Built using the a modified version of the workflow I used for the Illustrious version of uwumerge, this is the Anima version of uwumerge! The default style is influenced by the Anima version of my uwustyle LoRa.
Note: The style is trained on a lot of cartoon style furry characters with paws or 4 fingers, so sometimes it will give even non-cartoony characters 4 fingers on their hands.
Settings & Prompt:
Start with a lower CFG and step count. A good starting point for Euler A is 2.5 to 4.5 CFG and 20-28 steps.
To get the intended style, use E621 & booru tags such as anthro, furry, male, dog, solo plus quality tags, and natural English prompts wherever you need more complexity. The training data is mainly E621 tags with a small amount of booru tags and natural English in varying levels of verbosity.
The model is also good with prompts describing backgrounds, positioning of things in the image, and text within quotes, including controlling the font size and color.
Be warned, this model does not know as many species as previous versions of uwumerge, but it should know the most popular species, and as a fallback you can use some of the family tags such as canid, felid, etc.
Since this model is meant to generate cuter styled content, for some prompts you may want to add young to the negative prompt to get more adult-looking characters.
Description
This version is tuned towards more three-dimensional depth, deeper contrast & color tones, and characters with more defined anatomy, while retaining the style characteristics and knowledge of v5.0. Also converges at a slightly reduced step count.
INT8 version included, which trades a bit of quality for faster and lighter inference than regular BF16, on supported graphics cards, with the latest version of ComfyUI :3
