Nano Banana (Gemini Image)
GoogleNano Banana is Google's name for Gemini's native image generation and editing models, served through the Gemini app, Google products and the Gemini API. The line spans a premium Pro model, a general Flash model with 4K output and a low-cost Lite model, and it generates and edits images conversationally from text, image or video input.
Openness
1 high confidence- weights
- closed(no weights are distributed
- data
- closed
- code
- closed
- license
- Proprietary(Gemini API terms, which bar attempts to extract or replicate the model)
Nano Banana is available only through Google's apps and the Gemini API, and Google's terms forbid extracting the model. No weights, training data or code are published.
- https://ai.google.dev/gemini-api/docs/image-generation recorded 2026-09-26
"Nano Banana is the name for Gemini's native image generation capabilities", served through the Gemini API.
- https://ai.google.dev/gemini-api/terms recorded 2026-09-26
Gemini API terms: "You may not use the Services to develop models that compete with the Services" and may not "reverse engineer, extract or replicate any component of the Services".
Adoption
not assessedGoogle publishes no usage figure for its image models specifically, and a hosted model has no download count, so no reading was possible.
- https://deepmind.google/models/gemini-image/ recorded 2026-09-26
Model page, read for a usage disclosure: none specific to the image models.
Capability
4 medium confidenceNano Banana 2 places just behind OpenAI's models on the text-to-image arena and above every model with downloadable weights. GPT Image holds the top three places, and xAI's and Microsoft's models the next two.
- https://artificialanalysis.ai/image/leaderboard/text-to-image recorded 2026-09-26
Leaderboard entry "Nano Banana 2 (Gemini 3.1 Flash Image)" (rank 6, Elo 1122.8); the first open-weights entry, "Qwen-Image-2.1", is rank 18.
Verified 2026-09-26