Iscrizione PixAI
PixAI
PixAI
Generate
Sign in
Home
Generazione
Modelli
Studio
NEW
Contest
Crea con Mio.2
Toolbox
NEW
Guide

User LoRA

XL
Character

Hero's Daughter / Tabitha / タバサ PONY - DRAGON QUEST V (5)

#Dragon Quest

Crea

  • Generatore di immagini IA
  • Generatore di animazioni IA
  • Toolbox
  • Generatori tematici
  • Allena LoRA
  • Agente Mio.2
  • Studio

Scopri

  • Trending Tags
  • Classifica
  • Market dei modelli
  • Contest
  • Notizia

Informazioni

  • Guide
  • Come utilizzare PixAI
  • Tsubaki.2
  • Scopri Mio
  • Regole sui contenuti

Prezzi e assistenza

  • Appartenenza
  • Pacchetti di crediti
  • Contatto

App mobile

  • App Store
  • Google Play
© 2026 PixAI
  • Termini di servizio
  • Informativa sulla privacy
  • Politica sul copyright
  • Legge sulle transazioni commerciali specificate
Hero's Daughter / Tabitha / タバサ PONY - DRAGON QUEST V (5) - AI Model cover image
Caricato su
4 ago 2024, 17:24
Utilizzi
20.3k
Reviews
Excellent  (1)
Parole d'ordine

ctiantabitha, blue eyes, sleeveless dress, belt, purple cape, white footwear,

Permessi
  • Allow image generation & sharing
  • Permettete agli utenti di scaricare il vostro modello
  • Usi commerciali

Recommended LoRAs

Cheria Barnes / シェリア・バーンズ  Young and Adult - (3 OUTFITS)  Tales of Graces テイルズ オブ グレイセス - AI Model cover image

User LoRA

Cheria Barnes / シェリア・バーンズ Young and Adult - (3 OUTFITS) Tales of Graces テイルズ オブ グレイセス
24
Ran Mori from Detektiv Conan/Meitantei Konan - AI Model cover image

User LoRA

Ran Mori from Detektiv Conan/Meitantei Konan
7
bugcat capoo - AI Model cover image

User LoRA

bugcat capoo
0
Rei Todoroki 轟冷 - My Hero Academia - AI Model cover image

User LoRA

Rei Todoroki 轟冷 - My Hero Academia
1

Descrizione

https://civitai.com/models/536128

(Civitaiより転載。制作ありがとうございます。もしご自分でアップロードされるようでしたらお知らせ下さい。 Thank you to the creators. If you prefer to post it yourself, please leave a comment, and I will remove it.)


IMPORTANT: READ BELOW if you want you can prompt for her weapon by putting prompt "weapon on back" i tagged it, it is very inconsistent so probably just don't use it

Trigger words: ctiantabitha, blue eyes

Clothing: sleeveless dress, belt, purple cape, white footwear,

Example Positive prompt ✅: score_9, score_8_up, score_7_up, source_anime, masterpiece, 1girl, ctiantabitha, blue eyes, sleeveless dress, belt, purple cape, sitting, restaurant, eating burger, depth of field,

Negative prompt ❌: score_4, score_5, score_6, source_cartoon, source_furry, source_pony, sketch, 3d, painting, monochrome, dust particles, full body,

Recommended resolution, aspect ratio for sdxl, pony 📷 768 x 1344: Vertical (9:16) 832 x 1216: Portrait (4:5) ** 1024 x 1024: Square (1:1) 1182 x 886: Photo (4:3) 1254 x 836: Landscape (3:2) 1365 x 768: Widescreen (16:9)

Work flow, procedure 🔧

  1. Collect dataset (booru, anime screencaps, search)
  2. Clean up dataset using upscalers, inpainting and photoshop
  3. Tag dataset using booru github
  4. Train LoRa in kohya ss locally github
  5. Test epochs using xyz grid in controlnet to ensure LoRa is not overfitted/underfitted.
  6. Submit model to CivitAI profile https://civitai.com/user/ctian

do not ask me training parameters, check lora metadata for training parameters

Commenti