vanny (five nights at freddy's: security breach and etc) directed by gridanon
Viewing sample resized to 47% of original (view original) Loading...
Description

Look, she's waving! Why don't you go say hello?

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 is using different techniques instead of a specific style, namely "spot color" and "limited palette." Spot color colors specific parts of an image, usually the eyes or other focal points, and limited palette (also called "restricted palette") restricts it to a limited amount of colors. Combining them creates an effect like in this image, where most of the image has minimal color but a few focal points have vibrant color.

Sawmill pointed out that spot color can be done manually by configuring an image to be grayscale and then coloring the parts of the image you want. That results in an even more striking look since the rest of the image is black and white or gray except for whatever areas are colored. Doing a limited palette prompt like this can allow more color for the rest of the image (like the blueish gray here instead of just black and white gray), but you have less control over what the AI decides to color.

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 artsy looks like this, while 3WolfMond-LastSDG is the most realistic and the others are in between.

Hope something there is helpful to somebody!

Blacklisted

    There are no comments.