11 Best Anime Stable Diffusion Models for Anime Art Generation


If you click on a link and make a purchase, I may receive a small commission. As an Amazon affiliate partner, I may earn from qualifying purchases.
Read our disclosure.



Moonbeam is one of the top-rated and most used anime art models available on PixAI. While you can’t directly download the diffusion model for yourself, you can use it for free on PixAI. Moonbeam excels in details and shadow generation.

Hotaru Breed


Hotaru Breed, as an AI art model, is definitely focused more on an anime art style that is soft and gentle. Soft colors, characters with big cartoony eyes, and pastel-like backgrounds.

Anything V5


Anything model has already reached version 5, and the latest Prt-RE version fixes problems such as CLIP. Prt is currently the recommended version to have. You can get quality parameters (text prompt) from Civitai.

From users:

“a quality model for sure, keep up the innovative mix work”

“A changelog for v5 would be appreciated since the outputs are so similar to v3.”

Counterfeit V3.0


Counterfeit is one of the most downloaded anime diffusion models in Civitai. It’s rated 4.85/5 and pretty much works out of the box.

From users:

“I get these weird green circles when generating images. Tried changing the prompts and sampling methods, but nothing helped. Has anyone had any similar issues?”

“I love this model. But will there be a 2GB model for 3.0 version? 5GB is quite a lot…”



Cetus-Mix is a checkpoint merge model, with no clear idea of how many models were merged together to create this checkpoint model. Recommended settings for image generation: Clip skip 2 Sampler: DPM++2M, Karras Steps:20+.

From users:

“I have tried it with various Lora and VAE and I can say that this model, one of the best you can find now! Kudos to the author for his efforts!”

“Hello, your model is one of my favourites, thank you the author of this model, do you know on how to make checkpoint models, if not no problem”

Dark Sushi 2.5D


Dark Sushi 2.5D is an updated version of Dark Sushi. The model creator merged Chillout Mix with the previous Dark Sushi model and added a bit of NijiExpress V2 into the mix. Dark Sushi creates, as the name implies, slightly darker and heavier tones and art style than, say, a model like Anything V5.

Dark Sushi is already at the V4 version and is one of the best anime diffusion models out there.

From users:

“I love this model but I’m having trouble getting detailed faces, in a way I don’t with other models. The faces are usually noticeably lower detail than the rest of the picture.”

“I’ve got a problem with hands. No matter what I do there’s always a problem with hands. Having more than 3 hands or mutated hands etc. Do you have a suggestion for this problem? Great model btw”



Maturemalemix is a model specifically to generate male anime characters. Many models focus on female anime characters so it’s nice to see a AI art model focused on male character generation.

From users:

“How can I make it so the veins and muscles on the arms are less pronounced? It almost has a marbled effect.”

“the quality I get with the same prompts is nowhere near as good as these images D:”

Nyan Mix


Nyan Mix is one of those anime Stable Diffusion models that generate extremely detailed and flow-like images. The model creator has provided detailed instructions on how to use the model, why it was created, and what it has inside it. You also need NyanMix.vae.pt to use this model successfully (you can get it below the Download button (in Civitai)).

From users:

“Once you drop the NyanMix VAE into the VAE folder and select it under settings > Stable Diffusion, dont forget to click the “Apply setting” button. Turns out that was the final step to fixing the blue porridge”

“For all who their images turn out to be filled with blue noise, install the VAE too, and then in stable diffusion go to settings and pick in stable diffusion settings SD VAE and pick NynMix.vae.pt”



Mistoon-Anime differentiates itself from the crowd by generating AI art that is mostly seen in anime series and movies. The AI images are not so much of an illustration result that you get from a lot of other diffusion models.

From users:

“When I use it the images are a really dull colour, I’ve heard a VAE can help with that. Do you use one for these images? If you do then what one?”

“Have to say this is one of the best models I have used. Among select few SD model where didn’t felt I was fighting AI. Cooperates well with control net. Thank you for this.”



Neverland is a publicly unreleased diffusion model (though you can use it at PixAI’s AI anime art generator), but the results are stunning, to say the least. If you want clear line art for your AI artwork, you can complement this model with the Ligne Claire Anime Style LoRA.

Arthemy Comics


Arthemy Comics is a checkpoint merge model that combines six different stable diffusion models together. Arthemy Comics is not 100% about anime but works extremely well for creating anime and cartoon characters. The creator of the Arthemy model also has a dedicated website called Arthemy.ai for creating AI comic art.

From users:

“I downloaded this a couple of hours ago and I already think that this might be the single best checkpoint I have. Getting good looking images is so effortless with this one.”

Feature image credits.



Digital Artist

I’m a digital artist who is passionate about anime and manga art. My true artist journey pretty much started with CTRL+Z. When I experienced that and the limitless color choices and the number of tools I could use with art software, I was sold. Drawing digital anime art is the thing that makes me happy among eating cheeseburgers in between veggie meals.

More Posts

Thank You!

Thank you for visiting the page! If you want to build your next creative product business, I suggest you check out Kittl!