Google Launches Nano Banana Pro Image Model

Google has launched Nano Banana Pro (aka Gemini 3 Pro Image), a professional image model built on Gemini 3 that’s being pushed into creative workflows day one. Adobe integrated the model into Firefly and Photoshop for Text-to-Image, moodboarding, and Generative Fill; the model is also available via Gemini and Google AI Studio (API key required).

Key upgrades: far better text in images (legible multilingual typography), the ability to blend up to 14 reference images while keeping consistency for up to five people, and access to Google Search knowledge to produce more factually accurate visuals. Google will keep visible Gemini watermarks on free/Pro outputs but remove them for Ultra subscribers and Google AI Studio users; it’s also adding a SynthID-based verification tool so you can ask “Is this AI-generated?” and get a check against Google’s embedded watermark.

Why it matters: Nano Banana Pro inherits Gemini 3’s reasoning and benchmarks — Gemini 3 topped the LMArena leaderboard (about a 1501 Elo overall) and posts strong benchmark results across reasoning and vision tasks — making this a pragmatically smarter image model for designers. Adobe is also offering unlimited image generations through Dec. 1 for certain Creative Cloud Pro and Firefly subscribers, making it easy to try the model inside the apps designers already use.

Source