Model Information

Spirited

Description

Welcome!

I've been playing around with a lot of 2d anime style models lately, and decided to try making a merge of my own.  Let me know if you  like the style of this one.  It makes great clothed or unclothed images, good prompt adherence, and some flexibility for moderately complex prompts.   I'm pretty happy with the images I've created with it, so I wanted to share it with you all.  If you enjoy it, feel free to leave a note or post a gallery!

 

My Settings

Sampler -DEIS (or Euler A)

Scheduler -SGM Uniform

Steps - 35

Resolution -896x1152, 832x1216 (or flip for landscape)

 

Hires.fix:

Upscaler - 4x_foolhardy_Remacri

Steps - 12-15

Denoise -.3-.4

Upscale by - 1.5 - 2.0

Spirited

v2.1

616downloads
Download Model

Model Details

Type
AI Model
Task
text-to-image
Subtype
Safetensors / Checkpoint AI Model
Created
Updated
May 18, 2026

Versions

Related Models