Ahli PixAI
PixAI
PixAI
Generate
Sign in
Laman Utama
Jana
Model
Recipe
NEW
Studio
Kontes
Mio.2

Conversational creation

Kotak Alat
Guide

User LoRA

XL

Nyantcha style for AutismMix SDXL

Laman UtamaModelMio.2Profil

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

Temui

  • Tag Popular
  • Ranking
  • Pasaran Model
  • Kontes
  • Berita

Tentang

  • Tentang PixAI
  • 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
  • Attributions
  • Undang-undang Transaksi Komersial Tertentu
Nyantcha style for AutismMix SDXL - AI Model cover image
Dimuat naik pada
8 Mac 2024, 10:24 PTG
Kegunaan
105k
Ulasan
Cemerlang  (17)
Kata Pencetus

nyantcha

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

Recommended LoRAs

Skullmageddon - River City Girls | [ILXL] - AI Model cover image

User LoRA

Skullmageddon - River City Girls | [ILXL]
4
nami (weatheria ①) - AI Model cover image

User LoRA

nami (weatheria ①)
10
Celistia Ralgis | Saijaku Muhai no Bahamut/最弱無敗の神装機竜 (2 outfits) [COMMISION] - AI Model cover image

User LoRA

Celistia Ralgis | Saijaku Muhai no Bahamut/最弱無敗の神装機竜 (2 outfits) [COMMISION]
4
[illustrious]semahiro style - AI Model cover image

User LoRA

[illustrious]semahiro style
19

Keterangan

Activation tag is nyantcha, made to work with autismix so it might be a little overcooked with base ponyv6.If you are interested in making your own loras here are some training settings to use with Kohya GUI: Tags settings: https://files.catbox.moe/ocsne4.jsonNo tags settings: https://files.catbox.moe/nglzg5.jsonThey are not beginner or low VRAM friendly settings. First one requires bitsandbytes 36+ and second one requires bitsandbytes 0.35. I highly recommend resizing the lora with these settings in Kohya GUI if you use the no tags settings: imageTagging was done using SwingV2 at 0.35 weight and 0 min tag fraction with nyantcha, as prefix tag. Using 1000-2000 steps is also fine depending on the artist.

Komen1