PixAI Membership
PixAI
PixAI
Generate
Sign in
Home
Generate
Models
Recipe
NEW
Studio
Contest
Mio.2

Conversational creation

AI Tools
Guide

SDXL

Halcyon SDXL - Photorealism

#Mature Female#Realistic#Video Game#Photorealistic#Girl
HomeModelsMio.2Profile

AI Tools

  • 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

Discover

  • Trending Tags
  • Ranking
  • Model Market
  • Contest
  • News

About

  • About PixAI
  • Guide
  • PixAI Blog
  • Tsubaki.2
  • Meet Mio, Our Mascot
  • Content Rules

Pricing & Help

  • Membership
  • Buy Credits
  • Contact

Mobile App

  • Get the PixAI app
  • App Store
  • Google Play
© 2026 PixAI
  • Terms of Service
  • Privacy Policy
  • Copyright Policy
  • Attributions
  • Specified Commercial Transactions Law
Halcyon SDXL - Photorealism - AI Model cover image
Uploaded at
Aug 9, 2024, 11:26 PM
Uses
19.5k
Reviews
Satisfactory  (1)
Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Recommended LoRAs

Beautiful Eyes - Anime / Douyin Eyes, Eye enhancement ( v2 'Crystal Eyes' available now!) - AI Model cover image

User LoRA

Beautiful Eyes - Anime / Douyin Eyes, Eye enhancement ( v2 'Crystal Eyes' available now!)
2.84k
Better Quality - AI Model cover image

User LoRA

Better Quality
2.57k
dmd2_sdxl_4step_lora - AI Model cover image

User LoRA

dmd2_sdxl_4step_lora
3.13k
Rydia/リディア (Final Fantasy Ⅳ)【IllustriousXL,PonyXL】 - AI Model cover image

User LoRA

Rydia/リディア (Final Fantasy Ⅳ)【IllustriousXL,PonyXL】
20

Description

https://civitai.com/models/299933/halcyon-sdxl-photorealism?modelVersionId=709468

3/4/24 update - now includes SDXL vae fix.

This is the SDXL version of my SD1.5 model Halcyon. I'm a professional photographer and I've incorporated some training from my own images in this model. Most of the preview images are shown with no LORAs to give you an honest idea of the model's capabilities, obviously you may have better results using LORAs.

This is a very robust model primarily focused on photorealism but capable of generating all types of images. I typically use DPM++ 3M SDE KARRAS at around 30 steps with a CFG of 5-8, however feel free to use whatever sampler and steps you find gives you the best results.

Comments