Imagen 4 is now available in the Gemini API and Google AI Studio

Imagen 4, Google's advanced text-to-image model, is now available in paid preview via the Gemini API and Google AI Studio, offering significant quality improvements, especially for text generation within images. The Imagen 4 family includes Imagen 4 for general tasks and Imagen 4 Ultra for high-precision prompt adherence, with all generated images featuring a non-visible SynthID watermark.

Google logo
Google
•
Alisa Fortin, Guillaume Vernade, Seth Odoom
•3 min read•beginner•
--
•View Original
Gemini

Overview

The article announces the availability of Imagen 4, a text-to-image model, in the Gemini API and Google AI Studio. It highlights the model's improved text rendering capabilities and introduces two variants: Imagen 4 and Imagen 4 Ultra, each tailored for different image generation needs.

What You'll Learn

1

How to utilize Imagen 4 for diverse image generation tasks

2

Why Imagen 4 Ultra is suitable for precise prompt adherence

3

How to access and test Imagen 4 through the Gemini API and Google AI Studio

Key Questions Answered

What improvements does Imagen 4 offer over previous models?
Imagen 4 provides significantly improved text rendering capabilities compared to prior models, enhancing the quality of text-to-image generation. This advancement allows for better handling of a wide range of image generation tasks.
How much does it cost to use Imagen 4 and Imagen 4 Ultra?
Imagen 4 is priced at $0.04 per output image, while Imagen 4 Ultra costs $0.06 per output image. These pricing tiers reflect the models' capabilities and target different user needs.
What are the key features of Imagen 4 Ultra?
Imagen 4 Ultra is designed to produce outputs that closely align with user prompts, achieving strong results compared to other leading image generation models. This makes it ideal for tasks requiring high precision.
Where can I see examples of Imagen 4 in action?
The article provides several examples of images generated by Imagen 4 Ultra, showcasing its versatility across various styles and content, including a cosmic comic and a vintage travel postcard.

Technologies & Tools

API
Gemini API
Used to access Imagen 4 for image generation tasks.
Platform
Google AI Studio
Provides a platform for limited free testing of Imagen 4.

Key Actionable Insights

1
Explore the capabilities of Imagen 4 by testing it in Google AI Studio.
Using the limited free testing option allows you to understand how Imagen 4 can meet your creative needs without initial investment.
2
Consider using Imagen 4 Ultra for projects that require precise adherence to text prompts.
This model is specifically designed for high alignment with user instructions, making it suitable for detailed creative tasks.
3
Stay updated on upcoming billing tiers for Imagen 4 and Imagen 4 Ultra.
As additional billing options are introduced, you may find more flexible pricing that suits your usage patterns.