Google's Gemini models include image generation capabilities as part of their multimodal architecture. This means the same model can understand and generate both text and images.
Good to know:
Company: Google
Model Families: Gemini
Free Tier: Yes (with limits)
The latest Gemini model with image generation capabilities. This is a preview model and may change.
A faster, more cost-effective Gemini model with image generation. Does not support size selection.
Text to Image: Yes
Reference Image: Yes
Image to Image (editing): Yes
Multi-Image input: Yes
Go to Google AI Studio and create an API key.
Edit the System - AITiny plugin.
Go to the Image generation tab.
Under Image Service select Gemini.
Enter your API key.
Select your preferred Model.
Click on .
You can use the same Google API key for both the text AI service (Google) and the Gemini image generation service.