YouMind
Sign in

All Image Prompts

Browse free image prompts from YouMind's AI prompt library, grouped by styles. Every prompt is curated from real creative workflows and ready to copy, adapt, and reuse.

Prompt to ImageImage to Prompt
GPT Image 2.5
Editorial Art Poster with Scratchboard Illustration
View full prompt & copy

Create a high-resolution, vertical 2:3 editorial art poster using the uploaded reference photo. TOP HALF: Use the original photograph full bleed, preserving the subject's identity, appearance, natural lighting, and photographic quality. Crop carefully if needed. No borders or margins. BOTTOM HALF: On textured ivory paper, create a monochrome scratchboard illustration of only the main subject and essential accessories. Place a large, rough-edged black ink block in the center. The figure must be larger than the block, with roughly two-thirds inside it and the lower third breaking out onto the ivory paper. Add loose horizontal ink strokes beneath the feet for grounding. Inside the black block, use fine white and light-grey etched linework. Outside it, continue the same figure in expressive black pen strokes on ivory. Ensure a seamless transition between both tonal styles. Avoid excessive hatching and unnecessary background details. COLORS: The bottom half must use only black, white, and ivory, with subtle paper grain. TYPOGRAPHY: Use rough, upright handwritten lettering. - Top left: a 2 to 4 word title across two lines, followed by three short lowercase verbs separated by periods. - Top right: latitude and longitude on two lines only. - Bottom left: the location or theme followed by “DIARY.”, with a short descriptive sentence beneath. - Keep all typography black on ivory, natural and imperfect, never cursive. FINAL COMPOSITION: Exactly one standalone poster with two equal horizontal halves and one perfectly straight dividing line. Preserve the original subject's identity and proportions. Maintain generous negative space and a restrained, collectible editorial aesthetic, combining documentary photography with expressive hand-printed illustration. Print quality, 2:3 vertical aspect ratio.

Generate image
GPT Image 2.5
Landmark Editorial Poster Generator
View full prompt & copy

Create a premium contemporary editorial poster for [LANDMARK NAME], [CITY], [COUNTRY], using the uploaded photograph of the landmark as the primary visual reference. FORMAT AND COMPOSITION Vertical 3:4 portrait poster, divided into two perfectly equal horizontal sections. The upper half occupies exactly 50% of the total height, and the lower half occupies the remaining 50%. Both sections must have equal heights, with a precise horizontal division at the center. UPPER HALF — ORIGINAL PHOTOGRAPH Preserve the original landmark photograph as faithfully as possible. Maintain the landmark’s authentic architectural identity, silhouette, proportions, distinctive structures, windows, arches, columns, rooflines, materials, and characteristic colors. Retain the original lighting, natural shadows, surface textures, perspective, and surrounding environment. Apply subtle art-magazine color grading with refined tonal contrast, sophisticated color balance, and a contemporary fine-art photography aesthetic. If necessary, extend the background naturally to achieve the portrait composition without stretching, distorting, replacing, or altering the landmark. The photograph should feel authentic, timeless, and editorial rather than artificially enhanced. LOWER HALF — GEOMETRIC ARCHITECTURAL ABSTRACTION Reinterpret the same landmark as a sophisticated modular geometric illustration. Translate its most recognizable architectural features into bold, simplified geometric structures while maintaining an unmistakable visual connection to the photograph above. Construct the illustration using large rectangles, squares, rounded squares, circles, triangles, arches, and carefully composed irregular geometric forms. Recreate the landmark’s distinctive silhouette, structural rhythm, architectural proportions, and recognizable details through overlapping blocks, layered planes, simplified facades, and carefully balanced shapes. Avoid excessive fragmentation, tiny geometric pieces, photorealistic rendering, and generic architectural symbols. Favor fewer, larger, cohesive forms with deliberate spacing and strong compositional structure. Preserve the landmark’s unique identity rather than turning it into an interchangeable building. COLOR AND MATERIAL LANGUAGE Develop the illustration’s palette from the original photograph and the visual character of [COUNTRY]. Use a restrained, harmonious combination of architectural neutrals, muted heritage tones, earthy pigments, and carefully selected accent colors. Introduce subtle paper grain, matte printed surfaces, delicate screen-print textures, and refined color overlays. Maintain a sophisticated balance between flat geometric shapes and tactile printed materials. EDITORIAL ART DIRECTION Create the visual quality of a collectible architecture-art exhibition poster designed for a prestigious independent art magazine. Emphasize architectural rhythm, negative space, geometric balance, precise alignment,

Generate image
GPT Image 2.5
Cinematic Sci-Fi Clone Portrait
View full prompt & copy

Create an ultra-detailed, high-quality cinematic sci-fi film still in a 1:1 square aspect ratio. MAIN SUBJECT: A beautiful young woman standing in the extreme foreground, shown in left-facing side profile, her head slightly lowered and expression calm, mysterious, and confident. She wears a sleek, minimalist black futuristic coat with a high collar. Her dark hair is loosely tied back, with a few natural strands framing her face. Her facial features, skin texture, and hair must look photorealistic and natural. UNEXPECTED VISUAL: Behind her, an impossibly long, perfectly aligned row of identical versions of the same woman stretches into the distance, each wearing exactly the same black outfit and standing completely motionless. The clones gradually disappear into dense atmospheric fog, creating an eerie sense of infinite repetition. ENVIRONMENT: A colossal circular portal dominates the background, glowing with intense emerald green and icy cyan light. Towering futuristic monoliths and thin vertical neon light pillars rise through the darkness. The ground is wet, glossy black stone, reflecting the portal and scattered amber lights. Thick rolling fog flows around the subjects' legs and across the reflective floor. LIGHTING & CAMERA: Dramatic cyan-green volumetric light rays, strong rim lighting outlining the woman's silhouette, deep cinematic shadows, subtle amber highlights, realistic skin pores, fine hair details, rich blacks, controlled highlights, shallow depth of field, and atmospheric perspective. The foreground woman is razor-sharp while the distant clones progressively soften into the mist. VISUAL STYLE: Premium Hollywood dystopian sci-fi, photorealistic cinematic photography, sophisticated color grading, realistic materials, subtle film grain, powerful composition, surreal scale, mysterious atmosphere, and breathtaking visual depth. COMPOSITION: The foreground woman occupies the left third of the square frame. The line of clones creates a strong diagonal leading toward the enormous glowing portal in the background. Every clone has consistent facial identity, anatomy, clothing, and proportions. QUALITY CONTROL: No distorted faces, duplicate body parts, extra limbs, malformed hands, inconsistent outfits, floating objects, random characters, text, logos, watermarks, excessive neon saturation, or artificial plastic skin. Every element must feel intentional, coherent, and visually believable

Generate image
GPT Image 2.5
Starbucks Brew Big Ad Poster
View full prompt & copy

STARBUCKS — “BREW BIG.” 4:5 vertical premium poster, 8K, exaggerated bold typography × high-impact commercial art direction × photorealistic product advertising 🧠 CORE IDEA: “BREW BIG.” 🎬 LAYOUT: BACKGROUND BLOCK: Solid, vivid Starbucks green background with oversized graphic shapes and strong contrast. GIANT TYPOGRAPHY: “BREW” Extremely bold, oversized, tightly cropped typography dominating almost the entire composition. Letters extend beyond the canvas edges, with the Starbucks cup overlapping the text. 👤 SUBJECT: A hand holding an iced Starbucks drink directly toward the camera, extreme forced perspective, cup dramatically enlarged in the foreground, realistic condensation, crisp ice, natural lighting. ☕ PRODUCT + VISUAL TWIST: The Starbucks cup becomes the centerpiece of the typography. The oversized word “BREW” appears to wrap behind the cup, creating striking depth through scale, layering, and composition. Keep the cup, logo, and beverage completely photorealistic. ✨ GRAPHIC ELEMENTS: * Oversized green and white shapes * Sharp contrasting shadows * Minimal starburst accents * Small directional arrows * Bold editorial layering ✍️ TEXT SYSTEM: Top pill: “STARBUCKS COFFEE” Main headline: “BREW BIG.” Supporting text: “YOUR DAILY DOSE OF EXTRAORDINARY.” BOTTOM FEATURE STRIP: * Freshly Brewed * Rich Flavour * Iced or Hot * Made for Your Moment ANTI-SLOP DIRECTION: Typography is the main design feature, not a small decorative element. Extreme scale, aggressive cropping, strong visual hierarchy, deliberate overlap, premium print-ad finish. No floating coffee beans, no miniature landscapes, no random surreal objects, no excessive particles, no cluttered layouts, no generic gradients. The final poster should feel like a bold global advertising campaign with unmistakable graphic impact.

Generate image
Nano Banana Pro
Pixar Style Twin Portrait
View full prompt & copy

Create an ultra-realistic, high-quality studio photograph featuring a real human and a giant 3D Pixar-inspired cartoon version of the SAME person, both accurately matching the uploaded reference image. Both versions must have the same facial features, skin tone, hairstyle, and overall appearance. The real person wears a pastel pink and cream oversized knitted sweater, light blue high-waisted jeans, and clean white high-top sneakers. The Pixar-style character wears the exact same outfit with realistic knitted fabric details. Pose & Expression: The real person stands naturally beside the giant cartoon version, smiling warmly at the camera with one hand resting gently on the cartoon character's shoulder. The cartoon character stands confidently with slightly wider legs, one hand in its jeans pocket, a mischievous smile, one raised eyebrow, and large expressive animated eyes. The cartoon character should be slightly taller and larger than the real person, with a charming 3D animated appearance while maintaining the person's recognizable identity. Background & Lighting: Minimalist gray-blue photography studio, soft professional lighting, subtle floor shadows, realistic skin texture on the human, smooth 3D cartoon shading, detailed sweater fibers, natural denim folds, cinematic composition, sharp focus, premium 3D rendering, 8K quality. Important Instructions: Strictly preserve the identity of the uploaded reference person. Keep the real person's face photorealistic and the cartoon version recognizably identical. Maintain consistent clothing colors, body proportions, and natural interaction between both characters. No extra people, no text, no watermark, no distorted hands, and no unnecessary accessories. Aspect Ratio: 4:5 (Portrait)

Generate image
GPT Image 2
Hand-Drawn Storybook Illustration Prompt
View full prompt & copy

Transform the uploaded photo into a beautiful, heartwarming, hand-drawn storybook illustration. Preserve the original subjects’ recognizable features, hairstyles, poses, expressions, clothing, body language, and emotional connection. Keep the composition and interaction faithful to the reference photo. ART STYLE: Warm, playful, modern children's book illustration with a soft hand-painted, colored-pencil, and crayon texture. Use expressive black-brown sketch outlines, slightly imperfect lines, simplified organic shapes, gentle facial features, rosy cheeks, and natural, joyful expressions. Apply a warm pastel palette with coral pink, dusty blue, caramel brown, soft peach, and creamy off-white. TEXTURE & DETAILS: Visible pencil strokes, subtle paper grain, lightly uneven coloring, sketchy hair strands, minimal shading, and charming handmade imperfections. Create a cozy, nostalgic, affectionate atmosphere full of warmth and personality. BACKGROUND: Simplify the original background into a clean, minimal cream-colored paper backdrop. Add a few small, hand-drawn decorative marks, playful lines, tiny hearts, or expressive doodles that complement the scene without distracting from the subjects. COMPOSITION: Maintain the original framing, subject placement, pose, and interaction. Make the subjects the clear focal point. Use clean shapes, balanced negative space, and an organic editorial storybook aesthetic. IMPORTANT: Illustrate the actual uploaded photo rather than inventing a new scene. Preserve the subjects' identities and defining characteristics. Avoid photorealism, 3D rendering, glossy digital painting, excessive detail, harsh shadows, complex backgrounds, and overly polished vector graphics. No text, watermark, or border. OUTPUT: A high-quality, charming, hand-drawn storybook illustration with a soft vintage print feel, warm colors, visible artistic texture, and genuine emotional expression. Adapt the illustration naturally to the uploaded photo, regardless of the subjects or setting.

Generate image
GPT Image 2
Halloween Wolf Dress Girl
View full prompt & copy

A girl wearing a Halloween wolf-motif dress. The outfit is a dark navy off-shoulder mini dress. Thick grey fur trim on the collar, cuffs, and skirt hem. Large prints of white wolf fangs and paw prints on the skirt. Thin black ribbon at the waist with a fang-shaped charm at the end. Short fur cape on the shoulders. No ears on the head. Small fang pins in the hair. Colors are navy, grey, white, and night blue. Full body visible with fur trim and fang patterns. A slightly wild smile.

Generate image
GPT Image 2
Shallow Depth of Field I2I
View full prompt & copy

Maintain the person, costume, composition, and art style of the original image, and apply a three-dimensional focus expression with shallow depth of field. Focus center on eyes and face. Keep pupils, eyelashes, and main facial lines clear. As you move away from the focal plane of the face, smoothly blur hair, shoulders, costume, and background according to distance. Create natural focus differences within the person as well. Add soft foreground bokeh to hair and shoulders close to the camera, and large melting background bokeh for the background. Describe point light sources in the background as soft circular bokeh. Illuminate hair and skin contours thinly with warm diagonal backlighting, adding subtle bloom and light bleed only to strong highlights. Maintain calm darkness in shadows to create cinematic depth that draws the eye to the face. Uniform blurring across the entire screen is prohibited. Do not erase facial details; maintain the original line art and drawing texture.

Generate image
GPT Image 2.5
Surfer Riding Barrel Wave at Sunset
View full prompt & copy

A breathtaking, hyper-realistic action photograph of a male surfer riding deep inside the barrel of a massive, curling ocean wave. The shot is taken from a low angle at water level, looking directly into the hollow tube of the wave. The surfer, who has tanned skin and wet dark hair, wears dark board shorts and crouches low on a white surfboard, his body angled forward with intense focus as he navigates the curve. The interior of the wave glows with translucent emerald green and turquoise tones where the sunlight passes through the water. To the left, the sun is setting near the horizon, creating a brilliant golden starburst effect that illuminates the spray and mist exploding off the lip of the wave in warm orange and yellow hues. In the far background on the left, silhouetted mountains and palm trees are visible along the coastline under a sky filled with soft, scattered clouds tinged with sunset colors. The foreground features rippling blue-green water reflecting the golden light. The image captures high-speed motion with sharp detail on the water droplets and foam, showcasing a dramatic contrast between the cool teal of the wave and the warm gold of the sunset.

Generate image
GPT Image 2.5
Maker Bench Notes Anchor Chart
View full prompt & copy

Hand-drawn classroom anchor chart on cream lined notebook paper, kawaii illustration style, clean handwritten markers, playful doodles. Vertical 4:5. Cream notebook paper with blue ruled lines and a faint pink margin. Title at top in bold coral marker: "Maker Bench Notes". Subtitle paragraph in fine black pen: "A one-page cheat sheet for lighting a product still." Green marker subtitle: "Core Moves". Bullet list in black fine pen on the left half: "Name the subject + surface first."; "Pick one key light direction and stick to it."; "Add a soft bounce fill, not a second hard light."; "Keep reflections honest — metal, glass, matte each behave differently."; "Crop tight enough that props support the hero, not compete."; "Write a short negative list for logos and text drift.". Right side: three small coral cloud bubbles, each containing a simple bolt-and-washer doodle, no text inside bubbles. Lower center: a cute matte charcoal raccoon sitting side-view with big eyes, tiny nose, soft cream cheek highlight, thick teal outline, no text on the raccoon. Lower-left corner: a surreal hand-drawn doodle eye with concentric iris rings, a tiny star pupil, three lashes, subtle drip, purple stroke with teal accent. Handwritten marker variation, slight ink bleed, visible paper texture, flat overhead classroom light. No photorealistic fur, no 3D gradients, no logos, no watermark, no UI chrome.

Generate image
Nano Banana Pro
Early 2000s Internet Cafe Webcam Couple
View full prompt & copy

A candid couple photo of the Woman's Look and Man's Look in the Setting, engaged in the Activity. Render it as the Camera Type, with soft focus, smeared facial detail, color noise, dim uneven indoor light and low-resolution compression. Use awkward webcam framing from a desk-level angle, with a slight tilt and casually cropped shoulders or arms. Include the Era Props naturally in the booth. The couple should look genuinely close and relaxed, with real skin, messy everyday hair and no heavy retouching. Use Face Reference for the matching faces when applicable. Make it feel like an unedited early-2000s personal photo from an old Facebook album or MSN chat, not a modern image with a retro filter. No date stamp, text, watermark, modern electronics or current fashion. Output in the Format. Use these details: Woman's Look: "Young woman in her early 20s with straight black hair, a casual graphic T-shirt and a loose zip hoodie" Man's Look: "Young man in his early 20s with a thin mustache, tousled hair and a worn casual sweatshirt" Setting: "A cramped internet cafe booth with a laminate desk, worn carpet, beige walls and bulky CRT monitors" Activity: "Leaning close together and looking into the webcam during an online chat" Camera Type: "Low-resolution built-in webcam capture from a chunky desktop computer" Era Props: [Wired earphones, A burned CD in a paper sleeve, A chunky desktop keyboard] Face Reference: "Use attached photos for the matching person's face when provided; if none are attached, invent both faces" Format: "4:3 landscape"

Generate image
GPT Image 2.5
Assembling Police Robot Model Kit
View full prompt & copy

A hyper-realistic, high-resolution photograph of a complex plastic model kit (gunpla style) in mid-assembly on a workbench. The central subject is a bipedal police robot with a black skeletal frame and white armor plating. The robot features a head composed of multiple camera lenses arranged horizontally, red emergency light bars on its shoulders, and '警視庁 MPD' text printed on the chest and shoulder plates. Surrounding the standing robot are numerous sprue trees containing unassembled black and white parts, scattered loose components including detached hands and feet, and an open instruction manual showing line art diagrams. In the background to the right stands the product box featuring an illustration of the completed robot against a blue sky with clouds and the Tokyo Skytree visible; the box reads '警視庁 MPD' and '1/100 SCALE PLASTIC MODEL KIT'. A bottle of Tamiya-style paint sits near the box. On the green cutting mat surface in the foreground lie hobby tools including side cutters, tweezers, and a metal tray filled with tiny screws or pins. The lighting is soft and natural, highlighting the glossy texture of the plastic and the mechanical details.

Generate image
GPT Image 2.5
Authentic Cyanotype Sun Print Transformation
View full prompt & copy

Transform the attached photograph into a single, authentic cyanotype sun print, photographed as a physical artwork. Vertical 4:5 composition. THE SHEET A handmade cyanotype on thick cotton rag paper, lying on a plain, pale surface in soft natural daylight. The image fills most of the sheet, leaving visible white margins on all four sides. Keep the entire sheet inside the frame, with at least three edges clearly visible and one edge preferably showing a fibrous tear. The paper has subtle cockling from washing and drying, with realistic surface texture and a soft shadow along one side. HAND-BRUSHED COATING The photosensitive coating is applied by hand. Blue boundaries are naturally irregular, with visible brushstroke endings, small uncoated patches, uneven edges, and a few stray blue flecks on the white margins. Avoid perfectly straight, mechanical borders on all four sides. CYANOTYPE TONES Use only authentic cyanotype colours: - Shadows: Deep Prussian blue. - Midtones: Pale to medium cyan. - Highlights: Completely bare, raw white paper with no blue pigment. Maintain strong contrast and abrupt transitions between blue and white where appropriate, as in a traditional contact print. Fine paper fibres should remain visible through the blue. No grey, black, sepia, or additional colours. The result must look like a chemically produced cyanotype, not a blue filter over a photograph. PRESERVE THE ORIGINAL IMAGE Use the attached photograph as the sole source. Preserve the exact number, identity, position, proportions, silhouettes, poses, and arrangement of all subjects. Do not add, remove, duplicate, or rearrange people, animals, vehicles, or environmental details. Translate the original photograph into cyanotype tones only: bright areas become bare paper white, midtones become cyan, and dark areas become deep Prussian blue. Preserve the original composition and recognisable facial and body shapes. PHYSICAL PRESENTATION Photograph the finished print as a real object resting on a plain, pale surface. Use soft directional daylight, realistic paper fibres, subtle shadows, and natural surface imperfections. Keep the entire sheet visible within the vertical 4:5 frame. STRICT NEGATIVE CONSTRAINTS - No text, letters, numbers, signatures, logos, stamps, or watermarks. - No additional or missing subjects. - No grids, graph lines, measuring scales, or blueprint-style graphics. - No blue tint in the brightest highlights; they must be raw paper white. - No extra colours, decorative effects, or artificial distressing. - No hands, clips, frames, tools, props, or additional sheets. - No cropping of the sheet or digitally flat presentation. PRIORITIES If every detail cannot be achieved simultaneously, prioritise preserving the exact original subjects and making the brightest highlights completely paper white. Next, maintain realistic physical paper texture and visible sheet edges. If necessary, simplify the brushed margins to one ir

Generate image
GPT Image 2
GPT Image 2 Prompt Length Comparison
View full prompt & copy

A horizontal triptych comparison image with a dark navy background, divided into three equal vertical panels. Each panel displays a photorealistic 3D render of a fantastical 'Space Library' scene, illustrating the difference in prompt complexity. Left Panel: Labeled "5 WORDS" at the bottom in white sans-serif text. The image shows an exterior wide shot of a grand, ornate library building floating in deep space. It features a large glass dome revealing a galaxy interior, surrounded by nebulae and stars, with a reflection on a water-like surface below. Center Panel: Labeled "25 WORDS" at the bottom. The image is an interior perspective looking out through a massive curved window at a giant ringed planet (resembling Saturn). Inside, there are tall wooden bookshelves lining the walls, a cozy leather armchair, a small table with a lamp, and a patterned rug on a polished floor. Right Panel: Labeled "100 WORDS" at the bottom. The image is a close-up interior detail shot featuring a wooden desk with an open book, a brass banker's lamp, and a globe. Behind it, large arched windows look out onto the same ringed planet and starry sky, with warm lighting contrasting against the cool blue space background.

Generate image
GPT Image 2
Giant MPD Robots Carrying Heavy Load
View full prompt & copy

A photorealistic, wide-angle shot of two massive bipedal humanoid robots standing on a wet concrete surface at a Japanese port. The robots are painted in white and dark grey armor plating with red emergency lights on their shoulders and heads. Each robot has '警視庁' (Metropolitan Police Department) and 'MPD' written in black text on their chest plates and shoulder guards. They are jointly holding a large, heavy industrial metal container or piece of machinery between them. In the background, there is a suspension bridge (resembling Tokyo Rainbow Bridge), city skyscrapers, and a blue sky with scattered clouds. On the ground level, numerous construction workers wearing yellow safety vests and hard hats are visible, along with police officers in dark uniforms directing traffic. A black police truck with similar markings is parked to the left.

Generate image
Loading more prompts

FAQ

Where do YouMind prompts come from?
YouMind curates high-signal AI prompt examples from creator communities and public creative workflows. The library focuses on prompts that are useful to inspect, reuse, and adapt.
How are image prompt categories organized?
Image prompts are grouped into use cases, styles, and subjects. Use cases describe the job to be done, styles describe the visual treatment, and subjects describe what the image is mainly about.
How are prompts assigned to categories?
YouMind uses AI to analyze each image prompt, its title, metadata, and generated result when available, then assigns the closest categories. Editors can refine categories as the taxonomy evolves.
What is YouMind?
YouMind is an AI workspace for turning research, ideas, and creative references into usable outputs. The prompt library is one public part of that workflow, built to help creators learn from strong examples faster.