Master LLMs with our FREE course in collaboration with Activeloop & Intel Disruptor Initiative. Join now!


GLIGEN, the Tool to Rule All AI Image Generators
Artificial Intelligence   Data Science   Latest   Machine Learning

GLIGEN, the Tool to Rule All AI Image Generators

Author(s): Ignacio de Gregorio

Originally published on Towards AI.

The Grounding Problem Solved?

The tool all artists have been waiting for is here.

GLIGEN is a new framework by Microsoft and the Universities of Washington-Madison and Columbia that allows much higher control over the generation of images by allowing you to draw bounding boxes and other visual cues besides simply stating what you want through a text description, the current standard.

And the best thing of all is that is designed to be reusable on any open-source image generator, making it clear that if 2023 was the year of AI promise, 2024 is the year of real value.

What’s more, you can try it today.

This insight and others have mostly been previously shared in my weekly newsletter, TheTechOasis.

If you want to be up-to-date with the frenetic world of AI while also feeling inspired to take action or, at the very least, to be well-prepared for the future ahead of us, this is for you.

U+1F3DDSubscribe belowU+1F3DD

The newsletter to stay ahead of the curve in AI

Anyone who has fiddled with AI image generators like Stable Diffusion, DALL-E, or MidJourney has quickly run into the same wall:

Lack of control.

In other words, the fact that you can only state what you want through text signifies that there’s a limit to… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI

Feedback ↓