Keanggotaan PixAI
PixAI
PixAI
Generate
Sign in
Beranda
Buat
Model
Studio
NEW
Kontes
Buat dengan Mio.2
Toolbox
NEW
Dokumen PixAI

LoRA Pengguna

XL
Karakter

Reisa (Magical) / Blue Archive

Buat

  • Generator Gambar AI
  • Generator Animasi AI
  • Toolbox
  • Generator Tematik
  • Latih LoRA
  • Agen Mio.2
  • Studio

Temukan

  • Tag Populer
  • Peringkat
  • Model Market
  • Kontes
  • Berita

Tentang

  • Dokumen PixAI
  • Cara Menggunakan PixAI
  • Tsubaki.2
  • Kenalan dengan Mio
  • Aturan Konten

Harga & Bantuan

  • Keanggotaan
  • Paket Kredit
  • Kontak

Aplikasi Seluler

  • App Store
  • Google Play
© 2026 PixAI
  • Ketentuan Layanan
  • Kebijakan Privasi
  • Kebijakan Hak Cipta
  • Undang-Undang Transaksi Komersial Tertentu
Reisa (Magical) / Blue Archive - AI Model cover image
Diunggah pada
30 Okt 2025, 12.57
Penggunaan
183
Ulasan
Belum ada ulasan
Izin
  • Izinkan pembuatan & berbagi gambar
  • Izinkan pengguna mengunduh model Anda
  • Penggunaan komersial

LoRA yang Direkomendasikan

Jin Kazama (Tekken) - AI Model cover image

LoRA Pengguna

Jin Kazama (Tekken)
6
Shouko komi san  - AI Model cover image

LoRA Pengguna

Shouko komi san
3
Ruby Choi | The Perfect Roommates - AI Model cover image

LoRA Pengguna

Ruby Choi | The Perfect Roommates
4
chisa/千咲 - AI Model cover image

LoRA Pengguna

chisa/千咲
15

Deskripsi

https://civitai.com/models/2086593?modelVersionId=2360849

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

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.

Komentar