Nova Cartoon XL
Nova Cartoon XL is a sdxl checkpoint that is focused on cartoon / toon aesthetic
Which can be described as XL-tized Nova Cartoon
All images on example were created with diffusers with custom png tags
Rules
You cannot use the generated images for commercial use if it's not edited (or just turning it to black and white)
You can share images without any restriction if you don't monetize it
Advertising this model to outside is always welcome
Recommend Settings
Sampler: Euler a
Steps: 20~30
Clip Skip: 1-2
Denoising Strength: 0.65 - 0.8
CFG Scale: 3-5
Prompt: masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, cartoon, toon, {Prompt}, BREAK, depth of field, volumetric lighting
Negative Prompts: modern, recent, old, oldest, anime, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digits, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, username, simple background, conjoined, bad ai-generated
Description
Higher contrast control and bit closer style to v4.0
NoobAI EPS v1.1 + Illustrious v2.0-stable DARE applied
FAQ
Comments (15)
I use V5 and love the style! But one personal preference is that I don't like blush lines, which this model draws a lot. I have a hard time getting the model to output smooth, un-lined blushes. Have any of y'all had luck with this?
I currently put things like "blush lines" or "hatching blush" in the negative prompt, but this usually doesn't help.
Try blush_stickers. Albeit that might be more cartoonized as well. It might be difficult but there's a tag for it, i'm sure. You could try a bunch of different negatives, one of them will work. It might be hard though considering blush in anime is usually done with the hatching lines. Ah there's a word for ya
Really love this model, hope we can get it back to onsite generation. The bidding system is terrible (will probably never buy Buzz again, it feels like a scam) and using this model locally takes so much longer with worse results :/
I still don't know how to reproduce the full workflow of Civitai locally with ComfyUI or another tool.
@Brisby it really sucks :/ I'm using AUTOMATIC1111 but the process is very slow, even with a 4070
@lgpetro thank you, I will try automatic1111
@lgpetro I'd check your settings then, a 4070 should be able to generate images in like 6-12 seconds an image
I JUST bid on this. One of the best models on this site that doesn't need extra help to produce flawless images! Stop trying to take it from me please!
Amazing checkpoint, honestly. But I personally ran into grain/noise problems when using it with DMD2. If somebody knows how to fix it in ComfyUI, please let me know in the comments. Still, very good checkpoint and highly recommended.
When will it be available again?
The line between anime and cartoons is very thin, I can no longer tell if it's anime or toon O_O
I think it's the noses.
Best model for cartoon characters the only one I use
Any chance you'll create an Anima version of this one?
This remains one of my favorite styles, works really good with LORAs too. Wondering how v7 will turn out, and yeah, an Anima version sounds nifty.