Adhésion à PixAI
PixAI
PixAI
Generate
Sign in
Accueil
Génération
Modèles
Studio
NEW
Concours
Créer avec Mio.2
Boîte à outils
NEW
Document PixAI

LoRA utilisateur

XL

Yamamoto Souichirou Style

#Forehead

Créer

  • Générateur d’images IA
  • Générateur d'animation IA
  • Boîte à outils
  • Générateurs thématiques
  • Entraîner un LoRA
  • Agent Mio.2
  • Studio

Découvrir

  • Tags tendance
  • Classement
  • Marché des modèles
  • Concours
  • Nouvelles

À propos

  • Document PixAI
  • Comment utiliser PixAI
  • Tsubaki.2
  • Découvrir Mio
  • Règles du contenu

Tarifs et aide

  • Adhésion
  • Packs de crédits
  • Contact

Application mobile

  • Télécharger l'application PixAI
  • App Store
  • Google Play
© 2026 PixAI
  • Conditions d'utilisation
  • Politique de confidentialité
  • Politique de droits d'auteur
  • Loi sur les transactions commerciales spécifiées
Yamamoto Souichirou Style - AI Model cover image
Formé par
Avatar image of pettankoutei

pettankoutei

Téléchargé à
17 mars 2024, 03:19
Utilisations
52.2k
Avis
Excellent  (3)
Permissions
  • Autoriser la génération et le partage d'images
  • Permettre aux utilisateurs de télécharger votre modèle
  • Utilisations commerciales

LoRAs recommandées

Filene / フィルレイン (Shadowverse) - AI Model cover image

LoRA utilisateur

Filene / フィルレイン (Shadowverse)
5
DIZZY--Guilty Gear Strive - AI Model cover image

LoRA utilisateur

DIZZY--Guilty Gear Strive
17
3D 風 XL - AI Model cover image

LoRA utilisateur

3D 風 XL
70
MYRHA-Ψ00 | by UTdT 69 - AI Model cover image

LoRA utilisateur

MYRHA-Ψ00 | by UTdT 69
13

Description

https://www.buymeacoffee.com/pettankoutei If you like my content consider supporting me! 😊 1 Cookie = Early access to future releases! 🍪❤️ Locon trained on the style of Yamamoto Souichirou for Pony Diffusion v6 XL based models.All sample images uses a weight of 0.8 and no trigger word.Since it is prominent in this specific style, the tag 'forehead' makes the style closer to the original. Also, the tag 'grin' is highly recommended 😊.In my opinion the end result looks very close to the artist's illustrations, but I think sometimes it might negatively affect body composition or hand/feet anatomy. For that reason I made 'special mix' version: a couple of community Loras of similar style at very low weights merged to the original trained model. The end result is very slightly different, but I think I managed to improve the aspects mentioned while retaining 95% of the original style. Personally I'm statisfied with both results, so I'll be releasing both versions.To sum it up:V1.0: closer to the original illustrations style. Might have some hand/anatomy problems. Pick this one if you want to use it alone or mix with other styles.V1.0 Mix: still very very close to the original style, but in my opinion a bit more stable.I'm still experimenting with training parameters for Pony and SDXL, so if you have any tips or more advanced knowledge for better training with Pony let me know through Chat/DM.

Commentaires