PixAI Membership
PixAI
PixAI
Generate
Sign in
Home
Generation
Models
Studio
NEW
Contest
Create with Mio.2
AI Tools
NEW
Guide

User LoRA

XL

Yamamoto Souichirou Style

#Forehead

Create

  • AI Image Generator
  • AI Animation Generator
  • AI Tools
  • Thematic generators
  • Train LoRA
  • Mio.2 Agent
  • Studio

Discover

  • Trending Tags
  • Ranking
  • Model Market
  • Contest
  • News

About

  • Guide
  • PixAI Blog
  • Tsubaki.2
  • Meet Mio, Our Mascot
  • Content Rules

Pricing & Help

  • Membership
  • Buy Credits
  • Contact

Mobile App

  • App Store
  • Google Play
© 2026 PixAI
  • Terms of Service
  • Privacy Policy
  • Copyright Policy
  • Specified Commercial Transactions Law
Yamamoto Souichirou Style - AI Model cover image
Trained by
Avatar image of pettankoutei

pettankoutei

Uploaded at
Mar 17, 2024, 3:19 AM
Uses
52.1k
Reviews
Excellent  (3)
Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Recommended LoRAs

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

User LoRA

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

User LoRA

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

User LoRA

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

User LoRA

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.

Comments