Generative AI Images with Gemini and Imagen - an Introduction
Briefly

The article announces the author's search for a new position in developer relations while introducing Google's Imagen 3 technology for image generation via APIs. The author shares a basic coding example using the GenAI libraries to demonstrate how to generate images based on prompts. They emphasize the simplicity of the code, highlighting the importance of the prompt in the image generation process. Additional features from the Imagen API are mentioned, encouraging developers to explore the documentation for more advanced capabilities.
Hire Me! I'm currently looking for my next role in developer relations and advocacy. If you've got an open role and think I'd be a fit, please reach out.
I thought I'd start off today with a simple short example. To begin, and remember this may not available just yet, take a look at the docs, Imagen 3 in the Gemini API.
I've been doing GenAI stuff for over a year and I continuously find myself surprised at just how short and simple the code is. That's because, as we're all learning now, so much is driven by the prompt.
The parameters above are a subset and while the rest are documented, as a quick overview you can specify a prompt, of course ("a cat with a top hat").
Read at Raymondcamden
[
|
]