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

LoRA Pengguna

XL

Iwao178 / いわお Style [Pony XL]

AI Tools
  • AI Anime Generator
  • Generator Gambar AI
  • Generator Animasi AI
  • Anime Figure Generator
  • Character Sheet Generator
  • Magazine Cover Generator
  • Plushie Generator
  • Giant Statue Generator

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
  • Attributions
  • Undang-Undang Transaksi Komersial Tertentu
Iwao178 / いわお Style [Pony XL] - AI Model cover image
Diunggah pada
15 Agu 2024, 16.23
Penggunaan
4.0k
Ulasan
Luar Biasa  (1)
Izin
  • Izinkan pembuatan & berbagi gambar
  • Izinkan pengguna mengunduh model Anda
  • Penggunaan komersial

Deskripsi

Makes images similar in style to the artist Iwao178. Pony XL version on request of a previous NAI-based LyCORIS.How to usePrompt as normal, themes this artist likes are "shiny skin", nudity, various large breast sizes, sexual themes, tight clothing and general NSFW.The dataset was rough with a lot of censor bars, odd poses and other noise but thanks to Pony XL this version should be easier to work with than the previous.While I haven't tested it the much dataset contains a lot of very friendly ladies in various states of undress entertaining one (or more) gentlemen so that type of content should gen well.If that isn't your cup of coffee you can also use this LoRA for a general clean 2D look styler. While the dataset contains no names any of iwao's favorite characters should work well too.MISCDataset of 163 images trained at 1024resolution on Pony XLAll sample images are raw txt2img upscaled, no helper embeddings/negatives used. E.g. - things should look even better if you do.The training was done on a small subset of images, as such the output of this LoRA is not an accurate representation neither in quality or style of the source material. Go support the artist if you want the good stuff.

Komentar