Scale: 3 – 5

Steps: 20 – 35

Clip Skip : 2

Recommended Prompt:

1girl, furry female, anthro, kemono, digitigrade, body fur, rating explicit

Recommended Negetive:

worst quality, low quality, lowres, off-topic, old, early, signature, watermark, censored, not furry, humanoid face, humanoid feet, humanoid ears, humanoid hands, chibi inset, character doll

[DeepViolet] Vpred Model

Make sure you know how to use it properly

[Noob AI] Recommended Parameters:

Sampler : DPM++_2M_SDE

Steps : 24

CFG Scale : 3.5

Clip Skip : 2

Recommended Prompt:

1girl, furry female, anthro, kemono, digitigrade, body fur, rating_explicit, ~prompt BREAK masterpiece, best quality, amazing quality, very aesthetic, absurdres, newest

Recommended Negetive:

worst quality, low quality, lowres, off-topic, old, early, chromatic aberration, abstract, jpeg artifacts, scan artifacts, signature, watermark, logo

[ILXL] Recommended Parameters:

Sampler : euler a

Steps : 28

CFG Scale : 5.5~6

Clip Skip : 2

Recommended Prompt:

1girl, furry female, anthro, kemono, digitigrade, body fur, rating_explicit, masterpiece, best quality, amazing quality, very aesthetic, absurdres, newest

Recommended Negetive:

worst quality, low quality, lowres, off-topic, old, early, chromatic aberration, abstract, jpeg artifacts, scan artifacts, signature, watermark, logo, english text, nesoberi, censored

Komentarze