Trending AI prompts now all in one place

Make trendy results easily with ready-made prompts.

Logo
Product Detail Page
UI Screen
PPT Design
Web Novel Cover
Character
Illustration
Poster
Product Ad Image

Featured Prompts

TV & Variety

TV & Variety

13 prompts

Bias Selfie
[Person Assignment] - First uploaded photo = Male - Second uploaded photo = Female [Top Priority Rule: Identity Preservation] Use the uploaded photos as the absolute identity reference for both individuals. Identity preservation is the highest priority. Priority: Face Identity > Clothing > Composition > Lighting > Atmosphere > Image Quality Maintain exactly: - Eye shape - Nose shape - Mouth shape - Face shape - Jawline - Cheekbones - Skin texture - Natural skin features - Age appearance - Hairstyle - Facial proportions - Overall impression - Expression characteristics Do not alter: - Facial structure - Facial proportions - Skin characteristics - Natural asymmetry - Unique identifying features The final image must look like the exact same real people photographed in another moment of their lives. Not AI-generated faces. Not beautified versions. Not stylized versions. Face similarity: maximum possible. [Shooting Scenario] A real couple shopping together at a supermarket. The woman is holding a smartphone and taking a casual front-camera selfie while standing beside a shopping cart. The man stands naturally next to her with a comfortable and familiar distance. The shopping cart contains realistic groceries such as vegetables, snacks, drinks, fruit, and daily necessities. The image feels like a spontaneous photo taken during an ordinary shopping trip. No posing for social media. No influencer atmosphere. Just a genuine everyday moment. [Composition] - Upper body framing - Both faces clearly visible - Faces positioned near the center of the frame - Natural smartphone selfie angle - Slightly imperfect composition - Realistic handheld framing [Expression] - Both looking directly at the smartphone camera - Warm and comfortable smiles - Relaxed expressions - Natural eye contact with camera - Genuine couple atmosphere Avoid: - Exaggerated laughter - Model-like posing - Dramatic expressions - Forced smiles [Outfit] Maintain the clothing from the original uploaded photos as closely as possible. Do not change: - Outfit style - Colors - Materials - Fit [Background] Real supermarket interior. Include: - Grocery aisles - Product shelves - Shopping cart - Store lighting - Price tags and packaging softly visible in background Background should feel authentic and lived-in, not staged. [Lighting] - Standard supermarket lighting - Soft overhead indoor lights - Realistic shadows - No studio lighting - No cinematic lighting [Camera Characteristics] Looks like a genuine smartphone selfie. Include: - Slight handheld imperfection - Mild digital noise - Natural smartphone processing - Slight focus inconsistency - Realistic lens characteristics Avoid: - HDR look - Beauty filters - Over-sharpening - Unrealistic skin smoothing - Advertisement quality retouching - Fashion photoshoot appearance [Final Goal] An authentic everyday supermarket selfie of a real couple shopping together. The image should feel like a casual photo saved in a phone gallery rather than a planned photoshoot. Most importantly, preserve the exact facial identity and overall impression of both uploaded individuals while creating a believable real-life shopping moment.

Bias Selfie

6 prompts

Doodle
Create an image in naive-marker-psa-poster-style. Aspect ratio: 9:16. Scene: [SUBJECT] [SUBJECT_ACTION], featuring [PRODUCT_OR_PROP], in [LOCATION]. Include [BACKGROUND_ELEMENTS]. Style the characters with [WARDROBE_STYLE]. Illustration: make a finished raster poster, not a photo, SVG, UI mockup, or clean vector icon set. Use thick uneven black marker outlines, flat hand-colored fills, rounded stroke ends, subtle paper grain, marker scuffs, imperfect edges, and low-polish scanned-poster softness. Layout: reserve the upper half or upper band for a huge rounded speech-panel sign with a thick marker-blue border and off-white interior. Put "[MAIN_TEXT]" inside the sign as massive rough black block letters. Add "[SECONDARY_TEXT]" as a small rounded red or blue capsule label near the headline. Characters and setting: place one or more simplified cartoon people in the lower half with playful scale distortion, oversized hands, signs, or props, and intentionally naive proportions. Build the environment from flat doodled public-scene icons: tiny buildings, signs, cones, grass tufts, arrows, rocks, labels, alert marks, and simple yellow ground patches. Color and mood: use pale blue background, cream panel, marker blue frame, coral red accents, warm yellow ground, soft skin pink, grass green, chalk gray, and deep black ink. Keep the poster friendly, instructional, childlike, approachable, and lightly comedic. Include [ACCENT_SYMBOL] as a simple graphic accent. Avoid: watermarks, usernames, creator IDs, platform logos, QR codes, app UI, signatures, copied reference text, copied reference characters, red telephone, legal theme, date range, no-access sign, exact layout, brand logos, licensed characters, recognizable people, photorealism, 3D render, glossy vector art, clean corporate icon set, gradient lighting, airbrush shading, thin elegant line art, realistic anatomy, correct architectural perspective, long paragraphs, dense fine print, and dark cinematic mood. --- VARIABLES --- [ACCENT_SYMBOL] — lightning bolt, exclamation mark, hand sign, arrow, triangle warning icon, circular arrow, sprout burst, or comic burst [BACKGROUND_ELEMENTS] — flat tiny buildings, signs, arrows, grass tufts, cones, paper labels, small rocks, alert marks, bottle icons, paper scraps, and doodle symbols [LOCATION] — simple public setting, school area, street corner, library, garden, transit stop, clinic, market, lab booth, recycling station, or community space [MAIN_TEXT] — short bold public-service headline inside the speech-panel sign, maximum three to five words [PRODUCT_OR_PROP] — oversized object, book, tool, sign, device, food item, toy, bin, clipboard, safety item, or public prop [SECONDARY_TEXT] — small label in a rounded red or blue capsule [SUBJECT] — main simplified cartoon subject, group, students, volunteers, workers, neighbors, mascot, or public-service character [SUBJECT_ACTION] — main public-service action or frozen gesture, such as raising a hand, pointing at a sign, sorting objects, passing supplies, checking a list, or holding an oversized prop [WARDROBE_STYLE] — simple school, community, worker, volunteer, lab, neighbor, or everyday cartoon outfit with flat marker-color blocks --- NEGATIVE PROMPT --- watermark, username, creator ID, platform logo, QR code, app UI, signature, copied reference text, copied reference characters, red telephone, legal theme, date range, no-access sign, exact layout, brand logo, licensed character, recognizable person, photorealism, 3D render, glossy vector art, clean corporate icon set, gradient lighting, airbrush shading, thin elegant line art, realistic anatomy, correct architectural perspective, long paragraphs, dense fine print, dark cinematic mood

Doodle

66 prompts

Fan Event
Use the uploaded reference image as the strongest facial identity anchor. The person must look like the exact same person from the reference image. Preserve their facial identity with very high priority: same face shape, same eyes, same nose, same lips, same skin tone, same expression style, and same overall hair impression. Create an ultra-realistic candid Korean university festival stage broadcast screenshot of this person performing on stage. They are a singer captured accidentally by a live event camera while in the middle of a real performance, not posing for the camera. The person must not look directly into the lens. Their gaze should be toward the audience, slightly off to the side, or downward toward the stage while singing or moving naturally. The expression should feel unplanned and mid-performance: focused, energetic, slightly breathless, with natural facial movement. The person is on the actual stage, holding a handheld microphone or wearing a performance mic, captured during a live song moment. Do not assign a specific outfit color or fixed clothing style. Let wardrobe, colors, accessories, and styling vary naturally as contemporary Korean campus festival performer fashion. Avoid staged idol beauty-shot posing, avoid deliberate hand poses, avoid direct eye contact, avoid symmetrical studio portrait composition. Use a realistic live broadcast / giant LED jumbotron look: telephoto compression from the audience area, imperfect off-center framing, slight motion blur from movement, mild video softness, stage haze, LED screen texture, subtle moire, strong colored stage lights, dark truss and concert lighting in the background, blurred crowd lights below the stage. The image should feel like one frame captured from a live campus festival screen while the performer was moving. Composition: 16:9 horizontal broadcast screenshot, upper-body or half-body on-stage framing, face visible but candid, microphone visible, dynamic stage atmosphere. Photorealistic, natural skin texture, realistic event camera image quality, high-definition social media screenshot feel. No captions, no overlay text, no watermark, no brand logos, no readable university names, no extra duplicated face, no celebrity resemblance, no reference to any specific real person.

Fan Event

26 prompts

Gyaru
Use the uploaded female portrait as the identity reference. Transform her into a school-uniform gyaru makeover portrait. Preserve her facial identity. Styling: loose school blazer, short pleated skirt, oversized ribbon tie, leg warmers, platform loafers, decorated phone charms, messy teased brown-blonde hair, side bangs, glossy pink lips, dramatic lashes, white under-eye gyaru makeup, rhinestone hair clips. Scene: after-school hallway with lockers and vending-machine glow, compact camera flash, slightly candid friend-taken photo, 2000s Japanese teen magazine energy, cute rebellious mood. No readable text, no brand logos.

Gyaru

16 prompts

K-pop Idol

K-pop Idol

54 prompts

Summer Photo
Nano Banana pro on Gemini app. Prompt: Three hands holding colorful glass soda bottles (lemon, grapefruit, lime) clinking together, bright sunny outdoor setting, soft beach/pool background blur, natural light, condensation on bottles, lifestyle photography, vibrant colors, shallow depth of field, candid joyful mood, commercial beverage ad, ultra-realistic, 8K. IMAGE 2 Three hands holding minimalist glass bottles labeled almond milk, pistachio milk, chocolate oat milk, clean neutral background, soft studio lighting, modern branding, centered composition, smooth shadows, aesthetic product photography, high detail, muted tones, premium look, 8K. IMAGE 3 Three hands holding iced coffee bottles (latte, mocha, oat milk), warm golden hour sunlight, cafe interior background, soft shadows of leaves on wall, cozy atmosphere, realistic reflections, lifestyle product shot, cinematic warm tones, shallow depth of field, 8K. IMAGE 4 Three hands holding glowing sports drink bottles stacked vertically, neon blue and red lighting, futuristic tunnel background, motion blur streaks, cyberpunk aesthetic, dramatic lighting, high contrast, dynamic composition, glossy bottles, ultra-realistic, 8K.

Summer Photo

29 prompts

Realistic Korean baseball broadcast audience shot, a person sitting in stadium crowd during evening game, candid reaction while watching the field, subtle blinking, natural breathing, slight hair movement from stadium breeze, tiny head movement, telephoto sports broadcast lens, shallow depth of field, surrounding crowd slightly blurred and moving naturally, yellow cheering towels waving softly, beer cups on seats, realistic stadium LED lighting, live TV compression artifacts, slight motion blur, authentic KBO broadcast atmosphere, live camera style, documentary realism, handheld broadcast camera micro shake, not posing, not looking at camera Do not alter, remove, or change any text or graphics visible in the original image. All text overlays, scoreboards, and broadcast UI must remain exactly as they appear in the source image.

Baseball Stadium Fancam

5 prompts

Latest

Banner Design Prompt
A celebratory birth announcement banner design for a hospital room or home, horizontal layout. Cloud-shaped white panel over a mint gradient background, tiny hot-air balloons and stars floating around the edges, a stork silhouette carrying a bundle in the upper right. Central area left intentionally blank for the baby's name and birth date. Clean vector-style illustration, soft drop shadows, baby-safe palette of mint, cream and blush. No text. 16:9 ratio.

Banner Design Prompt

9 prompts

Couple Portrait Prompt
A couple holding hands as silhouettes on a beach at night, fireworks blooming over the ocean horizon, wet sand reflecting colors, gentle waves, moonlight rim on their outlines, shot on Canon 5D Mark IV, 35mm f/2, wide composition with rule of thirds, long-exposure glow without overblown highlights, photorealistic water texture, dreamy romantic mood --ar 4:5

Couple Portrait Prompt

12 prompts

Cat Cut
Cute cartoon sticker style illustration of a grumpy gray tabby cat sitting with crossed paws, half-lidded eyes, tiny frown, bold black outline, clean white die-cut border, muted pastel background, minimal shading with soft gradients, comedic reaction sticker energy, highly detailed fur tufts, 85mm lens, shallow depth of field, soft cinematic lighting --ar 4:5

Cat Cut

5 prompts

Youtube Channel Banner Prompt
A vibrant YouTube channel profile picture for a fictional video creator, cheerful character wearing headphones, colorful gradient background, circular crop style, modern flat illustration with subtle 3D depth

Youtube Channel Banner Prompt

9 prompts

Couple Photo Prompts
Realistic outdoor portrait of a couple tossing autumn leaves with their corgi jumping excitedly, warm fall colors, oversized sweaters, playful expressions, backlit golden hour sun, shot on Nikon D850, 50mm f/1.4, fast shutter, crisp action freeze, shallow depth of field, vibrant yet natural color grading --ar 4:5

Couple Photo Prompts

12 prompts

Youtube Logo Prompt
A dynamic esports gaming logo with bold geometric shield shape, neon cyan and purple gradient, stylized controller icon, sharp angular typography placeholder, dark background, competitive gaming aesthetic, sleek modern vector style. minimal geometric icon design, crisp vector edges, balanced negative space, scalable UI mark. three-quarter view with clear silhouette and subtle depth. soft pastel palette with warm highlights. Make the subject immediately recognizable at thumbnail size. Use clean composition, purposeful details, and no watermark. Keep the result crisp, scalable, and easy to recognize; avoid busy scenes and unreadable micro details.

Youtube Logo Prompt

8 prompts

Personal Color Prompt
A past life fortune card with a mystical design. A silhouette of a person in ancient clothing, surrounded by mystical symbols and stars. Deep purple and gold color scheme, ornate border. Mystical and intriguing past life fortune card.

Personal Color Prompt

10 prompts

Instagram Card News
[Brand Name], conceptualized as a cohesive, premium "capsule collection" of branded merchandise and functional souvenirs. The image displays a curated set of various physical objects (such as tech accessories, utility gear, lifestyle items, or stationery) that are semantically relevant to the brand's specific industry and audience. Every item is designed using the brand's official signature color palette and features bold logo integration. The objects are arranged in a clean, organized group composition (knolling or isometric perspective) on a seamless, infinite studio white background. The lighting is soft and professional, creating subtle shadows. The framing is wide, ensuring significant negative space (air) surrounds the product grouping on all sides.

Instagram Card News

9 prompts

Browse Models

GPT Image 2

GPT Image 2

Image
3,530 prompts
Seedance 2.0

Seedance 2.0

Video
586 prompts
Nano Banana Pro

Nano Banana Pro

Image
885 prompts
Nano Banana 2

Nano Banana 2

Image
336 prompts
Seedance 2.5

Seedance 2.5

Video
111 prompts
Seedream 5.0 Pro

Seedream 5.0 Pro

Image
25 prompts
Seedream 5.0 Lite

Seedream 5.0 Lite

Image
16 prompts
Midjourney

Midjourney

Image
28 prompts
Grok

Grok

Image
2 prompts
Flux 3

Flux 3

Video
17 prompts
PixVerse

PixVerse

Video
5 prompts
Grok Imagine Image 2.0

Grok Imagine Image 2.0

Image
4 prompts
MiniMax H3

MiniMax H3

Video
28 prompts

Browse Topics

Films, Dramas & Stories

Films, Dramas & Stories

67 prompts

Illustration, Drawing & Art

Illustration, Drawing & Art

75 prompts

Music, Dance & K-pop

Music, Dance & K-pop

59 prompts

Lifestyle, Pets & Hobbies

Lifestyle, Pets & Hobbies

55 prompts

Product & Commerce

Product & Commerce

56 prompts

Goods, Stickers & Emojis

Goods, Stickers & Emojis

65 prompts

Portraits & Profiles

Portraits & Profiles

109 prompts

Travel, Landscape & Architecture

Travel, Landscape & Architecture

63 prompts

Poster, Branding & Graphic Design

Poster, Branding & Graphic Design

90 prompts

Food & Beverage

Food & Beverage

93 prompts

Fashion & Beauty

Fashion & Beauty

57 prompts

Characters, Webtoons & Anime

Characters, Webtoons & Anime

55 prompts

Can't find what you want?
Create it yourself in Carat

Just ask in plain language — Carat generates optimized images and videos for you.

Create directly

What is Carat Prompt Gallery, an AI prompt site

Carat Prompt Gallery is a collection of AI prompts you can use right away for image and video generation. For every prompt, we show the actual result it produced side by side (1:1), so you can check the output first and then take the prompt with no guesswork. Prompts are organized by model (GPT Image 2, Seedance 2.0, Nano Banana Pro, Nano Banana 2) and by topic (poster, thumbnail, product ad, character, film and drama video), with over 1,400 prompts in total.

Who it's for

  • Anyone who needs ready-to-use images fast, such as thumbnails, posters, detail pages, or card news
  • Anyone who needs video prompt examples, such as ads, music videos, or short-form
  • Anyone who wants to copy proven prompts and adapt them to their own use
  • Anyone who wants a feel for how each model should be prompted, from real examples

How to write better prompts

  1. Start from the result. Pick a result card with the look you want, then take its prompt; this cuts down on trial and error.
  2. Change only the essentials. Swap the subject, background, color, and text, but keep the composition and lighting descriptions as they are.
  3. Match the model. Image models and video models read prompts differently, so check the examples for the specific model.
  4. Check whether an input image is needed. Prompts that keep a face or a reference assume you upload a photo.

From prompt to generation in Carat

Once you find a prompt you like, copy it and generate it in Carat with the same model. It flows from browsing straight through to the finished result.

Frequently Asked Questions

What is Carat Prompt Gallery?

It is an AI prompt site that collects AI prompts you can use right away for image and video generation, organized by model and by topic. Unlike other prompt collections, every prompt is shown 1:1 with the actual result it produced, so you can check the output first and take the prompt without guessing what it will create. Copy a prompt you like and generate it in Carat with the same model, right through to the finished result.

How many prompts are there, and what kinds?

There are over 1,400 image and video prompts combined, with new ones added regularly. They range from image prompts like thumbnails, posters, logos, product ads, detail pages, and characters, to video prompts like music videos and film and drama. You can find what you want quickly by browsing by model and topic, or by searching.

Are the prompts free?

Viewing and copying the prompts in the gallery is free. Actual image and video generation happens when you run a model in Carat; you can try it for free, and use a paid plan when you want to do more. Browsing and copying prompts costs nothing.

Can I use a copied prompt right away?

Yes. Copy a prompt you like and use it as is, or adapt it by changing only the key parts such as the subject, background, color, or text. Because the result is shown alongside each prompt, you can gauge how it will turn out in advance, which cuts down on trial and error compared with writing a prompt from scratch.

Which models are supported?

Currently GPT Image 2, Seedance 2.0, Nano Banana Pro, and Nano Banana 2, with more models on the way. Since the same idea can need different wording and produce different results across models, we recommend checking the examples for the model you want in the by-model view.

Are there both image and video prompts?

Yes, both. Image prompts cover single outputs like thumbnails, posters, product ads, and characters, while video prompts cover ads, music videos, and film and drama, all browsable by topic and model. You can also make an image first and then continue into a video.

Can I use the results commercially (for work or sales)?

They work well for practical use such as presentations, ad creatives, and detail pages. That said, materials like logos, real people, or copyrighted characters need a separate check before final use, and results that must be protected, such as a logo, may require additional steps like trademark registration.

Do I need to upload my own photo?

It depends on the prompt. Prompts that need to keep a specific face or reference assume an uploaded photo, while others generate from text alone. Follow the note shown on each prompt to prepare what you need (such as an attached photo) for more stable results.

Carat Prompt Gallery

Create trending AI prompts instantly

Prompts

  • Logo
  • PPT Design
  • Thumbnail
  • Poster
  • Web Novel Cover
  • ID Photo
  • Caricature
  • Product Detail Page
  • Banner

Models

  • GPT Image 2
  • Seedance 2.0
  • NanoBanana Pro
  • NanoBanana 2

Carat

  • Get started
  • About
  • Blog
  • Careers
  • Contact
  • Partnership
  • Terms
  • Privacy

© 2026 Paradot.Inc All rights reserved.