Despite the productivity-oriented perks of large language models, there’s the misconception that local LLMs need a lot of computational horsepower to run. Well, it’s true to some extent, as you’ll ...

UPDATE 03/13/2023: This plugin is now natively part of Krita as of Krita 5.0. I will keep this code here for reference, but you don't need to install this plugin any longer to get this functionality.

Drive a forked Krita by voice ("new layer", "select subject", "merge down", "undo") with low-latency commands, plus a slower agentic/LLM path for natural-language and ...