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.
Version 3 includes 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.
Version 4 has a softer style that no longer needs the Dynamic Thresholding plugin for best results.
(highly recommended) Use a negative embedding for best results
I use verybadimagenegative_v1.3 (all examples use this)
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 2.5x using R-ESRGAN 4x+ Anime6B works very well (no need for high weights, 0.45 will work fine). Additionally, generating the pre-upscaled image at a higher resolution such as 768x768 will improve quality a lot.
(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:
(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.>
(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