PixAI-Mitgliedschaft
PixAI
PixAI
Generate
Sign in
Startseite
Generation
Modelle
Studio
NEW
Wettbewerb
Mit Mio.2 erstellen
Toolbox
NEW
PixAI-Dokument

Benutzer-LoRA

XL

[XL&1.5] 2B (‎YoRHa No.2 Type B) Nier:Automata

#Mature Female#NieR#Girl#NieR:Automata

Erstellen

  • KI-Bildgenerator
  • KI-Animationsgenerator
  • Toolbox
  • Themengeneratoren
  • LoRA trainieren
  • Mio.2 Agent
  • Studio

Entdecken

  • Angesagte Tags
  • Rangliste
  • Modell-Marktplatz
  • Wettbewerb
  • Nachricht

Über uns

  • PixAI-Dokument
  • So verwendest du PixAI
  • Tsubaki.2
  • Mio kennenlernen
  • Inhaltsregeln

Preise & Hilfe

  • Mitgliedschaft
  • Credit-Pakete
  • Kontakt

Mobile App

  • App-Store
  • Google PlayStore
© 2026 PixAI
  • Nutzungsbedingungen
  • Datenschutzbestimmungen
  • Urheberrechtsrichtlinie
  • Gesetz über bestimmte kommerzielle Transaktionen
[XL&1.5] 2B (‎YoRHa No.2 Type B) Nier:Automata - AI Model cover image
Hochgeladen am
13.06.2024, 00:48
Verwendet
990
Bewertungen
Exzellent  (1)
Auslösende Worte

yorha2b, 2bblindfold

Berechtigungen
  • Bildgenerierung und -freigabe erlauben
  • Nutzern erlauben, dieses Modell herunterzuladen
  • Gewerbliche Nutzung

Empfohlene LoRAs

Mamar | Illustrious | A Rank party (Aparida) - AI Model cover image

Benutzer-LoRA

Mamar | Illustrious | A Rank party (Aparida)
7
Suzuki Momo | InCha Couple ga You Gal-tachi to SEX Training Suru Hanashi - AI Model cover image

Benutzer-LoRA

Suzuki Momo | InCha Couple ga You Gal-tachi to SEX Training Suru Hanashi
9
ボア・ハンコック - AI Model cover image

Benutzer-LoRA

ボア・ハンコック
7
Boruto Uzumaki (Timeskip) TBV - AI Model cover image

Benutzer-LoRA

Boruto Uzumaki (Timeskip) TBV
0

Beschreibung

SDXL 2.0Dataset overhaul, the face and outfit is more consistent.Adding some pose images, some poses can be achieve without using the ControlNetRecommended checkpoint: TurboVisionXL, DreamshaperXL, the preview pics also using those.Since the dataset was captured from the 3D model, adding the photograph style prompt will help to mitigate the "3D-like" feeling.TurboVisionXL works very good when blending the character into the background.Outfit prompt (SDXL 2.0):Skirt:black dress, black hairband, black gloves, cleavage cutout, juliet sleeves, thigh boots, black thighhighs, turtleneckno skirt:leotard, black hairband, black gloves, cleavage cutout, juliet sleeves, thigh boots, thighhighs under boots, black thighhighs, turtleneckV3.0/SDXL 1.0Dataset and reg set overhaulLowering the weight of the original outfit, now able to change clothes without dealing with Lora block weightAdetailer and Hires.fx help face generation by a lot, highly recommend using them.Weight: 0.5-0.75, I'm using around 0.65 in my demo picsWork with realistic and also anime style checkpointBase model: Chilloutmix-NiWorks with most Asian face checkpoint models, some Western face models also work, but the body ratio and the face are somewhat weird. The weight for my generate pics is 0.75V2.0Modified dataset, removing the yellowish and greyish lookingModified reg set, changing background is much easier than the previous versionReproduce the original game look of 2B in NieR: Automata, mainly focusing on her face, so no blindfold is offered in this version. The 0.65-0.9 range seems to work the best. The skirt and skirtless variants can be switched by using the "black skirt" and "white leotard" prompts. Highly recommend using it with Adetailer and Hires.fix, it helps face generation by a lot. Since there's only one outfit in my dataset, if you want to change the clothes, you need to use Lora block weight plugin to lower the corresponding weight.着重还原游戏里2B的形象, 推荐权重0.6-0.8, 可以通过black skirt和white leotard的提示词来切换无裙子有有裙子版本. 最好能配合Adetailer和Hires.fix一起用, 能极大减少脸崩的可能性. 因为训练集就一套衣服, 所以衣服基本是过拟合的, 想换衣服得用Lora block weight去降低相应的权重

Kommentare