Apple has bided its time in the ongoing AI competition between tech’s titans.
That all changed today as Cupertino unveiled its own text-based AI editing tool.
An MGIE model, something The Verge tells us that “stands for MLLM-Guided Image Editing” and which “can be applied to simple and more complex image editing tasks like modifying specific objects in a photo to make them a different shape or come off brighter.”
How does it work?
“The model blends two different uses of multimodal language models. First, it learns how to interpret user prompts. Then it “imagines” what the edit would look like (asking for a bluer sky in a photo becomes bumping up the brightness on the sky portion of an image, for example).”
The other part, the user text entry, is quite self-explanatory and similar to many of the other models of this type out in the wild.
Documentation is available on GitHub and current Internet commentary on the project is overall positive, comparing it to Open AI’s Dall-E. And while it is definitely a start, it is a genesis in a quite crowded field.
You might remember our article some time back about Adobe’s Firefly and the company’s concerns that advanced AI editing will put its own customers out of a job. On top of that, we have talked about other platforms that do everything from generating video to taking existing photographs and changing major compositional elements within it. In other words, there’s a lot going on in the AI space when it comes to media editing and generating so it remains to be seen how much of a player Apple intends to be in this space.
Any thoughts that you might have on text-based photo editing using artificial intelligence are welcome in the comments.
We have some more news for you to read at this link.