Movatterモバイル変換


[0]ホーム

URL:


Skip to main content
Google DeepMindDeepMind
code
Build with Gemini
spark
Chat with Gemini
Slide 1 of 4

Nano Banana Pro 🍌

Built on Gemini 3. Create and edit images with studio-quality levels of precision and control

Generate clear text

Generate clear text for posters and intricate diagrams, then translate your designs for different locales.

Studio-quality control

Exercise fine control over every aspect of your images for studio-quality results.

Real-world knowledge

Use Gemini’s real-world knowledge to deliver precise results, from complex infographics to historically accurate scenes.

Explore how powerful AI image editing can support advanced creative workflows. Test ideas, create eye-catching designs, and mock up prototypes.

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
A composite image showing a small photo of a woman in an astronaut suit standing in a city, connected to a four-panel hand-drawn storyboard titled 'Scene: Urban Astronaut' that breaks the photo down into an establishing shot, medium shot, close-up, and POV shot.A composite image showing a small photo of a woman in an astronaut suit standing in a city, connected to a four-panel hand-drawn storyboard titled 'Scene: Urban Astronaut' that breaks the photo down into an establishing shot, medium shot, close-up, and POV shot.

Prompt: Create a storyboard for this scene

A woodchuck sitting on a pile of logs in a forest, where the stacked wood pieces are arranged to spell out the 3D text: 'HOW MUCH WOULD A WOODCHUCK CHUCK IF A WOODCHUCK COULD CHUCK WOOD?'

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

A street view of colorful row houses under a blue sky, where the architectural facades of the buildings are shaped to spell out the word 'BERLIN' in large, multi-colored capital letters.

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

The word 'TYPOGRAPHY' designed in a tall, condensed font featuring a retro textured style with blue and pink halftone patterns and a heavy drop shadow.

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

A collection of eight expressive typographic designs for onomatopoeic words, where the visual style matches the meaning: 'CRASH' is broken, 'WHOOSH' is slanted with motion lines, 'SHIVER' is shaky, 'BANG' is explosive, 'DRIP' is melting, 'SQUEEZE' is pinched, 'ROAR' is arched, and 'WOBBLE' is uneven.

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

White typography on a black background featuring the words 'Moebius' and 'Nano Banana Pro' written in an elaborate, swirling, psychedelic typeface.

Prompt: "Nano Banana Pro" in this lettering style

The word 'IMPOSSIBLE' rendered in a 3D isometric style with optical illusion geometry, featuring gradients of yellow, purple, and orange against a black background.

Prompt: Word Impossible as impossible shape, 16:9, make 10 versions, one at a time, each it's own server call

The word 'MAGIC' created using intricate paper quilling art, formed by swirling strips of purple, pink, white, and blue paper against a black background.

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.

Eight words spelled out using the actual food items they represent: 'MINT' made of leaves, 'SOUP' using a bowl and noodles, 'TACO' made of chips, 'CURRY' made of spices, 'SUSHI' made of sushi rolls, 'PASTA' made of dry noodles, 'APPLE' made of fruit slices, and 'PIZZA' made of pizza ingredients.

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
A hand-drawn diagram illustrating a home solar energy system. It shows sunlight hitting solar panels to create energy, which travels through an inverter to power a house. The system includes connections to a storage battery and the main utility grid.

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

A composite image featuring a photo of a String of Turtles plant alongside an illustrated care guide. The guide, titled 'String of Turtles: Peperomia prostrata,' details the plant's reticulated leaf pattern, its origin in Ecuador, its trailing growth habit, and care essentials like bright indirect light.A composite image featuring a photo of a String of Turtles plant alongside an illustrated care guide. The guide, titled 'String of Turtles: Peperomia prostrata,' details the plant's reticulated leaf pattern, its origin in Ecuador, its trailing growth habit, and care essentials like bright indirect light.

Prompt: Create an infographic about this plant focusing on interesting information

Infographic titled 'How to Make Elaichi Chai (Cardamom Tea)' with step-by-step illustrations. Ingredients listed: Water, Milk, Tea Leaves/Powder, Green Cardamom Pods, Sugar, and Ginger (optional). Step 1: Prepare Cardamom & Water – Crush 2-3 cardamom pods. Bring 1 cup of water to a boil. Step 2: Add Tea & Spices – Add 1-2 tsp tea leaves, crushed cardamom, and optional ginger. Simmer 2-3 minutes. Step 3: Pour Milk & Sugar – Pour 1 cup of milk and add sugar to taste. Bring to a boil again. Step 4: Simmer & Steep – Lower heat and simmer for another 2-3 minutes for flavor development. Step 5: Strain & Serve – Strain the hot chai into cups. Enjoy! Tips for Perfect Chai: Adjust sugar and milk to preference; boil longer for stronger flavor; use whole milk for creaminess. The design features warm autumnal colors with decorative floral borders.

Prompt: Create an infographic that shows how to make elaichi chai

A diagram demonstrating the theory of light and color. A beam of white light enters a prism and refracts into a rainbow spectrum, then passes through a second inverted prism to recombine back into a single beam of white light.

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
A side-by-side comparison demonstrating product localization. On the left, three yellow beverage cans feature the English text 'REFRESH & REVIVE' and 'SPARKLING LEMON.' On the right, the same can design is adapted for the Korean market, with the text translated into Hangul characters reading '상쾌함 & 활력' (Refreshment & Vitality).A side-by-side comparison demonstrating product localization. On the left, three yellow beverage cans feature the English text 'REFRESH & REVIVE' and 'SPARKLING LEMON.' On the right, the same can design is adapted for the Korean market, with the text translated into Hangul characters reading '상쾌함 & 활력' (Refreshment & Vitality).

Prompt: Translate all the English text on the three yellow and blue cans into Korean, while keeping everything else the same

Three panels showing the localization of an outdoor digital billboard for a drink called 'Aura Fizz.' The first panel shows the ad in English ('TASTE THE AURA') on a rainy London street with a double-decker bus; the middle panel shows the ad in Spanish ('saborea el aura') on a colorful colonial street; the third panel shows the ad in Japanese in a neon-lit urban setting.Three panels showing the localization of an outdoor digital billboard for a drink called 'Aura Fizz.' The first panel shows the ad in English ('TASTE THE AURA') on a rainy London street with a double-decker bus; the middle panel shows the ad in Spanish ('saborea el aura') on a colorful colonial street; the third panel shows the ad in Japanese in a neon-lit urban setting.

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

An illustration comparison showing how a coffee shop scene is culturally adapted from the UK to Germany. The left image features a red double-decker bus outside and a poster for 'Zestful' juice in English. The right image replaces the bus with a yellow tram, changes the café menu to list 'Kaffee & Kuchen,' and translates the juice poster to German, titled 'Schwungvoll.'An illustration comparison showing how a coffee shop scene is culturally adapted from the UK to Germany. The left image features a red double-decker bus outside and a poster for 'Zestful' juice in English. The right image replaces the bus with a yellow tram, changes the café menu to list 'Kaffee & Kuchen,' and translates the juice poster to German, titled 'Schwungvoll.'

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
A branding design showcase where a simple black-and-white sketch of a bubbly 'WAVE' logo is transformed into various merchandise mockups. The collection includes the blue vector logo, a yellow tote bag, a paper coffee cup, a yellow t-shirt, a white t-shirt with a cap, and street posters reading 'Surf Your Truth Now,' all featuring the logo.A branding design showcase where a simple black-and-white sketch of a bubbly 'WAVE' logo is transformed into various merchandise mockups. The collection includes the blue vector logo, a yellow tote bag, a paper coffee cup, a yellow t-shirt, a white t-shirt with a cap, and street posters reading 'Surf Your Truth Now,' all featuring the logo.

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

A conceptual design image showing a simple line drawing of a car and a photo of a pleated white paper fan being combined. The result is a high-quality 3D rendering of a futuristic vehicle that matches the sketch's shape but is texturally composed of folded white paper, resembling an origami car.A conceptual design image showing a simple line drawing of a car and a photo of a pleated white paper fan being combined. The result is a high-quality 3D rendering of a futuristic vehicle that matches the sketch's shape but is texturally composed of folded white paper, resembling an origami car.

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

A design process image where a line sketch of a curved chair is combined with a reference photo of a colorful polka-dotted vintage car. The output is a photorealistic 3D rendering of the chair, which now features the glossy, bright blue, red, and yellow polka dot pattern from the car, placed in a modern minimal interior.A design process image where a line sketch of a curved chair is combined with a reference photo of a colorful polka-dotted vintage car. The output is a photorealistic 3D rendering of the chair, which now features the glossy, bright blue, red, and yellow polka dot pattern from the car, placed in a modern minimal interior.

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

An architectural visualization display starting with a hand-drawn sketch titled 'Cliff Side Pods (Vertical Habitat).' The sketch is visualized in four distinct 3D rendering styles: a clean white 'clay' model, a realistic miniature diorama model, a close-up view of the metal walkways, and a dramatic sunset rendering of the wooden hexagonal pods attached to a rocky cliff.An architectural visualization display starting with a hand-drawn sketch titled 'Cliff Side Pods (Vertical Habitat).' The sketch is visualized in four distinct 3D rendering styles: a clean white 'clay' model, a realistic miniature diorama model, a close-up view of the metal walkways, and a dramatic sunset rendering of the wooden hexagonal pods attached to a rocky cliff.

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
A side-by-side comparison where a close-up portrait of a woman looking upward is expanded into a wide shot, revealing she is standing in the middle of a large crowd at a concert venue with stage lights in the background.A side-by-side comparison where a close-up portrait of a woman looking upward is expanded into a wide shot, revealing she is standing in the middle of a large crowd at a concert venue with stage lights in the background.

Prompt: Focus on the faces of the crowd and make woman blurry

A split-screen black and white image demonstrating a focus shift. The left side focuses on a mustachioed man's face with his reaching hand blurred in the foreground, while the right side shifts the focus to the sharp details of the hand, blurring the man's face.A split-screen black and white image demonstrating a focus shift. The left side focuses on a mustachioed man's face with his reaching hand blurred in the foreground, while the right side shifts the focus to the sharp details of the hand, blurring the man's face.

Prompt: Focus on man's hand, blur his face

A comparison showing a change in scale. The left image is a close-up of a young woman watching a butterfly, while the right image zooms out to show her as a tiny figure walking through a vast, sun-drenched forest with towering trees.A comparison showing a change in scale. The left image is a close-up of a young woman watching a butterfly, while the right image zooms out to show her as a tiny figure walking through a vast, sun-drenched forest with towering trees.

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
A side-by-side comparison of a landscape featuring a stag standing on a rocky cliff. The left image depicts a moody, misty sunset with the stag in silhouette against a dark sky. The right image transforms the scene into bright daylight with blue skies, white clouds, and a lush green valley visible in the background.A side-by-side comparison of a landscape featuring a stag standing on a rocky cliff. The left image depicts a moody, misty sunset with the stag in silhouette against a dark sky. The right image transforms the scene into bright daylight with blue skies, white clouds, and a lush green valley visible in the background.

Prompt: Change to daytime

A comparison showing how color grading changes the mood of a photo of a red fox in a snowy birch forest. On the left, the scene is lit with warm, pink sunlight. On the right, the same image is color-graded with cool, deep blue tones to simulate a moonlit night.A comparison showing how color grading changes the mood of a photo of a red fox in a snowy birch forest. On the left, the scene is lit with warm, pink sunlight. On the right, the same image is color-graded with cool, deep blue tones to simulate a moonlit night.

Prompt: Turn this scene into nighttime

Two versions of a moody landscape photo showing a person standing in a foggy field at sunrise. The left image features distinct beams of sunlight (god rays) streaming through a tree. The right image replaces the beams with soft, circular bokeh light orbs for a dreamier atmosphere.Two versions of a moody landscape photo showing a person standing in a foggy field at sunrise. The left image features distinct beams of sunlight (god rays) streaming through a tree. The right image replaces the beams with soft, circular bokeh light orbs for a dreamier atmosphere.

Prompt: Replace volumetric lighting with bokeh

A split image showing a black and white portrait of a man wearing a hat with different lighting effects. On the left, his face is evenly shadowed but fully visible. On the right, a 'film noir' style shadow is applied, obscuring most of his face and leaving only a narrow strip of light across his eyes.A split image showing a black and white portrait of a man wearing a hat with different lighting effects. On the left, his face is evenly shadowed but fully visible. On the right, a 'film noir' style shadow is applied, obscuring most of his face and leaving only a narrow strip of light across his eyes.

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
A side-by-side comparison of a black-and-white ink illustration. The left image shows a wide view of a figure standing on a railway bridge looking up at a massive steampunk airship. The right image zooms in closely on the figure and the mechanical details of the ship's underbelly.A side-by-side comparison of a black-and-white ink illustration. The left image shows a wide view of a figure standing on a railway bridge looking up at a massive steampunk airship. The right image zooms in closely on the figure and the mechanical details of the ship's underbelly.

Prompt. Zoom in on this image, maintaining a 16:9 aspect ratio

A comparison showing a surreal scene of an astronaut in a landscape of pink, fluffy clouds. The left image depicts the full astronaut standing in the clouds, while the right image is a close-up crop focusing on the texture and details of the astronaut's life-support backpack and helmet.A comparison showing a surreal scene of an astronaut in a landscape of pink, fluffy clouds. The left image depicts the full astronaut standing in the clouds, while the right image is a close-up crop focusing on the texture and details of the astronaut's life-support backpack and helmet.

Prompt. Zoom in on this image, maintaining a 16:9 aspect ratio

A split image demonstrating a high-resolution zoom on a nature photograph. The left side shows a colorful orb-weaver spider resting on a dew-covered web with a blurred background. The right side is an extreme macro close-up, revealing the minute textures, hairs, and water droplets on the spider's legs and body.A split image demonstrating a high-resolution zoom on a nature photograph. The left side shows a colorful orb-weaver spider resting on a dew-covered web with a blurred background. The right side is an extreme macro close-up, revealing the minute textures, hairs, and water droplets on the spider's legs and body.

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
Collage of fashion photography featuring a Black model with short hair against a solid blue background. She is wearing an elaborate pink gown detailed with pearls, beads, and voluminous feathers, and wears matching pink eyeshadow. The grid includes close-ups of her face and bodice, as well as a full-length shot of the gown.

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

Collage of stylized illustrations depicting a snowy mountain landscape. A lone figure in a blue and red traditional outfit walks away from the viewer along a snowy path. The scene features snow-covered pine trees, bare trees, and towering orange rock formations or ancient ruins carved into the cliffs, all set against a bright blue sky.

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
A split-screen graphic demonstrating image generation. On the left is a grid of 14 small 'input images' showing individual 3D furry monsters of various colors and one sheep against white backgrounds. On the right is a large, cohesive scene showing all these characters sitting together on a couch and floor in a cozy, dimly lit living room, watching a television.A split-screen graphic demonstrating image generation. On the left is a grid of 14 small 'input images' showing individual 3D furry monsters of various colors and one sheep against white backgrounds. On the right is a large, cohesive scene showing all these characters sitting together on a couch and floor in a cozy, dimly lit living room, watching a television.

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

A demonstration of AI scene composition. The left side displays six isolated 'input images': a man working on a dress, a pink floral gown, a cream armchair, two potted plants, and a framed sketch. The right side shows a photorealistic studio scene where the man is adjusting the gown on a mannequin, with the furniture and decor items perfectly integrated into the bright, minimalist background.A demonstration of AI scene composition. The left side displays six isolated 'input images': a man working on a dress, a pink floral gown, a cream armchair, two potted plants, and a framed sketch. The right side shows a photorealistic studio scene where the man is adjusting the gown on a mannequin, with the furniture and decor items perfectly integrated into the bright, minimalist background.

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

A graphic showing the synthesis of individual fashion elements into a group scene. On the left are thumbnails of models wearing avant-garde, white, puffy 'balloon-style' tennis outfits and a standard poodle. The large image on the right depicts a high-fashion editorial shot in a sunny desert setting with concrete architecture, featuring five models in the puffy white outfits posing and walking the dog.A graphic showing the synthesis of individual fashion elements into a group scene. On the left are thumbnails of models wearing avant-garde, white, puffy 'balloon-style' tennis outfits and a standard poodle. The large image on the right depicts a high-fashion editorial shot in a sunny desert setting with concrete architecture, featuring five models in the puffy white outfits posing and walking the dog.

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

A visual example of compositing distinct elements into a cinematic landscape. The left side shows four 'input images': a vibrant sunset, a futuristic astronaut, a rusty space capsule, and a glowing organic stone. The right side combines these into a sci-fi scene where the astronaut stands on a wet beach gazing at a massive orange sun, with the capsule and glowing object resting on the sand.A visual example of compositing distinct elements into a cinematic landscape. The left side shows four 'input images': a vibrant sunset, a futuristic astronaut, a rusty space capsule, and a glowing organic stone. The right side combines these into a sci-fi scene where the astronaut stands on a wet beach gazing at a massive orange sun, with the capsule and glowing object resting on the sand.

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.

A demonstration of consistent character style in AI image generation. On the left is a labeled 'Input image' featuring a close-up 3D render of a man with pink skin, a bulbous nose, a rainbow-colored beard, and a checkered shirt. On the right is a grid of nine scene illustrations retelling the story of 'Goldilocks and the Three Bears' in the same vibrant, colorful, patchwork aesthetic. The scenes depict a girl with colorful pigtails entering a geometric house, eating porridge, breaking a chair, sleeping in a bed, and finally being discovered by a family of three—who all share the input character's distinct colorful beard and style—before she runs away.A demonstration of consistent character style in AI image generation. On the left is a labeled 'Input image' featuring a close-up 3D render of a man with pink skin, a bulbous nose, a rainbow-colored beard, and a checkered shirt. On the right is a grid of nine scene illustrations retelling the story of 'Goldilocks and the Three Bears' in the same vibrant, colorful, patchwork aesthetic. The scenes depict a girl with colorful pigtails entering a geometric house, eating porridge, breaking a chair, sleeping in a bed, and finally being discovered by a family of three—who all share the input character's distinct colorful beard and style—before she runs away.

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
High-angle aerial shot of a scattered crowd walking across a vast, white concrete plaza, casting long, sharp shadows due to bright, low-angle sunlight.

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

Digital sci-fi artwork depicting a futuristic city skyline at dusk with towering skyscrapers and massive spaceships hovering overhead, viewed by a silhouetted couple standing on a high-rise balcony.

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

A lone silhouette stands at the base of a massive, brutalist concrete spiral structure leading up to a circular skylight, illuminated by moody teal and warm yellow lighting.

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

Cinematic close-up profile of a woman with short dark hair standing inside a futuristic, organic structure with glowing, cellular-patterned walls.

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

Long-exposure photography of a dancer in a dark industrial corridor, surrounded by swirling trails of neon pink and blue light created by their movement.

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

Macro photography of a vibrant tree frog with orange, green, and blue skin and large red eyes, perched on a wet green leaf covered in water droplets.

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.

Nano Banana Pro 🍌

Image editing in Gemini just got a major upgrade

Benchmarks

Nano Banana Pro (Gemini 3 Pro Image) is a state-of-the-art image generation and editing model.

Slide 1 of 5
Scatter plot for 'Image Editing' comparing Elo score vs. Latency. Gemini 3 Pro Image achieves the highest quality score, while Gemini 2.5 Flash Image is the fastest. GPT-Image 1 shows significantly higher latency (slower speed) than the others.Scatter plot for 'Image Editing' comparing Elo score vs. Latency. Gemini 3 Pro Image achieves the highest quality score, while Gemini 2.5 Flash Image is the fastest. GPT-Image 1 shows significantly higher latency (slower speed) than the others.
Scatter plot for 'Text to Image' comparing Elo score vs. Latency. Gemini 3 Pro Image has the highest Elo score. Gemini 2.5 Flash Image has the lowest latency (fastest performance). GPT-Image 1 has high latency compared to the Gemini models.Scatter plot for 'Text to Image' comparing Elo score vs. Latency. Gemini 3 Pro Image has the highest Elo score. Gemini 2.5 Flash Image has the lowest latency (fastest performance). GPT-Image 1 has high latency compared to the Gemini models.
Heatmap table showing 'Single-line text rendering error rate' across various languages. Gemini 3 Pro Image has the lowest error rates (mostly under 10%), while Flux Pro Kontext Max shows the highest error rates (frequently 100%).Heatmap table showing 'Single-line text rendering error rate' across various languages. Gemini 3 Pro Image has the lowest error rates (mostly under 10%), while Flux Pro Kontext Max shows the highest error rates (frequently 100%).
Bar chart titled 'Image Editing' comparing Elo scores of models Gemini 3 Pro, Gemini 2.5 Flash, GPT-Image 1, Seedream v4, and Flux Pro. Gemini 3 Pro Image scores the highest across all categories, including Overall Preference, Object/Environment, Stylization, and Consistency.Bar chart titled 'Image Editing' comparing Elo scores of models Gemini 3 Pro, Gemini 2.5 Flash, GPT-Image 1, Seedream v4, and Flux Pro. Gemini 3 Pro Image scores the highest across all categories, including Overall Preference, Object/Environment, Stylization, and Consistency.
Bar chart titled 'Text to Image' showing Elo scores for Overall Preference, Visual Quality, and Infographics. Gemini 3 Pro Image leads in all three categories, with a particularly strong score in Infographics compared to GPT-Image 1 and others.Bar chart titled 'Text to Image' showing Elo scores for Overall Preference, Visual Quality, and Infographics. Gemini 3 Pro Image leads in all three categories, with a particularly strong score in Infographics compared to GPT-Image 1 and others.

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.



Try Nano Banana Pro (Gemini 3 Pro Image)


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.


[8]ページ先頭

©2009-2025 Movatter.jp