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

User LoRA

XL
Character

Annie leonhart - Shingeki no kyojin/Attack on Titan - WIT studio S1/OVA

Create

  • AI Image Generator
  • AI Animation Generator
  • Toolbox
  • 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
Annie leonhart - Shingeki no kyojin/Attack on Titan - WIT studio S1/OVA - AI Model cover image
Uploaded at
Apr 11, 2025, 8:08 AM
Uses
1.1k
Reviews
No reviews
Trigger Words

annleo, blonde hair, folded ponytail, grey eyes, pink lips, , belt, thigh_strap, brown jacket, brown skirt, white pants, white hoodie, paradis_military_uniform, hood_down, chest_harness, training_corps_(emblem),

Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Recommended LoRAs

Palpu & Shion - Idol Project / ぱるぷ・蘭々 & 鈴風紫音(アイドルプロジェクト) - AI Model cover image

User LoRA

Palpu & Shion - Idol Project / ぱるぷ・蘭々 & 鈴風紫音(アイドルプロジェクト)
0
Tsukimoto Kizuki Style - AI Model cover image

User LoRA

Tsukimoto Kizuki Style
5
[PonyV6 XL] Okinami (KANCOLLE) - AI Model cover image

User LoRA

[PonyV6 XL] Okinami (KANCOLLE)
0
[Artist] Arekishi Raiho 荒岸 来歩 -il - AI Model cover image

User LoRA

[Artist] Arekishi Raiho 荒岸 来歩 -il
1

Description

Annie leonhart - Shingeki no kyojin/Attack on Titan - WIT studio S1/S2When people ask about the checkpoint and prompts I use, I generally prefer Hassaku XL, mainly because it retains the original LoRA styles more faithfully than other checkpoints. I've noticed other checkpoints often slightly distort the intended aesthetics, especially when working with manga-style LoRAs. Regarding prompts, I typically use 'masterpiece' only in the positive prompt and include 'bad quality' and 'worst quality' in the negative prompt. I deliberately avoid adding terms like 'good quality' 'best quality', or 'official style', since these tend to diminish or override the distinctive characteristics and facial details provided by the LoRA.A huge thank you to everyone who's supported me!The reason I ask for buzz or support, is because I genuinely want to keep creating and updating better LoRAs. People might have noticed that I've been uploading LoRAs much less frequently lately. This is because I'm running low on the buzz I had saved up (around 200K) before I started creating content.Although I am still a half rookie as a trainer. But honestly, I didn't have to share any of these, since I could have just kept them for myself. I chose to upload them hoping for at least some encouragement or support, but if I keep receiving no help at all, I may start keeping my work private going forward. I'm seriously considering this option.

Comments