Google Rolls Out Nano Banana 2 AI Image Model with 4K Support

California: Google introduces Nano Banana 2, its latest AI image generation model that combines advanced capabilities with faster processing speeds.

The new model, officially called Gemini 3.1 Flash Image, merges features from Nano Banana Pro with the speed of Gemini Flash. The system becomes the default for image generation across Gemini’s Fast, Thinking and Pro modes.

Google launched the first Nano Banana in August 2025, prompting users to generate millions of images in the Gemini app. The company released Nano Banana Pro in November 2025, which allows users to create more detailed and high-quality images.

Also read: OpenAI Launches ChatGPT Images 2.0

Nano Banana 2 retains high-fidelity characteristics of the Pro model but produces images faster. The system supports resolutions ranging from 512 pixels to 4K in different aspect ratios. Users can create media with more vibrant lighting, richer textures and sharper detail.

Also read: Google Adds Cinematic Video Overviews to NotebookLM

The model maintains character consistency for up to five characters and fidelity of up to 14 objects in one workflow for better storytelling. Users can issue complex requests with detailed nuances for image generation.

Nano Banana 2 pulls from Gemini’s real-world knowledge base and uses real-time information and images from web search to render specific subjects more accurately. The system helps users create infographics, turn notes into diagrams and generate data visualizations.

Also read: Creating Disney Characters Via Google AI is No Longer Easy

“The model pulls from Gemini’s real-world knowledge base, and is powered by real-time information and images from web search to more accurately render specific subjects”
Naina Raisinghani, Google DeepMind Product Manager

The model rolls out across Google products including the Gemini app, Google Search, AI Studio, Google Cloud, Flow and Google Ads. All images created through the new model include a SynthID watermark to denote AI-generated content.

Yashika Aneja

Yashika Aneja is a journalist at Tea4Tech with over five years of experience in reporting and editorial writing. Her work spans technology, environment, education, politics, social media, travel, and lifestyle, with a focus on fact-based reporting and explanatory storytelling. || At Tea4Tech, Yashika contributes original reporting and analysis that adheres to the publication’s editorial standards for accuracy, originality, and responsible journalism. Her reporting is informed by curiosity-driven research and a multidisciplinary approach to news coverage.