Google says it is behind the viral “nano-banana” image model and launches it as Gemini 2.5 Flash Image with finer edit controls in the Gemini app, API, and more
Google is upgrading its Gemini chatbot with a new AI image model that gives users finer control over editing photos …
TechCrunchMaxwell Zeff
Context & Ripple Effects
This launch establishes Nano Banana as a Google-owned image capability rather than a standalone viral novelty, placing it inside Gemini and making it available to developers through the API.
The subsequent arc shows distribution widening from the model’s original surfaces to Search AI Mode and Google Lens, followed by a more controllable Pro version. That makes this release the starting point for a product-family strategy centered on iterative image-editing capabilities.
First-order effects
Gemini users gain more granular photo-editing controls, while API customers can build the same image-generation and editing capability into their own products.
Google turns attention around the viral model into a named Gemini feature, consolidating the experience under its consumer app and developer platform.
Second-order effects
Embedding the model in both a chatbot and API increases pressure on rival image-AI providers to compete not only on generation quality but on editable, product-integrated workflows.
As Google later placed the capability in Search and Lens, image creation and editing can become a feature of visual search journeys rather than a separate destination.
Third-order effects
If the iteration pattern continues, image models are likely to be managed as evolving platform capabilities—new control, text, speed, and personalization layers—rather than one-off model releases.
The durable competitive advantage shifts toward distribution across consumer surfaces and developer tools, a hallmark of a broader synthetic-media control plane.
The trend: This is one early step in the shift from standalone generative-image tools to continuously upgraded, embedded visual-AI services across consumer products and APIs.
Image generation with Gemini just got a bananas upgrade and is the new state-of-the-art image generation and editing model. 🤯 From photorealistic masterpieces to mind-bending fantasy worlds, you can now natively produce, edit and refine visuals with new levels of reasoning, [vide…
🚨🍌Big Reveal: who was “Nano Banana?” The anonymous model, “nano-banana,” that caught the world's attention with its ability to follow complex instructions, preserve character identity, and maintain contextual details was: Gemini-2.5-Flash-Image-Preview by @GoogleDeepMind 🍌✨ [vide…
The new Gemini 2.5 image model🍌is by far the best out there with a whopping +180 ELO point lead in image editing & it really excels at character consistency. Available for free in the @GeminiApp right now. Try uploading an image & playing around with it, it's pretty amazing! [ima…
Introducing Gemini 2.5 Flash Image Preview, our best image generation and editing model! With conversational editing, multi-image composition. Test it now in @googleaistudio! 🍌 🎉 - Maintain character consistency across multiple prompts and images. - Targeted edits/replacing [imag…
nano-banana is here :) Improved native image generation now available in AI Studio and the Gemini API (gemini-2.5-flash-image-preview) SOTA on image generation and editing with leaps in character consistency, precise editing, image combinations, speed, and more. [image]
We just shipped Gemini 2.5 Flash Image, aka nano-banana, a SOTA image generation and editing model 🔥 Among its impressive capabilities, you get native world understanding, multi-image merging, character consistency, and more! https://aistudio.google.com/ ... [video]
Image generation and editing was upgraded in Gemini (Bananas is official now). It's sota and freaking amazing. Seriously, how can Midjourney, Ideogram and all the others continue to compete with Google?
We've just upgraded Gemini 2.5 Flash image generation & editing! 🍌🍌🍌 Besides topping leaderboards, it topped my model usage this month. It keeps subjects consistent, you can make precise edits & combine creative elements. Have fun with it @GeminiApp @GoogleAIStudio [image]
Nano banana turns out to be Gemini Flash 2.5 Image Generation (not quite as catchy a name). I had a bit of early access, first through the same LMArena link everyone had, then privately. It is impressive, crossing a threshold that goes beyond toy (though is a pretty fun toy too) …
It still has the same randomness as other image-gen, and is not free from flaws, but it excels at quick editing of existing images in impressive ways and, most importantly for amateur users, follows instructions very well in a way that can be delightful. Here is my book photo. [i…
🚨Breaking: Google DeepMind has taken a lead . They just dropped Gemini 2.5 Flash Image (nano-banana) Best image editing model right now. Tested on AI Studio for a week and nothing comes close. Thanks to Google DeepMind for early access. More details 👇 Video source : [video]
Gemini-2.5-flash-image-preview (nanobanana) is here! 🥇SOTA image generation and editing 🧑🔧incredible character consistency Checkout nanobanana starting on Mars but staying consistent through an entire planetary journey! Available in @googleaistudio, the Gemini API and [image]
Here's a summary of today's big news: unpeeling the story of a tiny banana. 🤏 🍌 Gemini-2.5-Flash-Image-Preview by @GoogleDeepMind is an image editing model that has taken the world by storm. It allows conditioning on both text and images, so it can follow textual instructions [im…
Introducing Gemini 2.5 Flash Image (aka nano-banana), our SOTA image generation and editing model 🍌 As you might have already seen, this model excels at character consistency, creative edits, and has Gemini's world knowledge! [image]
Our image editing model is now rolling out in @Geminiapp - and yes, it's 🍌🍌. Top of @lmarena's image edit leaderboard, it's especially good at maintaining likeness across different contexts. Check out a few of my dog Jeffree in honor of International Dog Day - though don't let [i…
Google has FINALLY released the best AI image editing model Gemini 2.5 Flash Image can edit any photo or generate new ones from scratch 🔥 You can already use it for free today! Few examples below: [image]
Our new native image generation and editing is state-of-the-art, and ranked #1 in the world. And we're rolling it out for free to everyone today. You've got the tools. Now go bananas. Ideas & inspiration in the 🧵below. [video]