Gemini Image Prompts
26 copy-paste prompts for generating and editing photos in the Gemini app, powered by Gemini 2.5 Flash Image (a.k.a. Nano Banana): text-to-image, photo editing, background swaps, restoration, and product mockups. Free in the Gemini app.
Last updated July 17, 2026
Generating & Editing Images in Gemini
Gemini's image capabilities run on Gemini 2.5 Flash Image, the model most people know by its nickname Nano Banana. It does two things well from inside the Gemini app: it generates images from text, and it edits photos you upload. For generation, describe the picture, subject, setting, style, lighting, and aspect ratio, then refine in follow-up messages. For editing, attach a photo and say what to change in plain language.
What sets it apart is consistency. Give it a photo of a person, pet, or product and it keeps that subject's identity steady, the same face, the same logo, the same color, while you change backgrounds, outfits, seasons, or scenes. It also removes objects, swaps backgrounds, blends multiple images, restores and colorizes old photos, and applies style transfer, all conversationally, so each follow-up refines the last result. There is real free access with a daily quota in the Gemini app and Google AI Studio; heavier use is billed through the Gemini API at about $0.039 per image, and every output carries an invisible SynthID watermark.
Prefer the nickname? Our Nano Banana prompts page covers the same model, and for other assistants see our ChatGPT image prompts. The prompts below are grouped by task, attach a photo where the prompt calls for one, and keep instructions short and specific.
26 Copy-Paste Gemini Image Prompts
Grouped by task. Copy a block, attach your photo where noted, and paste into the Gemini app or Google AI Studio.
Text-to-Image Generation
Describe the picture you want. Name subject, setting, style, lighting, and aspect ratio, then refine conversationally.
Create a photorealistic image of a cozy Scandinavian living room at golden hour, soft natural light through large windows, a linen sofa, a few plants, warm neutral tones, shot at eye level. 16:9.
Generate a vibrant flat-design vector illustration of a city skyline at sunset, bold shapes, a limited warm color palette, clean and modern, suitable for a website hero with space on the left for text.
Create a studio product shot of a matte-black wireless headphone floating on a soft gradient background, gentle reflection below, crisp rim lighting, lots of clean negative space at the top for a headline. 1:1.
Generate a whimsical children's book illustration of a small fox reading a book under a glowing mushroom at night, soft watercolor texture, warm and cozy, gentle bokeh fireflies.
Create a moody cinematic portrait of a chef in a dim kitchen, single warm key light from the side, shallow depth of field, steam rising in the background, film-grain texture. Vertical 9:16.
Photo Editing (attach your photo)
Upload a photo and describe the change. Gemini keeps the subject identical while editing everything you specify.
Keep this exact person identical, same face, hairstyle, and outfit, but change the background to a sunlit Tokyo street at golden hour. Match the lighting on their skin to the new scene.
Remove the person on the far left and the trash can from this photo, then fill the gaps naturally so the background looks seamless and untouched.
Brighten this underexposed photo, recover the washed-out highlights, balance the shadows, and make the colors look natural and true to life without over-saturating.
Keep everything the same but change the season: place this same scene in autumn with warm October light and falling leaves, keeping the people and their poses identical.
Replace the plain wall behind this product with a soft beige studio backdrop and add a gentle shadow beneath it, keeping the product's shape, color, and label exactly the same.
Background Swaps & Object Removal
The most-searched Gemini edits. Say what to keep and what to change, and name the new lighting so it looks believable.
Cut out this person and place them on a clean white studio background with soft, even lighting and a subtle shadow, keeping their exact appearance and pose.
Swap the cloudy sky in this landscape for a dramatic sunset with warm orange and pink tones, and adjust the lighting on the foreground to match the new sky.
Remove the distracting signs and cables from this street photo and reconstruct the buildings behind them naturally, keeping the overall scene recognizable.
Change the background of this headshot to a softly blurred modern office, keeping the person's face, expression, and clothing identical and matching the indoor lighting.
Erase the watermark and the date stamp from the corner of this photo and fill the area seamlessly so it looks like they were never there.
Restoration, Colorization & Style
Revive old photos or reimagine images in a new style while keeping the subject recognizable.
Restore this old, faded photograph: remove scratches, creases, and dust, sharpen the details, and rebuild torn areas while keeping the people's faces exactly as they are.
Colorize this black-and-white portrait with natural, period-accurate tones, realistic skin, hair, and clothing colors, without altering the facial features or expression.
Restyle this photo as a hand-painted watercolor illustration with soft edges and visible brush texture, while keeping the subject, pose, and composition clearly recognizable.
Convert this portrait into a clean line-art ink drawing on white, preserving the exact facial features and hairstyle so it still looks like the same person.
Reimagine this street scene in a warm 1990s film look: gentle grain, soft contrast, slightly faded colors, and a nostalgic glow, keeping the scene unchanged.
Product Mockups & Marketing
Drop your product into polished commercial scenes for ads, listings, and social posts.
Place this product on a minimalist podium against a soft gradient backdrop with studio lighting and a gentle reflection, leaving clean negative space at the top for ad copy.
Create a lifestyle scene: show this skincare bottle on a marble bathroom shelf beside a folded white towel and a small green plant, in bright natural morning light.
Generate a flat-lay social image of this product surrounded by complementary props on a pastel background, top-down, with even lighting and room for a caption.
Mock up this logo printed on a folded heather-grey t-shirt laid flat on a wooden table, with realistic fabric texture and soft daylight shadows.
Blend these two product photos into a single clean flat-lay on a beige background, arranged as a balanced top-down composition with even studio lighting and subtle shadows.
Show this same sneaker on five different surfaces, marble, wood, concrete, grass, and sand, keeping the shoe's shape, colorway, and logo identical in every shot.
8 Tips for Better Gemini Image Results
- For edits, start with 'Keep everything the same except…' so Gemini preserves identity and changes only what you name.
- Use short, clear sentences. Concise instructions consistently beat long, complex paragraphs with this model.
- Edit conversationally: make one change, review it, then refine in your next message instead of rewriting the prompt.
- Name the lighting you want ('warm afternoon light', 'soft studio lighting') so edited or relocated subjects look believable.
- State the aspect ratio (1:1 for feed, 9:16 for stories, 16:9 for widescreen) directly in generation prompts.
- For a consistent series, reuse the same reference image and the phrase 'the same person/product' in every prompt.
- For product shots, describe the surface, props, and mood to get commercial-grade mockups, not flat cut-outs.
- Every image carries an invisible SynthID watermark; use edits for enhancing images you own or have rights to.
Turn your Gemini images into a real site
Building a portfolio, a photo gallery, or a product store around your AI images? Lovable builds the whole site from a plain-English prompt, no code. Free to start.
Affiliate link, we may earn a commission at no extra cost to you.
Gemini Image FAQ
Can Gemini generate and edit images?
Yes. Gemini's image model, Gemini 2.5 Flash Image (widely nicknamed Nano Banana), both generates images from text and edits photos you upload, all in the Gemini app on web and mobile. For generation you describe the picture you want; for editing you attach a photo and describe the change in plain language (swap the background, remove an object, restyle, colorize). Its standout strength is keeping the same person, pet, or product consistent across edits.
How do I generate an image with Gemini?
Open the Gemini app (web or mobile), start a prompt, and either choose the image tools or simply ask it to 'create an image of…' followed by a clear description. Name the subject, the setting, the style, the lighting, and the aspect ratio you want. Gemini generates the image, and because it is conversational you can refine it in follow-up messages ('make it warmer', 'add more space at the top') instead of rewriting the whole prompt.
How do I edit a photo in Gemini?
Attach the photo to your Gemini prompt and describe the edit in natural language, for example 'keep this exact person but change the background to a sunlit beach' or 'remove the person on the left and fill the space naturally.' Gemini preserves the subject's identity while applying your change. Edit conversationally: make one change, review it, then refine in the next message. Every edited image carries an invisible SynthID watermark identifying it as AI-made.
Is Gemini image generation free?
Yes, there is genuine free access. You can generate and edit images in the Gemini app and in Google AI Studio with a daily quota, which is enough for experimentation and light use. Heavier or commercial use is billed through the Gemini API and Vertex AI at roughly $0.039 per image. All generated images include an invisible SynthID watermark. Use edits for enhancing images you own or have the right to use, and avoid impersonating real people.
What is Nano Banana, and is it the same as Gemini image?
Nano Banana is the popular nickname for Gemini 2.5 Flash Image, the exact model powering image generation and editing in the Gemini app. The nickname caught on during anonymous testing on the LMArena leaderboard before Google confirmed it. So 'Gemini image', 'Gemini 2.5 Flash Image', and 'Nano Banana' all refer to the same underlying model, and the prompts on this page work whether you call it Gemini or Nano Banana.
What is Gemini's image model best at?
Consistency and instruction-driven editing. Hand it a photo and it holds the subject's identity steady (same face, same logo, same color) while you change backgrounds, outfits, or scenes. It also blends multiple images into one, restores and colorizes old photos, applies style transfer, and supports conversational multi-turn refinement. For 'keep this exact subject and change one thing' workflows it is usually the fastest, most reliable choice; for crisp readable text inside an image, other models can edge it out.