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

User LoRA

DiT.2DiT.1
Karakter

Chacha Akaza - 藜チャチャ / Maken-ki! - マケン姫っ! | DiT V1/V2

#white hair#green eyes#Maken-ki!#Chacha Akaza

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

  • Dapatkan aplikasi PixAI
  • App Store
  • Google Play
© 2026 PixAI
  • Syarat Perkhidmatan
  • Dasar Privasi
  • Dasar Hak Cipta
  • Undang-undang Transaksi Komersial Tertentu
Chacha Akaza - 藜チャチャ / Maken-ki! - マケン姫っ! | DiT V1/V2 - AI Model cover image
Dilatih oleh
Avatar image of Hans

Hans

Latih LoRA Anda Sendiri
Dimuat naik pada
29 Mac 2026, 10:34 PTG
Kegunaan
123
Diperoleh
4,325
Ulasan
Tiada ulasan
Kata Pencetus

ChachaAkaza, from anime Maken-Ki! Two, green eyes, white hair, ponytail, huge breasts, school uniform,

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

Keterangan

Trained on Tsubaki, 13 images.

Delightful Chacha. Brazilian and Japanese blood runs through her veins. Did you know that many Japanese people migrated to Brazil more than a hundred years ago?

Applies for DiT V1: Two recommended prompts to add: 'brown skin' and 'mature woman'. In one scenario, Chacha was generated "normally", and in a different scenario, she was generated with white skin colour. Just add it as a preemptive measure. For an unknown reason, in NON-NSFW ( in NSFW, she seems to generate fine) scenarios, she is sometimes generated without her proportions and generally looks younger. I have no idea why, as I didn't include any image of Chacha in LoRA creation that looks younger. So yeah, be wary. Besides this, she's fine.

I only used Tsubaki to generate the images, but I think you can use other DiT models.

I use Euler A. 28 steps. Because the results are pretty good, I think you can generate 3 images in parallel, and you will still be fine. Unlike SDXL, DiT is pretty consistent from my initial experience. Of course, if you demand a lot of detail, then maybe go cheap first.

I use 3, 4.5 and 6CFG.

0.7 Rescale CFG.

LoRAs I used in generation: https://pixai.art/en/model/1839426804048327588

Thumbnail model: Tsubaki

Komen