Google unveiled a major upgrade to its Gemini app on Monday, September 1, 2025, introducing Nano Banana, a cutting-edge AI image editing model that brings professional-grade capabilities to users, according to CNBC. Developed by Google DeepMind, Nano Banana officially named Gemini 2.5 Flash Image has already topped LMArena’s image-editing leaderboard for its photorealistic output and lightning-fast processing. The tool allows users to transform photos with natural language prompts, ensuring consistent results across multiple edits.
Available now in the Gemini app, Nano Banana enables seamless changes like altering backgrounds, swapping outfits, or merging multiple images while preserving the subject’s likeness. For instance, users can place themselves in a new scene or style a pet in a costume without losing recognizable features, a challenge for earlier AI models. “We know that when editing pictures of yourself or people you know well, subtle flaws matter,” Google noted in a blog post, emphasizing Nano Banana’s focus on maintaining character consistency, per CNBC.
Key features of Nano Banana include:
- Photorealism: Delivers crisp, realistic edits, especially for faces and hands.
- Speed: Generates images in 1.5–2 seconds, outpacing competitors like GPT-4o.
- Multi-Image Fusion: Combines multiple photos into cohesive scenes with ease.
The model, accessible via the Gemini app, API, Google AI Studio, and Vertex AI, supports free users with up to 100 daily edits, while paid users enjoy higher limits. All images carry visible and invisible SynthID watermarks to mark them as AI-generated, addressing concerns about misuse. As Google rolls out Nano Banana, it’s positioning Gemini as a leader in AI-driven creativity, competing with tools like Midjourney and Photoshop, per CNBC. The update is live now, inviting users to explore its transformative potential.
