Gemini 2.0 Flash Makes Mediocre Images...But That's Not The Point!
Image quality is a red herring. We're finally witnessing true multimodality.
Today’s post is also a developing story, so the “Hot Take” format fits nicely.
TL;DR
Gemini 2.0 Flash Experimental can create and edit images natively.
What is it?
Yesterday, Google’s Logan Kilpatrick announced the release of Gemini 2.0 Flash with native image generation:
Gemini can now create multi-step illustrated stories from a single prompt, edit existing images directly, rework uploaded images, and more.
The best part?
It’s 100% free to try.
How do you use it?
The easiest way to try the new model is via Google AI Studio.
Here’s the step-by-step process:
Go to aistudio.google.com and log in with your Google account.
Select “Gemini 2.0 Flash Experimental” from the model picker. Note: You want the gemini-2.0-flash-exp model, not the default Gemini 2.0 Flash. (I know, I know.)