Your assistant can generate images from text descriptions and edit existing images using Google’s Gemini image models.
Available models
| Model | Strength | Best for |
|---|
| Gemini 3.1 Flash (Nanobanana 2) | Fast, general-purpose | Quick drafts, iterative exploration |
| Gemini 3 Pro (Nanobanana Pro) | Highest quality | Final assets, detailed illustrations |
Generating images
Ask your assistant to create an image by describing what you want:
- “Generate a photorealistic golden retriever sitting in a park”
- “Create a minimalist logo for a coffee shop called ‘Brew’”
- “Draw a technical diagram of a microservices architecture”
You can specify aspect ratio and detail level:
- “Generate a 16:9 banner image of a mountain landscape at sunset”
- “Create a square icon for a mobile app”
Supported aspect ratios
1:1 · 3:4 · 4:3 · 9:16 · 16:9 · 3:2 · 2:3 · 4:5 · 5:4 · 21:9
Editing images
You can also ask your assistant to modify existing images:
- “Remove the background from this image”
- “Change the sky to a sunset in this photo”
- “Add a watermark to the bottom-right corner”
Attach the image to your message or reference one the assistant previously generated.
Credits
Image generation uses credits from your Coral plan, same as text model requests. The cost varies by model and image size.
Start with the Flash model for quick iterations, then switch to Pro for the final version to conserve credits.
