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

SDXL

Mergestein - Uncanny R

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
  • Attributions
  • Undang-undang Transaksi Komersial Tertentu
Mergestein - Uncanny R - AI Model cover image
Dimuat naik pada
8 Apr 2026, 4:51 PG
Kegunaan
36.7k
Ulasan
Cemerlang  (12)
Langkah Pensampelan

13

Kaedah Pensampelan

Euler a

Skala CFG

2.5

Negatif

worst quality, bad quality, low quality, lowres, low resolution, traditional media, anatomical nonsense, artistic error, bad anatomy, interlocked fingers, bad feet, poorly drawn, censored, watermark, bad hands, extra digits, fewer digits, bar censor, mosaic censor, conjoined

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

Recommended LoRAs

little girl XL - AI Model cover image

User LoRA

little girl XL
44
Backstreetgirl Style (Nashe AI) - AI Model cover image

User LoRA

Backstreetgirl Style (Nashe AI)
127
Jessica Rabbit - Who Framed Roger Rabbit - XL LORA - AI Model cover image

User LoRA

Jessica Rabbit - Who Framed Roger Rabbit - XL LORA
171
ロリ loli / 幼児・幼女・女児 little child, little girl - AI Model cover image

User LoRA

ロリ loli / 幼児・幼女・女児 little child, little girl
230

Keterangan

Less CFG = more Realistic, More CFG = Less realistic

available for download at Civitai: https://civitai.com/models/2074692?modelVersionId=2562800

Simple Uncanny: Better than Uncanny - on realism and output with low steps.

Uncanny-: More realistic, downside it needs more steps to look good (still looks ok at low steps), and some unrealistic prompts doesn't work. Better for realism and a little of uncanny.

Uncanny+: Less realistic, better at low steps and unrealistic prompts works better, better mix of realism and uncanny.

Realistic lighting and backgrounds with Uncanny characters, decent quality with low steps, good prompt adherence, uses danbooru tags but understands some other words and descriptive prompt.

Recommended positive prompts for more realism: (best quality, masterpiece), realistic, photorealistic, photo (medium)

Komen