Gauss For Mac

AI image generation is as revolutionary as it is controversial, but while the tools you need are readily available, they’re not always as accessible as you’d like.

To make things a bit easier for beginners, you have apps like Gauss. It’s an open-source, Swift-based application that lets you run Stable Diffusion models locally and generate images with minimal technical knowledge.

There are lots of online Stable Diffusion image generators, but they come with many limitations. Running the model locally lets you do anything you like, with no internet connection required.

First things first, you’ll need to download at least one of the available models, which can be done through the app’s UI. They’re all quite large, so it’ll take a while to set them up. When it’s done, you’ll be able to generate as many images as you like without relying on an API.

Gauss saves every session as a separate document, so you can easily continue a job later. Once the project is loaded, go ahead and provide various prompts to generate the images you need. Figuring out what to type is the most difficult part of AI image generation, but a trial-and-error approach works.

Unfortunately, while the app is very intuitive, it also lacks almost all the advanced features supported by Stable Diffusion. It doesn’t support negative prompts, changing image dimensions, reusing the same seed, and img2img functions.

You can tweak the speed and creativity, which should translate to the number of sampling steps and CFG scale, and generate one, four, or nine images at a time. The same prompt can be run again later, but without the ability to use the same seed, tweaking is limited. To save an image, just drag it to Finder or another app.

Essentially, Gauss is a good choice if you’re just getting started with AI image generation, but it’s too limited for anything other than occasional use. Nevertheless, the fact that it’s written in native code and runs models locally, in an intuitive UI, is worth appreciating.