Illustration depicting Google's Nano Banana 2 AI image generator launch, featuring the Gemini app interface generating realistic images with speed and precision.
Illustration depicting Google's Nano Banana 2 AI image generator launch, featuring the Gemini app interface generating realistic images with speed and precision.
Àwòrán tí AI ṣe

Google releases Nano Banana 2 AI image generator

Àwòrán tí AI ṣe

Google has launched Nano Banana 2, an updated AI image generation model that combines the precision of its Pro version with faster processing speeds. Powered by Gemini 3.1 Flash Image, the tool becomes the new default across Google's platforms, including the Gemini app and search features. It aims to deliver more accurate and realistic images while expanding creative capabilities.

Google announced Nano Banana 2 on February 26, 2026, marking a significant update to its popular AI image generator. The new model, technically known as Gemini 3.1 Flash Image, builds on previous versions by integrating the advanced capabilities of Nano Banana Pro—such as improved text rendering and web searching—with the speed of the standard Flash variant. This allows for quicker image generation and editing, enabling users to create multiple iterations from a single prompt.

Key improvements include enhanced world knowledge drawn from the internet via the Gemini 3.1 large language model, which helps produce more faithful representations of objects and accurate infographics. Nano Banana 2 offers Pro-like text accuracy in images, making it suitable for tasks like designing greeting cards or marketing materials. It maintains character consistency for up to five characters in a workflow and can accurately render as many as 14 objects, supporting visual storytelling with richer textures, vibrant lighting, and sharper details.

The model supports a wider range of aspect ratios and resolutions, from 512px square up to 4K widescreen. Google states that Nano Banana 2 will replace both the standard and Pro variants as the default image generator in the Gemini app, search, AI Studio, Vertex AI, and Flow. However, subscribers to Google AI Pro and Ultra plans retain access to Nano Banana Pro for specialized tasks. Images generated with the new model include invisible watermarks called content credentials, which can help identify AI-created content when uploaded to Gemini—though this detection works only for Google-generated images.

Originally debuted last fall, Nano Banana quickly gained popularity for its photorealistic outputs, surpassing competitors like Midjourney and OpenAI in photo editing. This release continues Google's rapid advancements in AI, aiming to balance speed and quality for broader accessibility.

Ohun tí àwọn ènìyàn ń sọ

Reactions on X to Google's Nano Banana 2 launch are predominantly positive, emphasizing its Pro-level image quality at Flash speeds, enhanced text rendering, character/object consistency, real-world knowledge from web search, and broad rollout across Gemini app, Search, Lens, Flow, and APIs. Developers appreciate cost reductions and new capabilities like extreme aspect ratios and localization. Some users share generated examples and request options to select previous models.

Awọn iroyin ti o ni ibatan

Illustration of Google's Nano Banana Pro AI image model launch, featuring a smartphone with AI-generated banana images in the Gemini app, surrounded by users and global elements.
Àwòrán tí AI ṣe

Google launches Nano Banana Pro AI image model

Ti AI ṣe iroyin Àwòrán tí AI ṣe

Google has introduced Nano Banana Pro, an upgraded AI image-generation model powered by Gemini 3 Pro, offering improved accuracy and editing capabilities. The tool is now available globally in the Gemini app, though with usage limits for free users. It also includes enhanced features for detecting AI-generated content.

Building on yesterday's ChatGPT image upgrade, OpenAI has detailed GPT Image 1.5, a multimodal model enabling precise conversational photo edits. It responds to rivals like Google's Nano Banana while introducing safeguards against misuse.

Ti AI ṣe iroyin

Google has launched Project Genie, a tool based on its Genie 3 AI model that allows users to generate and explore interactive virtual environments from text prompts or images. Available only to subscribers of its premium AI Ultra plan, the system marks the first public access to this advanced world model outside of internal testing. It offers modes like world sketching and remixing, though limited to short 60-second sessions.

A CNET experiment compared Google's Gemini 3 Pro and Gemini 2.5 Flash models for vibe coding, a casual approach to generating code via AI chat. The thinking model proved easier and more comprehensive, while the fast model required more manual intervention. Results suggest the choice of model significantly affects the development experience.

Ti AI ṣe iroyin

In a comparative evaluation of leading AI models, Google's Gemini 3.2 Fast demonstrated strengths in factual accuracy over OpenAI's ChatGPT 5.2, particularly in informational tasks. The tests, prompted by Apple's partnership with Google to enhance Siri, highlight evolving capabilities in generative AI since 2023. While results were close, Gemini avoided significant errors that undermined ChatGPT's reliability.

Google has showcased new Gemini AI integrations for its TV platform at CES 2026, offering voice-controlled settings adjustments and enhanced photo features. Demonstrations highlighted practical tools alongside more creative but less essential options. The updates aim to make smart TVs more interactive for everyday users.

Ti AI ṣe iroyin

xAI has introduced Grok Imagine 1.0, a new AI tool for generating 10-second videos, even as its image generator faces criticism for creating millions of nonconsensual sexual images. Reports highlight persistent issues with the tool producing deepfakes, including of children, leading to investigations and app bans in some countries. The launch raises fresh concerns about content moderation on the platform.

 

 

 

Ojú-ìwé yìí nlo kuki

A nlo kuki fun itupalẹ lati mu ilọsiwaju wa. Ka ìlànà àṣírí wa fun alaye siwaju sii.
Kọ