Gemini Prompt Guide: 38 Powerful Ideas for AI Art (2025)

Reading time 50 minutes

Of course! As requested, here is the complete list of powerful Nano Banana Prompts ready for you to copy and paste, followed by a simple guide on how to use them with Gemini AI.

I. 3D Figures, Dolls & Collectibles

That’s a great way to restructure that information! Based on your request, I’ve converted the table into a simple block format with a sub-heading, description, and code block for each item.

Since you are a web developer and sometimes write blogs, this format might be very useful for creating clean, scannable content on your website, webdevservices.in!

1. Nano Banana 3D Action Figure (Gemini Prompt)

This prompt is designed to generate a highly detailed, commercialized 1/7 scale action figure render of a character, placed in a realistic environment like a computer desk. It includes specific requirements for the base, the computer screen content (showing the ZBrush modeling process), and a BANDAI-style packaging box next to the screen.

create a 1/7 scale commercialized figure of the character in the illustration, in a realistic styie and environment. Place the figure on a computer desk, using a circular transparent acrylic base without any text. On the computer screen, display the ZBrush modeling process of the figure. Next to the computer screen, place a BANDAI-style toy packaging box printed with the original artwork.

2. Chibi Knitted Doll (Gemini Prompt)

This prompt focuses on creating a close-up, warm, and highly tactile photograph of a hand-crocheted chibi yarn doll. The emphasis is on craftsmanship, texture, vivid colors, and a realistic portrayal of hands gently cradling the doll in an intimate indoor setting with natural light.

A close-up, professionally composed photograph showcasing a hand-crocheted yarn doll gently cradled by two hands. The doll has a rounded shape, featuring the cute chibi image of the [upload image] character, with vivid contrasting colors and rich details. The hands holding the doll are natural and gentle, with clearly visible finger postures, and natural skin texture and light/shadow transitions, conveying a warm and realistic touch. The background is slightly blurred, depicting an indoor environment with a warm wooden tabletop and natural light streaming in from a window, creating a comfortable and intimate atmosphere. The overall image conveys a sense of exquisite craftsmanship and cherished warmth.

3. Character Capsules (Gashapon) (Gemini Prompt)

This prompt aims to generate a photorealistic image of a miniature collectible Gashapon (capsule toy) diorama. It requires a transparent capsule held between fingers, featuring a character in an iconic pose within a relevant setting. It calls for dramatic lighting, specific colored base, and labeling with the character’s name or nickname.

A detailed, transparent gashapon capsule diorama, held between fingers, featuring [NAME] in their [ICONIC POSE / STYLE]. Inside: [short description of figure’s look, clothing, and accessories], with background elements such as [relevant setting: stadium, stage, lecture hall, etc.]. Lighting should be dramatic and cinematic, matching their theme. The capsule has a transparent top and a colored base [choose fitting color: e.g., royal blue, gold, black, red], decorated with [motifs related to the person]. The base is labeled with [NAME or NICKNAME] in a matching font style. The design should look like a miniature collectible, with photorealistic detail and soft bokeh.

4. Character Plush Toys (Gemini Prompt)

This prompt is for creating a soft, high-quality plush toy with a classic chibi design (oversized head, small body). It highlights the need for visible stitching, fuzzy fabric, embroidered features, and a realistic, collectible plush aesthetic, usually set against a neutral background with soft, even lighting.

A soft, high-quality plush toy of [CHARACTER], with an oversized head, small body, and stubby limbs. Made of fuzzy fabric with visible stitching and embroidered facial features. The plush is shown sitting or standing against a neutral background. The expression is cute or expressive, and it wears simple clothes or iconic accessories if relevant. Lighting is soft and even, with a realistic, collectible plush look. Centered, full-body view.

5. Funko Pop Figure (Gemini Prompt)

This prompt is focused on generating a detailed 3D render of a chibi-style Funko Pop figure. The key instruction is to accurately and strictly base the figure on a provided reference photo, ensuring high detail, studio lighting, photorealistic texture, and a pure white background.

Create a detailed 3D render of a chibi Funko Pop figure, strictly based on the provided reference photo. The figure should accurately reflect the person's appearance, hairstyle, attire, and characteristic style from the photo. High detail, studio lighting, photorealistic texture, pure white background.

II. Style & Art Transformations

6. iPhone Selfie (Gemini Prompt)

This prompt generates an intentionally ordinary and unremarkable iPhone selfie, mimicking a casual, accidental snapshot. It includes elements like slight motion blur, uneven lighting with mild overexposure, awkward angles, messy composition, and a deliberately plain aesthetic, as if taken unintentionally.

Please draw an extremely ordinary and unremarkable iPhone selfie, with no clear subject or sense of composition — just like a random snapshot taken casually. The photo should include slight motion blur, with uneven lighting caused by sunlight or indoor lights resulting in mild overexposure. The angle is awkward, the composition is messy, and the overall aesthetic is deliberately plain — as if it was accidentally taken while pulling the phone out of a pocket. The subjects are [Names], taken at night, next to the [Location].

7. Chibi Emoji Sticker (Gemini Prompt)

This prompt focuses on creating a set of playful chibi emoji stickers, each depicting a different exaggerated expression and pose (peace sign, crying, hugging, sleeping, pointing, blowing a kiss). It emphasizes the chibi aesthetic with big expressive eyes and soft facial lines, all set against a vibrant red background with star or confetti elements, with white space around each sticker.

Making a playful peace sign with both hands and winking. Tearful eyes and slightly trembling lips, showing a cute crying expression. Arms wide open in a warm, enthusiastic hug pose. Lying on their side asleep, resting on a tiny pillow with a sweet smile. Pointing forward with confidence, surrounded by shining visual effects. Blowing a kiss, with heart symbols floating around. Maintain the chibi aesthetic. Exaggerated, expressive big eyes. Soft facial lines. Background: Vibrant red with star or colorful confetti elements for decoration. Leave some clean white space around each sticker. Aspect ratio: 9:16

8. Ghibli Style (Gemini Prompt)

This is a concise prompt designed to transform an existing photo into the distinctive artistic style of Studio Ghibli, known for its enchanting animation, lush backgrounds, and soft character designs.

Redraw this photo in Ghibli style

9. Game UI (Rhythm Game)

This prompt creates a vibrant screenshot of a rhythm dance game. It features a 3D animated character from a reference photo, maintaining its style and pose, within an immersive environment with cinematic neon lighting, reflective dance floors, and dynamic UI elements like score meters, waveforms, timers, and combo numbers.

A vibrant rhythm dance game screenshot featuring the 3D animated character from the reference photo, keeping its unique style, hat, outfit, and confident dance pose. Immersive cinematic lighting with neon pink and purple glow, glossy reflective dance floor shining under spotlights, and dynamic 3D cartoon style. Rhythm game interface with immersive UI: score meter at the top, colorful music waveform animations synced to the beat, stage timer countdown, and floating combo numbers. Highly detailed, game-like atmosphere with energy bars, neon particle effects, and immersive arcade rhythm game HUD elements. Ultra-detailed, cinematic, immersive, 3D animation.

10. Image Fusion: Combine Multiple Images (Gemini Prompt)

This prompt instructs the AI to combine several distinct images into one cohesive, photorealistic image. The goal is to seamlessly integrate all key subjects while maintaining their proportions, details, and consistent lighting, shadows, perspective, and overall style.

Combine multiple images ([Image1], [Image2], [Image3], …) into a single cohesive image. Keep all key subjects recognizable and maintain their proportions and details. Blend the images naturally with consistent lighting, shadows, perspective, and style. Photorealistic, high-resolution, seamless integration.

11. Style Fusion (Gemini Prompt)

This prompt is designed to apply the artistic style of one image to the subject and composition of another. It requires maintaining the main subject and details from the first image while adopting the colors, textures, and overall aesthetic from the second image, resulting in a high-quality illustration.

Transform this image [Image1] into the artistic style of [Image2]. Keep the main subject, composition, and details from [Image1], but apply the colors, textures, and overall aesthetic of [Image2]. High-quality, [illustraition] style, consistent details.

12. 16-Bit Video Game Character (Gemini Prompt)

This prompt transforms a given character into a 16-bit video game character and places them within a 2D 16-bit platform video game level, evoking the classic retro gaming aesthetic.

Recreate this [Character] as a 16-bit video game character, and place the character in a level of a 2D 16-bit platform video game.

13. Polaroid-Style Photo (Gemini Prompt)

This prompt creates a normal-looking photo with a Polaroid aesthetic. It specifies a slight blur, a consistent light source (like a flash in a dark room), and replacing the background behind the subjects with a white curtain, while keeping their faces unchanged.

Take a picture with a Polaroid camera. The photo should look like a normal photo, without any clear subject or props. The photo should have a slight blur a consistent light source. Such as a flash from a dark room, spread throughout the photo. Do not change the faces. Replace the background behind the two people with a white curtain.

14. AI Hug Younger Self (Gemini Prompt)

This prompt aims to generate a Polaroid-style photo where two people from a reference picture appear to be hugging. It specifies an ordinary photo look with slight blur, consistent flash lighting, and a white curtain background, while keeping the faces unchanged.

Take a photo taken with a Polaroid camera. The photo should look like an ordinary photograph, without an explicit subject or property. The photo should have a slight blur and a consistent light source, like a flash from a dark room, scattered throughout the photo. Don’t change the face. Change the background behind those two people with white curtains. Make it look like both people in the reference picture are hugging each other.

15. AI B&W Studio Portrait (Gemini Prompt)

This prompt is designed to generate a top-angle, close-up, black and white studio portrait focusing on the head, upper chest, and shoulder. It requests a 35mm lens look, high quality (10.7K 4HD), a proud expression, and a deep black shadow background.

Please generate a top-angle and close-up black and white portrait of my face, focused on the head facing forward. Use a 35mm lens look, 10.7K 4HD quality. Proud expression. Deep black shadow background - only the face, the upper chest, and the shoulder.

16. AI Cinematic Portrait (Gemini Prompt)

This prompt creates a vertical cinematic portrait shot using exact face features, characterized by stark lighting and intense contrast. The composition uses a low, upward-facing angle to dramatize the jawline and neck, set against a deep, saturated crimson red background to create a bold visual contrast.

Create a vertical potrait shot using the exact same face features, characterized by stark cinematic lighting and intense contrast. Captured in a slightly low, upward-facing angle that dramatized the subject’s jawline and neck, the composition evokes quite dominance and sculptural elegance. The background is a deep, saturated crimson red, creating a bold visual clash with the model’s luminous skin and dark wardrobe.

III. Precise Image Editing & Control

17. Virtual Change Clothes (Gemini Prompt)

This prompt allows for virtual clothing replacement. It keeps the character, pose, body proportions, and facial features from the first image unchanged, but replaces a specific clothing item (e.g., pants) with the color, texture, and style from an item in a second image, aiming for a high-quality, realistic, and consistent result.

Keep the character in [Image1] unchanged, but replace her pant with the outfit in [Image2]. Maintain the same pose, body proportions, and facial features, while applying the color, texture, and style of the pants in [Image2]. High-quality, realistic, consistent detail.

18. Facial Expression Control (Gemini Prompt)

This prompt enables precise control over a person’s facial expression in an image. It preserves the person’s identity, pose, body proportions, hairstyle, and overall appearance from the first image, while changing only their facial expression to a desired one (e.g., smiling, surprised, angry), ensuring realistic lighting and photorealistic details.

Keep the person from [Image1] unchanged, but change their facial expression to [desired expression, e.g., smiling, surprised, angry]. Preserve the pose, body proportions, hairstyle, and overall appearance. Maintain realistic lighting, shadows, and photorealistic details.

19. Pose Control (Gemini Prompt)

This prompt focuses on transferring specific poses from one image to subjects in another. It instructs the AI to place two men into the exact poses of a man carrying another, while preserving their identities, body proportions, and clothing details. The goal is a natural, realistic pose with consistent lighting, shadows, and perspective.

Take the two men and place them in the exact poses of the man in green carrying the man in red. Preserve their identities, body proportions, and clothing details. Ensure the pose is natural and realistic, with consistent lighting, shadows, and perspective. Photorealistic, high-resolution result.

20. Body Reshape (Gemini Prompt)

This prompt allows for reshaping a person’s body in an image to a target body type. It requires keeping the face, identity, hairstyle, and clothing consistent, while ensuring realistic anatomy, natural proportions, and photorealistic details in the reshaped body.

Reshape the body of the person in [Image1] into a [target body type]. Keep the face, identity, hairstyle, and clothing consistent. Ensure realistic anatomy, natural proportions, and photorealistic details.

21. 3×3 Grid Portrait (Gemini Prompt)

This prompt generates a 3×3 grid of vibrant half-length portraits based on an uploaded photo. Each of the nine portraits should feature a different pose and be placed in a unique natural setting, with rich, colorful details that emphasize the diversity of nature.

Using the uploaded photo as a reference, generate a set of 9 vibrant half-length portraits featuring natural life. Each portrait should show a different pose and be placed in a unique setting, with rich, colorful details that highlight the diversity of nature.

22. Change Image Background (Gemini Prompt)

This prompt replaces the background of an image with a new, desired background (e.g., a beach, a forest, a city skyline). The main subject remains unchanged in its original proportions, lighting, and details, and is seamlessly integrated into the new photorealistic, high-resolution environment.

Replace the background of [Image1] with [desired background description, e.g., a beach, a forest, a city skyline]. Keep the main subject (person/object) unchanged, maintaining original proportions, lighting, and details. Ensure the subject blends naturally with the new environment. Photorealistic, high-resolution, seamless integration.

23a. Add Object to Image (Gemini Prompt)

This prompt is used to add a specified element (e.g., a tree, a lamp, a dog) naturally into an existing image. It ensures the added object matches the scene’s lighting, perspective, and style, while keeping all original elements unchanged, resulting in a photorealistic and seamless integration.

Add [desired element, e.g., a tree, a lamp, a dog] to [Image1]. Place it naturally in the scene, matching the lighting, perspective, and style. Keep the original elements unchanged. Photorealistic, seamless integration.

23b. Remove Object from Image (Gemini Prompt)

This prompt removes a specified element (e.g., a person, a car, a sign) from an image. It naturally fills the background to maintain the scene’s continuity, lighting, and details, ensuring all other elements remain unchanged, resulting in a photorealistic, high-resolution output.

Remove [element to remove, e.g., a person, a car, a sign] from [Image1]. Fill the background naturally to maintain the scene’s continuity, lighting, and details. Keep all other elements unchanged. Photorealistic, high-resolution.

24. Change Camera Angle (Gemini Prompt)

This prompt recreates a subject from an image in four different camera perspectives: Bird’s-eye view, Rear view, Side profile view, and Close-up portrait view. The subject’s identity, proportions, clothing, and background environment remain consistent across all four photorealistic and high-quality variations, presented side by side.

Recreate the person from [Image1] in four different camera perspectives. Keep the subject’s identity, body proportions, and clothing consistent across all four images. Maintain the same background environment as [Image1], with photorealistic lighting, natural shadows, and high-quality details. Generate four variations side by side: Bird’s-eye view (from above). Rear view (from behind). Side profile view. Close-up portrait view.

25. Edit Text in Image (Gemini Prompt)

This prompt allows for editing text within an image. It replaces existing text with new text while keeping the background, design, and other elements unchanged. The new text matches the original font style, size, and color to ensure a natural, consistent, photorealistic, and seamlessly integrated result.

Edit the text in [Image1]. Replace the existing text with “[your new text]” while keeping the background, design, and other elements unchanged. Match the font style, size, and color to look natural and consistent with the image. Photorealistic, seamless integration.

26. Time-Based Image Generation (Gemini Prompt)

This prompt generates an image of the same scene as a reference image, but depicts it 10 minutes later. It maintains consistent environment and style, while naturally incorporating changes over time such as alterations in light, weather, or the presence of people, aiming for photorealistic and seamless continuity.

Generate an image of the same scene as [Image1], but showing how it looks 10 minutes later. Keep the environment and style consistent, but add natural changes over time such as light, weather, people and so on. Photorealistic, seamless continuity.

27. Enhance Image (Gemini Prompt)

This prompt enhances an image to improve its overall quality and detail. It keeps the original composition, colors, and style intact, while increasing resolution, sharpness, texture clarity, and lighting realism, outputting a photorealistic, high-resolution result.

Enhance [Image1] to improve overall quality and detail. Keep the original composition, colors, and style intact. Increase resolution, sharpness, texture clarity, and lighting realism. Output as a photorealistic, high-resolution image.

28. Change the Weather (Gemini Prompt)

This prompt changes the weather in an image to a desired condition (e.g., rainy, snowy, foggy, sunny) while keeping the main subject and overall scene intact. It adjusts lighting, shadows, colors, and environmental effects to match the new weather, aiming for photorealistic, seamless integration and high resolution.

Change the weather in [Image1] to [desired weather, e.g., rainy, snowy, foggy, sunny]. Keep the main subject and overall scene intact. Adjust lighting, shadows, colors, and environmental effects to match the new weather. Photorealistic, seamless integration, high-resolution.

29. Change Image Color (Gemini Prompt)

This prompt changes the color scheme of an image to a desired style (e.g., warm tones, cool blue tones, pastel colors) while maintaining the main subject and composition. It adjusts lighting, shadows, and overall color balance to match the new scheme, resulting in a photorealistic, high-resolution, and natural-looking image.

Change the colors in [Image1] to [desired color/style, e.g., warm tones, cool blue tones, pastel colors]. Keep the main subject and composition intact. Adjust lighting, shadows, and overall color balance to match the new color scheme. Photorealistic, high-resolution, natural-looking result.

30. Image Replace (Gemini Prompt)

This prompt replaces a specific target element or area in an image with a new element (e.g., a different person, object, or scene). It ensures all other parts of the image remain unchanged and that the replacement blends naturally with the existing lighting, perspective, and overall style, resulting in a photorealistic, high-resolution, and seamless integration.

Replace [target element or area] in [Image1] with [new element or reference, e.g., a different person, object, or scene]. Keep all other parts of the image unchanged. Ensure the replacement blends naturally with lighting, perspective, and overall style. Photorealistic, high-resolution, seamless integration.

31. Image Outpainting (Gemini Prompt)

This prompt extends an image beyond its original borders through outpainting. It keeps the main subject and composition intact, generating new content around the edges that matches the style, colors, lighting, and perspective of the original image, aiming for photorealistic, high-resolution, and seamless integration.

Extend [Image1] beyond its original borders using outpainting. Keep the main subject and composition intact. Generate new content around the edges that matches the style, colors, lighting, and perspective of the original image. Photorealistic, high-resolution, seamless integration.

32. 3×3 Photo Grid Pose (Gemini Prompt)

This prompt transforms a given photo into a 3×3 grid of photo strips, with each strip featuring a different studio-style pose and expression from the subject.

Turn the photo into a 3x3 grid of photo strips with different studio-style poses and expressions.

IV. Specialized & Commercial Prompts

33. Object Extraction (E-commerce) (Gemini Prompt)

This prompt extracts a clothing item from an image and converts it into a clean, professional e-commerce product photo. It requires the removal of the model’s body, preservation of the garment’s natural 3D shape, realistic fabric details, and a pure white or transparent background, suitable for an online fashion catalog.

Extract the clothing from [Image1] and present it as a clean e-commerce product photo. Remove the model’s body completely. Keep the outfit in natural 3D shape, with realistic fabric folds, seams, and textures. Display the garment as if photographed on a mannequin or neatly laid flat, centered on a pure white or transparent background. High-resolution, professional lighting, suitable for online fashion catalog.

34. Line to Image (Gemini Prompt)

This prompt is designed to convert line art into a fully colored and detailed image. It preserves the original outlines and composition while applying a desired style (e.g., photorealistic, anime, digital painting) with realistic lighting, shadows, and textures for a high-resolution, seamless rendering.

Convert the line art in [Image1] into a fully colored and detailed image. Preserve all original outlines and compositions. Apply [desired style, e.g., photorealistic, anime, cartoon, digital painting] with realistic lighting, shadows, and textures. High-resolution, natural, seamless rendering.

35. AI Interior Design (Multi-Step)

This is a multi-step prompt for interior design generation. The first step adds core furniture (a gray sofa and wooden coffee table) matching a contemporary style. The second step adds smaller items, daily necessities, and changes the wallpaper to a warmer style, creating a detailed, photorealistic render.

1️⃣ Step one: Add a comfortable gray sofa and a wooden coffee table in the center, matching the room’s contemporary style, photorealistic render. 
2️⃣ Step two: Add more furniture-like items to the foreground and more daily necessities on the table. Also, change the wallpaper to something warmer.

36. Ingredients to Dish/Scene (Gemini Prompt)

This prompt generates an image of a resulting object, dish, or scene based on a provided list of ingredients or items. It requires the composition to be logically sensible, showing the relationship between the items, with clear placement, appropriate proportions, and a specified visual style.

Here are the items available: [List of items]. Based on these items, create an image of a [type of object/scene] that can be made or represented by combining them. The composition should make logical sense, considering the relationship between the items. Ensure the image is [visual style]. It should be with appropriate proportions and clear placement of each item.

37. AI Saree (Gemini Prompt)

This prompt generates a soft, sunlit portrait of a person wearing a flowing sheer yellow saree with delicate floral embroidery. It specifies a graceful sitting pose against a plain wall, warm natural lighting with artistic shadows, and includes details like holding sunflowers, a white flower behind the ear, a gentle expression, and a dreamy golden glow.

Create A soft, sunlit portrait wearing a flowing sheer yellow saree with delicate floral embroidery. Sit gracefully against a plain wall, bathed in warm natural light with a triangular patch of sunlight casting artistic shadows. Hold a vibrant bouquet of sunflowers close to the chest, and a small white flower is tucked behind he ear. Gentle expression, loose hair strands moving slightly, and the dreamy golden glow create a serene, poetic, and romantic.

38. Internal Structure Diagram (Gemini Prompt)

This prompt is designed to create an ultra-detailed, exploded view diagram of a product’s internal structure. It features metallic parts and electronic components floating in mid-air, perfectly aligned to reveal the inner workings, presented with a futuristic technology aesthetic, 8K resolution, and soft cinematic lighting.

Ultra-detailed exploded view of a product, metallic parts and electronic components floating in mid-air, perfectly aligned, revealing inner structure, futuristic technology aesthetic, 8K resolution, soft cinematic lighting, highly realistic.

How to Use Nano Banana AI with the Nano Banana Prompts

The Nano Banana model is the underlying image generation and editing engine available within Google’s AI tools, such as the Gemini App (on mobile/web) or Google AI Studio.

Here is the simple, step-by-step process for using these powerful, pre-written prompts:

Step 1: Access the Nano Banana Tool

Go to the Gemini App (web or mobile) and start a new chat.
Alternatively, the model is integrated into the API and other partner tools like Perplexity’s WhatsApp bot or Adobe Photoshop’s Generative Fill.

Step 2: Upload Your Image (If Required)

If the chosen prompt mentions [Image1], [upload image], or [reference photo], upload the base photo you want to edit or transform.
Note: If the prompt is for pure creation (like a 3D figure from scratch), you can skip the upload.

Step 3: Copy, Paste, and Customize the Prompt

Select and copy the Nano Banana Prompt from the list above.
Paste it directly into the Gemini prompt box.
Crucially, replace all placeholder text inside the brackets (e.g., [desired expression], [NAME], [Location]) with your specific, detailed descriptions.

Step 4: Generate and Refine

Send the prompt to the AI.
The model will generate the image based on the detailed instructions.
Pro-Tip (Iterative Refinement): If the result isn’t perfect, use follow-up commands to refine it without rewriting the whole prompt. For example: “Make the shadows softer” or “Change the background color to emerald green.”

By using these detailed Nano Banana Prompts, you are giving the AI precise, commercial-grade instructions, ensuring high-quality, professional results every time.

Conclusion: Unlock Your Creative Power

The age of struggling with weak, generic AI images is over! By leveraging the power of the Nano Banana Prompt system, you can easily access professional-grade transformations right inside tools like Gemini AI. Whether you’re a designer needing an exploded product view, a marketer visualizing a new outfit, or just a hobbyist creating a Ghibli-style portrait of your pet, these copy-and-paste prompts are your ultimate shortcut.

Now go forth, experiment, and transform your ordinary photos into extraordinary works of art!

Table of Contents