Description
(for best results, read the full description - usage guide below)
This is a merge of some random anime based and cartoon based models to achieve a somewhat cartoony anime style, more similar to what you would actually see in anime as opposed to the more common hyper-detailed anime models.
Versions 3, 4, and 4.5 include some custom training to further enhance the style. More details available in "About this Version" on the sidebar. Most positive prompts for the v3 sample images were randomly generated.
Usage Guide
(highly recommended) Use a negative embedding for best results
I use verybadimagenegative_v1.3 (all examples use this)
verybadimagenegative_v1.3
Place the downloaded file into the "embeddings" folder of the SD WebUI
In the negative prompt, paste "verybadimagenegative_v1.3"
(highly recommended) Upscaling at 2x (or more) is important to getting a good result. I would recommend the following settings:
Denoising strength of 0.45
Use the "R-ESRGAN 4x+ Anime6B" upscaler for a flatter look, or use "Latent" for a bit more detail
Leave hires steps at default of 0 (equal to your generation steps)
(highly recommended) Use DPM++2M Karas as the sampler. Other samplers can yield odd artifacts, though your mileage may vary depending on your specific setup.
(only for version 3 and below) Use the dynamic thresholding plugin (all example images do with cfg scale 10 mimic 7): https://github.com/mcmonkeyprojects/sd-dynamic-thresholding
Set the CFG scale to 10.0
Click the checkbox "Enable Dynamic Thresholding (CFG Scale Fix)"
Set the Mimic CFG Scale to 7
If you don't want to use this plugin, then set the config scale to 5 or 6
This model is very easy to prompt, and does not require a ton of prompt engineering to get good results. The following format will yield decent results:
Prompt:
(best-quality:0.8), perfect anime illustration, <normal description of the image, e.g. a woman running in tokyo at night, a flaming meteor, etc.>
Negative:
(worst quality:0.8), verybadimagenegative_v1.3, (surreal:0.8), (modernism:0.8), (art deco:0.8), (art nouveau:0.8)
The model is capable of NSFW
Description
This is a sharper version of v4.0, designed to have a cleaner look. It will follow prompts better than v4.0, along with providing higher saturation.
FAQ
Comments (11)
Amazing model. One of my all-time favorites 😍
The examples use prompting and not booru tagging. So is that the intended way to use it?
Like it so far. But seems to be very biased towards young girls. Virtually impossible to get an adult woman going.
Generally I try to keep prompts as simple and human readable as possible, as this best leverages the transformer model that exists in SD1.5, adding tags and such only in addition to the base prompts to tweak and tune the attention if something is not working out right. That being said, ymmv based on what you're shooting for as the base models may have different distributions of captions based on what you're targeting with your prompts.
maybe, will there be an sd3 version? :P
Can images created with this model be sold?
As the creator I don't have any restrictions on this, so feel free
@bigbeanboiler thank you!
@BUTTERFACE Wow!! that's a surprise.
Why is it impossible to make NSFW content with this model now?
I really really love this style 😞
This is probably my favorite cartoon model! The most magnificent flat style with an outline, excellent anatomy and responsiveness, expressive composition... The only drawback is a very strong female focus and a small variety of faces, making a male character or something else is quite problematic. Otherwise, everything is fine. I love this model, great job!
Very wholesome model. While it lacks some depth it can be a great tool to weigh more focus on characters.