IllustraToon

( Not my Model )


 <a href="https://civitai.com/models/2130613?modelVersionId=2712618" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/models/2130613?modelVersionId=2712618
 </a>




 This is the second version of my checkpoint. It uses a different VAE, aims for a more cartoony style, and differs significantly from v1.
 
 
 To increase the level of cartoon look, use "cartoon" or "toon" in your prompt.
 
 
 
 
 Settings
 
 
 
 CFG 2–6, minimum 15 steps.
 
 
 Euler Ancestral, Karras, or
 
 DPM_2, SGM Uniform
 
 
 I prefer CFG 4–6.
 
 
 I used FaceDetailer and lazy embeddings for some of the showcase images. If you use DMD2, the results will look more cartoony. Most of the showcase images were created without DMD2.

v2.0

( Not my Model )


 <a href="https://civitai.com/models/2130613/illustratoon?modelVersionId=2410098" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/models/2130613/illustratoon?modelVersionId=2410098
 </a>




 This is the more cartoon-styled version of my other checkpoint.


 CFG 4, minimum 15 steps. Euler ancestral, Karras.


 I’ve used FaceDetailer and lazy embeddings for some of the showcase pictures.


 If you use DMD2, the results will be more cartoony. Most of the showcase pictures were created without DMD2.


 I’ve trained a few cartoon LoRAs and baked them into IllustraCore. After that, I merged 25% of the OUTPUT-0 block of the base IllustraCore checkpoint with the baked-in model. I’m quite happy with the result and wanted to share it with you guys.