nano-banana-2
Nano Banana 2 is Google's fast image generation and editing model — text-to-image plus conversational editing, multi-image fusion (up to 14 references) and character consistency. Output at 1K, 2K or 4K. Optional Google Search and Image Search grounding pull current real-world references into the generation.
Input
Describe the image to generate, or the edit to apply when input images are provided.
Optional reference images (up to 14). Leave empty for text-to-image; pass one or more for editing, multi-image fusion, or character-consistency runs.
0 / 14
Output resolution. 2K is the sharper-than-web tier; 4K is print-prep grade. Higher tiers cost more per image.
Output aspect ratio. `match_input_image` inherits from the first reference image; explicit values include the standard set plus four banner-style extremes (1:4, 4:1, 1:8, 8:1).
Output file format.
Use Google Image Search grounding so the model can pull web images as visual context for the generation.
Use Google Web Search grounding so the model can incorporate real-time facts (current products, events, named entities) into the image.
Output
Run the model to see output here.
Pricing
Features
API Examples
curl -X POST \
/api/v1/model/google/nano-banana-2 \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {}
}'