{"id":49464,"date":"2025-10-02T18:09:18","date_gmt":"2025-10-02T22:09:18","guid":{"rendered":"https:\/\/mjtsai.com\/blog\/?p=49464"},"modified":"2025-10-02T18:09:37","modified_gmt":"2025-10-02T22:09:37","slug":"nano-banana","status":"publish","type":"post","link":"https:\/\/mjtsai.com\/blog\/2025\/10\/02\/nano-banana\/","title":{"rendered":"Nano Banana"},"content":{"rendered":"

Wikipedia<\/a>:<\/p>\n

Nano Banana (officially Gemini 2.5 Flash Image) is an artificial intelligence image generating and editing<\/a> tool created by Google<\/a>. “Nano Banana” was the codename used on LMArena<\/a> while the model was undergoing pre-release testing, allowing the community to evaluate its performance on real-world prompts without knowing its identity. When the company publicly released it in August 2025, it was part of their Gemini<\/a> line of AI products. The model became known for its editing skills and for starting a social media trend of styled “3D figurine<\/a>” photos.<\/p><\/blockquote>\n\n

Google<\/a>:<\/p>\n

\n

Imagine yourself in any world you can dream up. Our latest AI image generation update, Nano Banana, lets you turn a single photo into countless new creations. You can even upload multiple images to blend scenes or combine ideas. And with an improved understanding of your instructions, it's easier than ever to bring your ideas to life.<\/p>\n<\/blockquote>\n\n

There are tons of apps called<\/em> Nano Banana in the App Store<\/a>, some of them with Google-style icons<\/a>, but none seems to be an official Google app. Neither is the nanobanana.ai<\/a> Web front-end from Google.<\/p>\n\n

PicoTrex<\/a> (via Hacker News<\/a>):<\/p>\n

\n

We present Nano-consistent-150k — the first dataset constructed using Nano-Banana that exceeds 150k high-quality samples, uniquely designed to preserve consistent human identity across diverse and complex editing scenarios. A key feature is its remarkable identity consistency: for a single portrait, more than 35 distinct editing outputs are provided across diverse tasks and instructions. By anchoring on consistent human identities, the dataset enables the construction of interleaved data that seamlessly link multiple editing tasks, instructions, and modalities around the same individual.<\/p>\n<\/blockquote>\n\n

Fstoppers<\/a> (via Hacker News<\/a>):<\/p>\n

\n

Google Just Made Photography Obsolete<\/p>\n<\/blockquote>\n\n

Google<\/a> (tweet<\/a>):<\/p>\n

Our state-of-the-art image generation and editing model which has captured the imagination of the world, Gemini 2.5 Flash Image 🍌, is now generally available, ready for production environments, and comes with new features like a wider range of aspect ratios in addition to being able to specify image-only output.<\/p>

Gemini 2.5 Flash Image empowers users to seamlessly blend multiple images, maintain consistent characters for richer storytelling, perform targeted edits with natural language, and leverage Gemini’s extensive world knowledge for image generation and modification. The model is accessible through the Gemini API<\/a> on Google AI Studio<\/a> and on Vertex AI<\/a> for enterprise use.<\/p><\/blockquote>\n\n

Previously:<\/p>\n