Keanggotaan PixAI
PixAI
PixAI
Generate
Sign in
Beranda
Buat
Model
Studio
Kontes
Mio.2

Conversational creation

Toolbox
Dokumen PixAI

LoRA Pengguna

XL
Karakter

Fern Calliope(OC)

#Original#Mature Female#Dark skin#Torn clothes#Red Hair#long hair#Evening#Cloud#Ocean#Sunset#Beach#Fern#Plaid skirt#Pleated skirt#Dusk#Short sleeves#Girl#white shirt#Sand#Plunging neckline

Alat AI

  • OC Maker
  • AI Anime Generator
  • VTuber Maker
  • Sonic OC Maker
  • Hazbin Hotel OC Maker
  • Anime Character Creator
  • AI Figure Generator
  • Genshin OC Maker
  • All AI Tools

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

  • Dapatkan aplikasi PixAI
  • App Store
  • Google Play
© 2026 PixAI
  • Ketentuan Layanan
  • Kebijakan Privasi
  • Kebijakan Hak Cipta
  • Atribusi
  • Undang-Undang Transaksi Komersial Tertentu
Fern Calliope(OC) - AI Model cover image
Dilatih oleh
Avatar image of darth_brando9059
avatar-frame

darth_brando9059

Latih LoRA Anda Sendiri
Diunggah pada
6 Jun 2025, 11.21
Penggunaan
126
Diperoleh
5,590
Ulasan
Belum ada ulasan
Kata Pemicu

Original_Character, woman, dark_skin, redhead, castaway, torn_clothes, pleated_skirt, thighhighs,

Izin
  • Izinkan pembuatan & berbagi gambar
  • Izinkan pengguna mengunduh model Anda
  • Penggunaan komersial

Deskripsi

Original Character concept testing batch 1 for Fern Calliope, a student castaway on deserted island after a plane crash. The character is for use in making a Visual Novel parody project of LOST, which I am calling Project LUST: A H***** Parody. This is the first Lora, made with images from here and Yodayo, using AnimagineXL as base model.

Will update later with recommended settings, until then use is probably along the following:

  1. use with a detailer lora +/- a negative lora (fixer loras)
  2. steps; 18-50, CFG; 4.0 to 12, LoRA Weight: 0.2 to 1.2

Style of the lora input images is hyperanime and illustrative in nature. Think pin-up posters and full page color art from comics. Lora is trained on suggestive images but all images are SFW (do not show anything). As such this LoRA could be used for probably both SFW and NSFW outputs.

Komentar