Gemini 3 Pro Image – Nano Banana Pro — Google DeepMind Skip to main content Explore our next generation AI systems Explore models Gemini Gemini Build intelligent agents Gemini Omni Create anything from anything Nano Banana Create and edit detailed images Gemini Audio Talk, create and control audio Specialized models Veo Generate cinematic video with audio Imagen Generate high-quality images from text Lyria Generate high fidelity music and audio World models & embodied AI Genie 3 Generate and explore interactive worlds Gemini Robotics Perceive, reason, use tools and interact Open models Gemma Build responsible AI applications at scale Our latest AI breakthroughs and updates from the lab Explore research Breakthroughs SIMA 2 An agent that plays, reasons, and learns with you Genie 3 Generate and explore interactive worlds AlphaGo Mastering the game of Go Gemini Robotics Perceive, reason, use tools and interact Learn more Evals Publications Responsibility Unlocking a new era of discovery with AI Explore science Breakthroughs AlphaFold Predict protein structures with high accuracy WeatherNext Fast and accurate AI weather forecasting AlphaEarth Map our planet in unprecedented detail AlphaEvolve Design advanced algorithms for math and applications in computing Learn more Gemini for Science Experimental Tools Science Skills Our mission is to build AI responsibly to benefit humanity About Google DeepMind Responsibility Ensuring AI safety through proactive security, even against evolving threats News Discover our latest AI breakthroughs, projects, and updates Careers We’re looking for people who want to make a real, positive impact on the world Learn more Education Our National Partnerships for AI Accelerator programs The Podcast Models Explore our next generation AI systems Explore models Gemini Gemini Build intelligent agents Gemini Omni Create anything from anything Nano Banana Create and edit detailed images Gemini Audio Talk, create and control audio Specialized models Veo Generate cinematic video with audio Imagen Generate high-quality images from text Lyria Generate high fidelity music and audio World models & embodied AI Genie 3 Generate and explore interactive worlds Gemini Robotics Perceive, reason, use tools and interact Open models Gemma Build responsible AI applications at scale Research Our latest AI breakthroughs and updates from the lab Explore research Breakthroughs SIMA 2 An agent that plays, reasons, and learns with you Genie 3 Generate and explore interactive worlds AlphaGo Mastering the game of Go Gemini Robotics Perceive, reason, use tools and interact Learn more Evals Publications Responsibility Science Unlocking a new era of discovery with AI Explore science Breakthroughs AlphaFold Predict protein structures with high accuracy WeatherNext Fast and accurate AI weather forecasting AlphaEarth Map our planet in unprecedented detail AlphaEvolve Design advanced algorithms for math and applications in computing Learn more Gemini for Science Experimental Tools Science Skills About Our mission is to build AI responsibly to benefit humanity About Google DeepMind Learn more Education Our National Partnerships for AI Accelerator programs The Podcast Responsibility Ensuring AI safety through proactive security, even against evolving threats News Discover our latest AI breakthroughs, projects, and updates Careers We’re looking for people who want to make a real, positive impact on the world Build with Gemini Try Gemini Google DeepMind Google AI Learn about all our AI Google DeepMind Explore the frontier of AI Google Labs Try our AI experiments Google Research Explore our research Products and apps Gemini app Chat with Gemini Google AI Studio Build with our next-gen AI models Google Antigravity Our agentic development platform Models Research Science About Build with Gemini Try Gemini Slide 1 of 4 Nano Banana Pro 🍌 Built on Gemini 3. Create and edit images with studio-quality levels of precision and control Try in Gemini Try in Google AI Studio Generate clear text Generate clear text for posters and intricate diagrams, then translate your designs for different locales. Try in Gemini Try in Google AI Studio Studio-quality control Exercise fine control over every aspect of your images for studio-quality results. Try in Gemini Try in Google AI Studio Real-world knowledge Use Gemini’s real-world knowledge to deliver precise results, from complex infographics to historically accurate scenes. Try in Gemini Try in Google AI Studio Explore the latest Explore how powerful AI image editing can support advanced creative workflows. Test ideas, create eye-catching designs, and mock up prototypes. Your browser does not support the video tag. Capabilities Performance Safety Try Nano Banana Pro Generate clear text Sharp, legible text helps you create impactful posters, intricate diagrams, and detailed product mockups. Describe what type of font you want, or simulate different types of handwriting. Slide 1 of 9 Prompt: Create a storyboard for this scene Prompt: Create an image showing the phrase "How much wood would a woodchuck chuck if a woodchuck could chuck wood" made out of wood chucked by a woodchuck Prompt: View of a cozy street in Berlin on a bright sunny day, stark shadows. the old houses are oddly shaped like letters that spell out "BERLIN" Colored in Blue, Red, White and black. The houses still look like houses and the resemblance to letters is subtle Prompt: A vibrant, eye-catching "TYPOGRAPHY" design on a textured off-white background. The letters are bold, blocky, extra condensed and create a 3D effect with overlapping layers of bright blue and hot pink, each with a halftone dot pattern, evoking a retro print aesthetic. 16:9 aspect ratio Prompt: Make 8 minimalistic logos, each is an expressive word, and make letters convey a message or sound visually to express the meaning of this word in a dramatic way. composition: flat vector rendering of all logos in black on a single white background Prompt: "Nano Banana Pro" in this lettering style Prompt: Word Impossible as impossible shape, 16:9, make 10 versions, one at a time, each it's own server call Prompt: A paper quilling artwork, rendered in the exact style, colors (purple, pink, magenta, white strips), and intricate swirl patterns of depicting the word "MAGIC" in a elaborate, calligraphic script. The paper strips create depth and shadows on a dark grey textured background, similar to the original piece. Prompt: Make 8 sophisticated minimalistic logos, each is a fun food word, and make letters from realistic food to express the meaning of this word. composition: a rendering of all logos on a single solid white background Real-world knowledge Use the Gemini model’s real-world knowledge and deep reasoning capabilities to deliver precise, detailed, rich image results. Annotate pictures, represent data as infographics, or turn handwritten notes into diagrams. Slide 1 of 4 Prompt: High-quality flat lay photography creating a DIY infographic that simply explains how solar energy works, arranged on a clean, light gray textured background. The visual story flows from left to right in clear steps: Content is based on this: https://en.wikipedia.org/wiki/Solar_power. Simple, clean black arrows are hand-drawn onto the background to guide the viewer's eye from the sun to the house, clearly marking the flow of energy. The overall mood is educational, modern, and easy to understand. The image is shot from a top-down, bird's-eye view with soft, even lighting that minimizes shadows and keeps the focus on the process. Format 16:9 Prompt: Create an infographic about this plant focusing on interesting information Prompt: Create an infographic that shows how to make elaichi chai Prompt: Modern, clean, and minimalist flat lay photography illustrating Sir Isaac Newton's theory of light and color, presented on a seamless, matte light gray background. The composition follows a precise, geometric flow from left to right. All annotations are rendered in an ultra-clean, minimalist sans-serif font. Simple, numbered labels—"01", "02", "03", "04" - mark each stage of the process. The concept is a modern visualization of the experiment from Newton's 1671 letter, the content of which can be referenced here: https://hti.osu.edu/sites/hti.osu.edu/files/Sir-Isaac-Newton_Letter-Theory-Light-Colors.pdf The overall mood is scientific, precise, and elegant. The image is shot from a top-down bird's-eye view with bright, perfectly even, shadowless studio lighting to create a clean, high-tech aesthetic. Format 16:9 Translate and localize your ideas Generate localized text, or translate text inside images. See what products might look like in different locales, ready for international markets, and create posters and infographics for use across the world. Slide 1 of 3 Prompt: Translate all the English text on the three yellow and blue cans into Korean, while keeping everything else the same Prompt 1: Create a poster ad for a sparkling water called 'Aura Fizz'. The setting is a London street at dusk with neon lights. The tagline should be "Taste the Aura". The can design should be minimalist. Make the aspect ratio 16:9. Prompt 2: Localize this concept to a Mexico setting, keep the can exactly the same, making sure to include translation Prompt 3: Localize this concept to a Japan setting, keep the can exactly the same, making sure to translate the words "Taste the Aura" accurately and authentically Prompt 1: Design a poster for Zestful's new "Sunrise Defence" smoothie. The style should be playful, quirky, and hand-drawn, featuring the tagline "A little bottle of sunshine." The 16:9 poster is displayed on a digital screen inside a popular coffee chain in London during the morning commute. Prompt 2: Take this concept and localize it to a setting in Germany, including translation Design, style, standardize Turn scribbles into products. Sketches into objects. Ideas into 3D-rendered buildings. Slide 1 of 4 Prompt 1: Create a smooth logo in a graphic style is a vibrant and playful form of typographic illustration, deeply rooted in the retro aesthetics of the 1960s and 1970s loosely based on the sketch Its defining feature is a groovy, psychedelic-inspired typeface characterized by soft, rounded, and fluid letterforms. Don't exactly follow the sketch, get inspired from it. The letters are skillfully distorted, stretched, and compressed, abandoning rigid structure to flow together and form a cohesive, recognizable shape. This technique, known as a calligram, masterfully merges text and image, where the word's form visually embodies its meaning. The word "WAVE" is artfully arranged into the fluid silhouette of a wave. The design is a clever visual pun, making the message instantly accessible and memorable. The color palette reinforces the vintage feel, employing a simple two-toned scheme with warm, often muted or earthy colors light blue background and deep blue logo. This choice enhances the nostalgic charm of the artwork. The overall effect is one of whimsical nostalgia and clever graphic design. It’s a bold yet approachable style that communicates a simple, positive message through the seamless integration of shape and word, creating an immediate and delightful visual impact. Prompt 2: Now create identity system one by one, use 10 high quality mockups with variety of relevant products, ads, billboards, bus stop, etc. generate one at a time, 16:9 each Prompt: Transform the simple sketch into a realistic car, follow creative direction of the sketch and use the colors and texture from the uploaded image Prompt: Transform the simple sketch into a realistic chair, follow creative direction of the sketch and use the colors and texture from the car image Prompt. Create four images for of different architectural design processes based on this image, these need to be consistent with the input sketch. Ensure all text is legible and correctly spelt. Do not show any UI from design software. Generate 4 frames, one by one. You must create 4 separate images and not a single composite image. Studio-quality control Exercise fine control over every aspect of your images, for high-fidelity results. Explore different angles and shot types Wide angle, panoramic, close up – choose an angle and a type of shot. Or alter the depth of field to focus on different subjects in your image. Slide 1 of 3 Prompt: Focus on the faces of the crowd and make woman blurry Prompt: Focus on man's hand, blur his face Prompt. A wide shot of a woman walking in the forest, with sunbeams and volumetric lighting. 16:9 aspect ratio Play with color and lighting Adjust color grades and lighting directions – or even change a shot from day to night, among other dramatic alterations. Slide 1 of 4 Prompt: Change to daytime Prompt: Turn this scene into nighttime Prompt: Replace volumetric lighting with bokeh Prompt: Generate an image with an intense chiaroscuro effect. The man should retain his original features and expression. Introduce harsh, directional light, appearing to come from above and slightly to the left, casting deep, defined shadows across the face. Only slivers of light illuminating his eyes and cheekbones, the rest of the face is in deep shadow Upscale with precision Generate crisp visuals at 1k, 2k or 4k resolution. Slide 1 of 3 Prompt. Zoom in on this image, maintaining a 16:9 aspect ratio Prompt. Zoom in on this image, maintaining a 16:9 aspect ratio Prompt. Zoom in on this image, maintaining a 16:9 aspect ratio Aspect ratios Adapt your visuals for any platform or use by switching the aspect ratio at will. Slide 1 of 2 Prompt 1: change aspect ratio to 1:1 by reducing background. The character, remains exactly locked in its current position Prompt 2: change aspect ratio to 4:3 by reducing background. The character, remains exactly locked in its current position Prompt 3: change aspect ratio to 5:3 by reducing background. The character, remains exactly locked in its current position Prompt 4: change aspect ratio to 1.85:1 by reducing background. The character, remains exactly locked in its current position Prompt 5: change aspect ratio to 2.39:1 by reducing background. The character, remains exactly locked in its current position Prompt 6: change aspect ratio to 2.75:1 by reducing background. The character, remains exactly locked in its current position Prompt 7: change aspect ratio to 4:1 by reducing background. The character, remains exactly locked in its current position Prompt 8: change aspect ratio to 9:16 by reducing background. The character, remains exactly locked in its current position Prompt 9: change aspect ratio to 1:4 by reducing background. The character, remains exactly locked in its current position Prompt 1: change aspect ratio to 4:3 by reducing background. The character, remains exactly locked in its current position Prompt 2: change aspect ratio to 5:3 by reducing background. The character, remains exactly locked in its current position Prompt 3: change aspect ratio to 1.85:1 by expanding background. The character, remains exactly locked in its current position. Prompt 4: change aspect ratio to 2.39:1 by expanding background. The character, remains exactly locked in its current position. Prompt 5: change aspect ratio to 2.75:1 by expanding background. The character, remains exactly locked in its current position. Prompt 6: change aspect ratio to 4:1 by expanding background. The character, remains exactly locked in its current position. Prompt 7: change aspect ratio to 1:1 by reducing background. The character, remains exactly locked in its current position Prompt 8: change aspect ratio to 9:16 by expanding image downwards and upwards. The character, remains exactly locked in its current position. Prompt 9: change aspect ratio to 1:4 by reducing background. The character, remains exactly locked in its current position Subject consistency Maintain the consistency and resemblance of up to five characters and the fidelity of up to fourteen objects in a single workflow. Place your cast in fresh scenes with new outfits, or blend multiple reference images to build complex compositions that retain chosen details. Slide 1 of 4 Prompt: A medium shot of the 14 fluffy characters sitting squeezed together side-by-side on a worn beige fabric sofa and on the floor. They are all facing forwards, watching a vintage, wooden-boxed television set placed on a low wooden table in front of the sofa. The room is dimly lit, with warm light from a window on the left and the glow from the TV illuminating the creatures' faces and fluffy textures. The background is a cozy, slightly cluttered living room with a braided rug, a bookshelf with old books, and rustic kitchen elements in the background. The overall atmosphere is warm, cozy, and amused Prompt: Combine these images into one appropriately arranged cinematic image in 16:9 format and change the dress on the mannequin to the dress in the image Prompt: Put these six people into a single image, they should fit into a stunning award-winning shot in the style of a fashion editorial. the identity of all six people and their attire must stay consistent throughout but they can and should be seen from different angles and distances in as is most natural and suitable to the scene Prompt: Combine these images into one appropriately arranged cinematic image in 16:9 format One prompt, many possibilities Create several images at once to help you explore and review creative options quickly and efficiently. Or use this capability to help sketch out entire stories across a series of images. Prompt: Create a storyboard of a children's book, in the provided style and same color scheme. 10 frames, one by one. No text. Each frame should be a landscape 16:9 Next-level generation Create realistic images of landscapes, plants, people and animals with true-to-life details. Slide 1 of 6 Prompt: This is a high-angle, almost top-down photograph of a crowd of people dispersed across a vast, pale, sun-drenched surface, likely a concrete plaza or a salt flat. The composition feels spacious and uncentered, with figures scattered unevenly throughout the frame. Similar to its companion piece, the most striking artistic element is the interplay of light and shadow. A low, bright sun casts incredibly long, dark, and sharply defined shadows from each person, making the shadow often appear more prominent than the individual casting it. These elongated shadows create a powerful graphic pattern, a rhythmic series of dark lines that slice across the pale ground, all pointing in the same direction. The people themselves are small figures, distinguished by the varied colors of their attire, which appear as small dots of red, black, and blue in the expansive scene. The minimalist, almost bleached-out color palette of the ground starkly contrasts with the dark shadows and colorful specks of humanity, creating a sophisticated and highly stylized composition that explores themes of scale, individuality, and the collective Prompt: From a high-angle, cinematic viewpoint, the image presents a breathtaking panorama of a futuristic megalopolis at twilight. The scene is dominated by two colossal, wedge-shaped starships that hover with silent authority in the hazy air, their dark hulls punctuated by small, illuminated windows that underscore their immense scale. Below them, a dense urban landscape stretches into the distance, a vibrant tapestry of towering skyscrapers and complex structures glowing with a network of warm, golden lights. In the bottom right corner, the silhouettes of a man and woman stand on an unseen balcony, their forms small and dark against the city's luminous grandeur. This off-center composition and the dramatic perspective create a powerful sense of awe and contemplation, portraying a moment of human reflection within an environment of overwhelming technological and architectural achievement, rendered with the polished, atmospheric detail of a high-end concept art piece Prompt: This image captures a dramatic, spiraling interior space, viewed from a perspective near the base of a majestic, curving staircase. The composition is dynamic and asymmetrical, with the smooth, sweeping form of the staircase guiding the eye upward in a graceful, continuous curve. The walls, floor, and ceiling are all rendered in a single, continuous material that appears to be a mottled, patinated teal or verdigris-covered concrete, giving the space a monolithic, cavernous feel. The art style is one of minimalist, sculptural architecture, where form and light are the primary subjects. At the bottom of the frame, a lone, dark, slender figure stands in silhouette, providing a stark sense of scale and adding a solitary, contemplative mood. Light enters the scene dramatically from two sources: a warm, inviting glow illuminates the steps from an unseen point further up the spiral, while a cool, circular skylight high above casts a soft, ethereal light onto the upper wall. The cinematic effect is one of quiet grandeur and mystery, a journey through a space that feels both ancient and futuristic, carved from a single, seamless piece of material Prompt: This cinematic still captures a striking portrait of a woman, rendered with a dramatic, almost theatrical flair. The camera angle is a medium shot, framing her from the waist up, with her profile turned slightly upwards and to the right, as if in contemplation or awe. Her dark, sleek bob haircut frames a delicate face with a prominent nose and full lips, her gaze directed towards an unseen wonder above and beyond the frame. She wears a simple, dark turtleneck, which allows her face and the intricate background to take center stage. Her right hand is raised, fingers slightly splayed, adorned with a single, ornate ring on her ring finger, adding a touch of subtle elegance. The color palette is predominantly cool, dominated by deep blues and grays, with subtle hints of white and silver in the background, creating a mood that is both mysterious and serene. The lighting is low-key, with soft, diffused light illuminating her face and the background, creating a sense of depth and dimension. The ambiance is one of quiet wonder and discovery, inviting the viewer to share in her experience. The background is a swirling, organic tunnel-like structure, reminiscent of a fantastical cave or an alien landscape. It's composed of numerous circular and oval openings of varying sizes, through which a brighter, textured light source is visible, suggesting an otherworldly environment. The texture of the tunnel appears intricate and woven, like a complex web or a futuristic architectural marvel. This composition, with its strong leading lines and central subject, is reminiscent of a meticulously composed shot by a master of visual storytelling, evoking a sense of expansive scale and profound intrigue, often found in a grand science fiction or fantasy epic Prompt: In a burst of uninhibited movement, a figure is captured mid-spin in a corridor of light and mist. The photography freezes the action at its peak, the person’s arms flung wide, their head tilted back in a moment of pure, kinetic release. This rapid twirl has visibly disturbed the dense, colored fog, creating eddies and vortices of cyan, magenta, and violet light around their silhouetted form. The composition is vibrant and chaotic, a stark contrast to a static scene. Light from a warm, yellow-orange portal ahead illuminates the swirling mist from one direction, while a cool blue glow from behind adds depth and complexity to the color palette. The floor, a dark mirror, reflects a blurred, chaotic version of the scene—a painterly smear of motion and color. The camera angle is slightly tilted, a Dutch angle that enhances the feeling of disequilibrium and exhilaration, capturing a fleeting, joyful rebellion against the quiet, contemplative nature of the space Prompt: This is a stunning close-up photograph of a red-eyed tree frog, capturing its vibrant colors and intricate details with remarkable clarity. The frog is positioned on a large, dewy green leaf, its body angled slightly away from the viewer but its head turned to face us. Its most striking feature is its large, bulging red eye with a vertical black pupil, which seems to gaze intently. The frog's skin is a beautiful tapestry of colors: its head and the upper part of its back are a bright, almost lime green, transitioning into a striking orange on its lower back and legs. A band of iridescent blue runs along its side, separating the green from its pale, almost translucent underbelly. The entire surface of the frog and the leaf it rests on are covered in glistening water droplets, which catch the light and add a sense of freshness and life to the scene. The background is a soft, out-of-focus blend of green and teal, which makes the brightly colored frog stand out even more. The photograph is so detailed that you can see the texture of the frog's skin and the tiny suction pads on its orange feet. The overall effect is one of vibrant life and natural beauty, captured in a moment of quiet stillness. Creating your prompts Use detailed prompts to take more control over the images you generate. Think about what you want to see – the characters, the setting, and the overall feel. The more detail you add, the closer the image will be to what you’ve imagined. Learn how to prompt Try in Gemini Benchmarks Nano Banana Pro (Gemini 3 Pro Image) is an image generation and editing model. View model card Slide 1 of 5 Limitations While Gemini can now create a wide range of images, we’re still working on improving key capabilities. You should always carefully check images you create – including text in images – for accuracy. Visual and text fidelity Not every image Gemini generates will be perfect – it can still struggle with small faces, accurate spelling, and fine details in images. Data and factual accuracy The model's real-world knowledge is extensive but not infallible. When generating infographics, annotating diagrams, or representing complex data, it may misinterpret information or produce factually incorrect results. Always verify data-driven outputs. Translation and localization The model is capable of generating and translating text in many languages, but it may struggle with grammar, spelling, cultural nuances, or idiomatic phrases. Complex edits and image blending Advanced features like masked editing, major lighting changes (like day to night), or blending multiple images may sometimes produce unnatural results, visual artifacts, or disjointed scenes. Character features The model excels at character consistency, but it may not always get it right. We're working to make this consistency even more reliable. Safety We use extensive filtering and data labeling to minimize harmful content in datasets and reduce the likelihood of harmful outputs. We also conduct red teaming and evaluations on content safety, including child safety, and representation. Image generation in Gemini has all our latest privacy and safety features. All of our images are imperceptibly watermarked with SynthID technology, allowing you to detect whether an image has been created or edited using AI. Learn more Try in Gemini Try Nano Banana Pro Gemini 3 Pro Image Gemini Supercharge your creativity and productivity Try in Gemini Google AI Studio The fastest path from prompt to production Try in Google AI Studio Gemini API Get started building with cutting-edge AI models Learn more Gemini Enterprise Agent Platform Build, scale, and govern agents Learn more Large Language Models (LLMs), such as Gemini 3 Pro Image, may sometimes provide inaccurate or offensive content that doesn’t represent Google’s views. Use discretion before relying on, publishing, or otherwise using content provided by LLMs. Don’t rely on LLMs for medical, legal, financial, or other professional advice. Any content regarding those topics is provided for informational purposes only and is not a substitute for advice from a qualified professional. Follow us Sign up for updates on our latest innovations I accept Google's Terms and Conditions and acknowledge that my information will be used in accordance with Google's Privacy Policy. Sign up Build AI responsibly to benefit humanity Models Gemini Gemini Omni Nano Banana Gemini Audio Gemma Genie Lyria Veo Research Gemini Robotics Breakthroughs Evals Publications Responsibility Science AlphaFold AlphaGenome WeatherNext AlphaEarth AlphaEvolve Products Gemini app Google AI Studio Google Antigravity Learn more About News Careers National Partnerships for AI Accelerator programs The Podcast About Google Google products Privacy Terms Cookies management controls