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

User LoRA

XL
Karakter

Reisa (Magical) / Blue Archive

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
Reisa (Magical) / Blue Archive - AI Model cover image
Dimuat naik pada
11 Nov 2025, 4:30 PG
Kegunaan
267
Ulasan
Tiada ulasan
Kebenaran
  • Allow image generation & sharing
  • Benarkan pengguna memuat turun model anda
  • Kegunaan komersial

Recommended LoRAs

Nepgear/Purple Sister - Hyperdimension Neptunia Series | ネプギア 超次元ゲイムネプテューヌ - AI Model cover image

User LoRA

Nepgear/Purple Sister - Hyperdimension Neptunia Series | ネプギア 超次元ゲイムネプテューヌ
22
curvy - AI Model cover image

User LoRA

curvy
26
magbe - AI Model cover image

User LoRA

magbe
0
Yuri N The Zone v1 - AI Model cover image

User LoRA

Yuri N The Zone v1
5

Keterangan

https://civitai.com/models/2086593

1girl, solo, blue archive, long hair, pink hair, purple hair, light blue hair, multicolored hair, two-tone hair, streaked hair, twintails, drill hair, blue eyes, purple eyes, ahoge, halo, wing hair ornament, star hair ornament, dress, bow, star (symbol), puffy short sleeves, jacket, purple bow, white gloves, striped pantyhose,

purple shoes, wing footwear ornament

11.11 : vpred v1.1 update. Increased training dataset to 123 images, applied LoKr algorithm.

The advantage of LoKr is its compression capability, derived from high parameter efficiency. This gives it the potential to achieve equivalent or even greater expressive power than standard LoRA, despite having a file size that is approximately 8 times smaller.

10.30 : trained with 96 images

This is an experiment to compare the differences between the IL and Vpred LoRAs.

All training parameters for both LoRAs are identical, except for the difference in the learning models (IL 0.1 and NoobAI v-pred 1.0).

Overall, the IL side exhibits bright colors and thin lines (this look is somewhat closer to the 'Blue Archive' style), while the vpred side shows deep shadows/contrasts and thick lines.

If this washed-out/overexposed appearance (turning white) is due to the white background in the dataset, the vpred side could be considered to have learned the character features more effectively. However, since the IL model is also not bad for general use, it is difficult to determine which one is superior.

Komen