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

Conversational creation

Toolbox
Dokumen PixAI

LoRA Pengguna

SD
Karakter

Chacha Akaza - 藜チャチャ / Maken-ki! - マケン姫っ!

#Chacha Akaza

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
Chacha Akaza - 藜チャチャ / Maken-ki! - マケン姫っ! - AI Model cover image
Dilatih oleh
Avatar image of Hans

Hans

Latih LoRA Anda Sendiri
Diunggah pada
5 Sep 2023, 14.53
Penggunaan
909
Diperoleh
35,659
Ulasan
Luar Biasa  (1)
Kata Pemicu

ChachaAkaza, dark skin, green eyes, white hair, ponytail, massive breasts,

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

Deskripsi

Trained on Hassaku, 20 images. I will test ze model and add description later, trained on majority "SFW" images. I used anime screenshots as well as fanarts, I got some good data. I recommend using settings like Euler A: 23 seeds, 0 credits cost before you spend any. This model can be tricky to handle

Eyes, according to Wiki, Chacha has green eyes, but I only found a few images from season 1. Her eyes will likely generate grey or blue, I think you can brute force it with brackets.

GrahamAingPikas generates face without problem, DarkSushi too. MeinPastel and Hassaku mostly too it seems. It's definitely harder to generate a good face, I now know to not include art from artists who use a different style compared to anime, it can confuse ze program responsible for creating LoRa.

For me, LoRa strength 0.7 works best. You may experiment, I haven't got positive results with stronger LoRa, that might be a problem on my side though.

I use "6" or a bit unusual CFG, 6.8 instead of 7 or 8.

There's already one model, I haven't tried it, but you may also give it a go: https://pixai.art/model/1651579275644507526

Komentar