One of the most interesting AI app developments of late is Dall-E, an AI-based tool that lets you type in any text — like “horse via social media” — and it will pump out images based on its understanding of that data.
You’ve probably seen many of these visual experiments floating around the web (“Weird Dall-E Mini Generations” is a good place to find some more unusual examples), and some are extremely useful and applicable in a new context. And others are simply weird, mind-bending interpretations of how the AI system views the world.
Well, you may soon have another way to experiment with AI interpretation of this type, via Meta’s new “Make-A-Scene” system, which also uses text prompts as well as input drawings to create entirely new visual interpretations.
As explained by Meta:
“Make-A-Scene enables people to create images using text prompts and free-form sketches. Previous AI image generation systems typically used textual descriptions as input, but the results could be difficult to predict. For example, typing “picture of a zebra riding a bicycle” may not exactly reflect what you envisioned; the bike may be turned sideways or the zebra may be too big or small.
Make a Scene aims to solve this by providing more controls to help you direct your output – so it’s like Dall-E but, at least from a Meta perspective, slightly better, with the capacity to use more system guidance prompts.
“Make-A-Scene captures the scene layout to enable the input of nuanced sketches. It can also generate its own layout with text-only prompts if the creator so chooses. The model focuses on learning key aspects of images that are more likely to be important to the creator, such as objects or animals.
Such experiments highlight just how far computer systems have come in interpreting various inputs, and how well AI networks can now understand what we communicate and what we mean in a visual sense.
Ultimately, this will help machine learning processes learn and understand more about how humans see the world. Which might sound a little scary, but it will ultimately help power a range of functional applications, such as automated cars, accessibility tools, enhanced AR and VR experiences, and more.
However, as you can see from these examples, we are still a long way from AI thinking like a human or becoming sentient with its own thoughts.
But maybe not as far as you think. Indeed, these examples serve as an interesting window into the current development of AI, which is currently just for fun, but could have significant implications for the future.
In its initial testing, Meta gave various artists access to its Make-A-Scene to see what they could do with it.
It’s an interesting experiment – the Make-A-Scene app is not yet available to the public, but you can access more technical information about the project here.
Add Comment