Google Boosts Gemini AI Image Capabilities in Latest Salvo Against ChatGPT
Google launched Gemini 2.5 Flash Picture on Tuesday, delivering a brand new AI mannequin that generates and edits photos with extra precision and character consistency than earlier instruments—making an attempt to shut the hole with OpenAI’s ChatGPT.
The tech large’s push to combine superior picture modifying into Gemini displays a broader push amongst AI platforms to incorporate picture era as essential function. The brand new device, now out there throughout Gemini apps and platforms, lets customers edit visuals utilizing pure language—dealing with advanced duties like pose adjustments or multi-image fusion with out distorting faces or scenes.
In a weblog submit, Google mentioned the mannequin permits customers to “place the identical character into completely different environments, [and] showcase a single product from a number of angles… all whereas preserving the topic.”
🍌 nano banana is right here → gemini-2.5-flash-image-preview
– SOTA picture era and modifying
– unimaginable character consistency
– lightning quick
out there in preview in AI Studio and the Gemini API pic.twitter.com/eKx9lwWc9j
— Google AI Studio (@googleaistudio) August 26, 2025
The mannequin first appeared below the pseudonym “nano-banana” on crowdsourced testing website LMArena, the place it drew consideration for its seamless modifying. Google confirmed Tuesday it was behind the device.
Google mentioned the system can fuse a number of photos, preserve character consistency for storytelling or branding, and combine “world information” to interpret diagrams or mix reference supplies—all inside a single immediate.
The mannequin prices $30 per million output tokens—about 4 cents per picture—on Google Cloud. It’s additionally being distributed by way of OpenRouter and fal.ai.
OpenAI launched the GPT-4o mannequin in Could 2024 and added picture era in March 2025, which helped push ChatGPT’s utilization above 700 million weekly energetic customers. Google reported 400 million month-to-month energetic Gemini customers in August 2025, which might point out weekly utilization that significantly trails OpenAI.
Google mentioned all outputs will embrace an invisible SynthID watermark and metadata tag to mark them as AI-generated to deal with considerations round misuse and authenticity.
