cynder, diane foxington, and porsha crystal (spyro the dragon and etc) directed by gridanon
Viewing sample resized to 41% of original (view original) Loading...
Description

Girls day out!

AI Models are capable of so many different styles, and it'd be great to see genners use a wider variety. This month I'm going to try to demonstrate various different styles.

This image's style is "toon \(style\)," "cartoonized," and "cartoon." These tags cause a big eyed style based on classic American animation. There was an interesting discussion about how animation has changed over the decades and this isn't any one particular animated style like Disney or from a specific era, but rather a very generalized cartoon style made from anything that was tagged with any of these tags on Danbooru or e621. These are three characters from 3D source material often shown in more 3D styles so this demonstrates what a flatter cartoon look for them would be like.

An alt with a less strong version of this style is: https://files.catbox.moe/0r8jok.png

The main impact of these tags seem to be the big eyes and simpler look. It often causes dot eyes, big noses and simple but exaggerated features like Hartman hips. Comparing the posted version to the linked alt shows different ways the tags can be used. In the alt the tags still give a 2D look but the characters are much more on model resembling their 3D appearance, whereas giving the tags more weight like the posted version changes their body types a lot more and makes them look much more cartoonish than realistic.

The model used was StableMond, which you can get at: https://huggingface.co/Xeno443 . I'd highly recommend any of the Mond models, they're all some of the best furry SDXL models available. StableMond is the most anime influenced so it's best suited for cartoony looks like this, while 3WolfMond-LastSDG is the most realistic and the others are in between.

Getting multiple characters in a gen like this is much easier with Regional Prompter: https://github.com/hako-mikan/sd-webui-regional-prompter . That lets you divide an image into regions and prompt each region separately, so you can create different characters and give them different traits. Another way to do it is to gen a background and then inpaint the characters in, that gives you more control but it's more effort.

Hope something there is helpful to somebody!

Blacklisted

    There are no comments.