This model is designed to create vibrant, colorful images with bold, dynamic outlines. You don't need to use "toon" or "comic" in your prompt—the style is baked right in!

The outlines are a key feature and will vary between dark, inky lines and colored lines that blend with the art, giving everything a high-energy, illustrated feel.

Strengths

Due to its bright colors and training (it's slightly curated with LoRAs for better backgrounds), this model is good for:

Scenery & Compositions
Action Scenes & Fights
Vibrant Character Portraits

Recommended Settings

Here are the settings I use to get the best results:

CFG Scale: 3.5
Steps: 30 - 50
Sampler: Res_Multistep + Beta

Prompting Advice

The model is very flexible. It can handle detailed prompts if you want a specific scene.

However, I've found that basic, straightforward prompts often look best. This approach lets the model's core style shine through, creating a cleaner, more minimal look that really suits it. Feel free to experiment and find what you like!

Recommended Resolutions

The model works great at many resolutions. Here are the ones I've tested and recommend:

1024 x 1024
1152 x 896
896 x 1152
1216 x 832
832 x 1216 (I find this to be the most efficient)
1344 x 768
768 x 1344
1536 x 640
640 x 1536

I hope you enjoy Toonlistic!
Recommendations, and overall critique is welcome, even if it's negative. Just remember, I generate these merges for fun, and share them here without any actual incentives, only pure satisfaction from seeing what others make/generate. I always spend lots of my time working/curating to make specific styles that a normal lora might not be able to achieve. I am also terrible at lora training since I can't train locally, and here my models always fail to capture what I envision.