Ahli PixAI
PixAI
PixAI
Generate
Sign in
Laman Utama
Jana
Model
Studio
NEW
Kontes
Cipta dengan Mio.2
Kotak Alat
NEW
Guide

User LoRA

SD

Oguri Cap (umamusume)

Cipta

  • Penjana Imej AI
  • Penjana Animasi AI
  • Kotak Alat
  • Penjana Tematik
  • Latih LoRA
  • Ejen Mio.2
  • Studio

Temui

  • Tag Popular
  • Ranking
  • Pasaran Model
  • Kontes
  • Berita

Tentang

  • Guide
  • Cara Menggunakan PixAI
  • Tsubaki.2
  • Kenali Mio
  • Peraturan Kandungan

Harga & Bantuan

  • Keanggotaan
  • Pek Kredit
  • Kontak

Aplikasi Mudah Alih

  • App Store
  • Google Play
© 2026 PixAI
  • Syarat Perkhidmatan
  • Dasar Privasi
  • Dasar Hak Cipta
  • Undang-undang Transaksi Komersial Tertentu
Oguri Cap (umamusume) - AI Model cover image
Dimuat naik pada
1 Apr 2023, 1:15 PG
Kegunaan
19.5k
Ulasan
Cemerlang  (4)
Kata Pencetus

Oguri Cap (umamusume)

Kebenaran
  • Allow image generation & sharing
  • Benarkan pengguna memuat turun model anda
  • Kegunaan komersial

Recommended LoRAs

Konjiki no Yami (Golden Darkness) 金色の闇 / To Love Ru - AI Model cover image

User LoRA

Konjiki no Yami (Golden Darkness) 金色の闇 / To Love Ru
35
Kyoko Sakura (Swimsuit) - AI Model cover image

User LoRA

Kyoko Sakura (Swimsuit)
3
Yoshika Miyafuji (宮藤 芳佳) - Strike Witches (ストライクウィッチーズ) - AI Model cover image

User LoRA

Yoshika Miyafuji (宮藤 芳佳) - Strike Witches (ストライクウィッチーズ)
13
Haruna 榛名 / Kancolle - AI Model cover image

User LoRA

Haruna 榛名 / Kancolle
100

Keterangan

ウマ娘のオグリキャップ LoRA of Oguri Cap (umamusume)

Recommend options

LoRA weight 0.5~0.9

Trigger words

base

oguri cap (umamusume)

Racing competition clothes :

navel, blue skirt, long sleeves, pleated skirt, sailor collar, red neckerchief, belt, black pantyhose, white jacket, white shirt, grey footwear, fur-trimmed boots

Casual clothes(maybe) :

white shirt, light brown cardigan, open clothes

Christmas costume :

christmas hair ornament, white gloves, white jacket, black pantyhose, white shirt, frills, white skirt, white vest, belt, grey legwear

Use animefull based model

Settings

DPM++ SDE Karras

20 steps, CFG scale 4.5~6.5

kl-f8-anime2.vae

CLIP skip = 1

If using highres

Latent (bicubic antialiased)

Denoising strength 0.5~0.65

LoRA training info

based on Animefull-pruned

160 images of oguri cap

8x low quality 50 images

16x medium quality 60 images

32x high quality 50 images

=> 1 epoch = 2960 images

replaced character feature tags with oguri cap (umamusume)

horse girl, horse tail, grey hair, blue eyes, etc.

using aspect ratio bucketing

resolution : 768x768

rank=alpha=16

using dadaptation

batch size = 4, 7 epochs trained

clip skip = 1

This LoRA may be compatible with animefull-based models (ex. AbyssOrangeMix Series...)

This LoRA can generate nsfw images of oguri cap.

All uploaded images are output of AbyssOrangeMix2-nsfw, kl-f8-anime2.vae

Komen