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
Manga Page: Making an App with GPT Image 2.5
View full prompt & copy

Create a vertical, multi-panel black-and-white manga page in the style of GPT Image 2.5. The layout consists of five distinct panels arranged from top to bottom. Panel 1 (Top): A dynamic close-up of three characters. On the left, a boy with spiky light hair and a tank top raises his fist triumphantly with an energetic expression. To his right are two other characters: a girl with long light hair looking slightly confused or neutral, and a boy with dark messy hair wearing a sweater vest over a collared shirt, looking unimpressed. Japanese text bubbles read "GPT Image 2.5" and "アプリを作ったぞ!!" (I made an app!!). Panel 2: A split scene. On the left, the light-haired boy is laughing happily with eyes closed. In the center, three sample images are displayed like polaroids: a landscape photo, a portrait of a girl, and a fluffy white dog. On the right, the dark-haired boy points at them with a thoughtful expression. Text bubbles discuss cost efficiency: "これで1枚16円くらいで出力できるね。" (With this, we can output for about 16 yen per image.) and "日本円で換算されるとわかりやすいぜ!" (It's easier to understand when converted to Japanese Yen!). Panel 3: Another split scene. On the left, the dark-haired boy looks skeptical/sweating. On the right, the light-haired boy is smiling confidently with hands behind his head. Text bubbles say: "この漫画もアプリで出力したんだぜ!" (This manga was also outputted by the app!) and "要は他サービスなしで直接動かしてるからね…" (Basically, it's running directly without other services...). Panel 4: Similar composition to Panel 3 but reversed roles slightly. Left: Dark-haired boy explaining with a finger raised. Right: Light-haired boy cheering. Text bubbles: "アプリを作ったCodeXもすごいな!" (The CodeX that made the app is amazing too!) and "欲しい機能を簡易書きにしてお願いするだけでできたもんね。" (We just asked for the desired features in simple writing and it worked.). Panel 5 (Bottom): A wide shot. On the left, both boys are celebrating enthusiastically with fists up. On the right, the girl holds up a spiral notebook showing the previous manga panels she drew. She has a deadpan/annoyed expression with sweat drops. Her speech bubble contains ellipses "..." and text on the notebook says "この漫画、オチが無いね…" (This manga has no punchline...).

Generate image
GPT Image 2.5
Vintage Lolita Character Design Sheet
View full prompt & copy

Create a high-quality anime-style character design sheet titled "Classy Days" featuring a young girl in vintage Lolita fashion. The layout should include a large main portrait on the left, a full-body view on the top right, and three smaller detail views (back view, chibi expression, and accessory close-ups) arranged around the canvas. Subject Details: The character has short, layered silver-grey hair with soft pink highlights at the tips, styled with a large dark brown ribbon bow. She has large, expressive pink eyes and rosy cheeks. Her outfit consists of a black long-sleeved jacket with gold buttons over a white ruffled blouse, a brown plaid corset-style vest, and a matching grey-and-white plaid A-line skirt. She wears lace-trimmed socks and dark brown Mary Jane shoes, carrying a small structured brown handbag. Layout & Text Elements: 1. Top Left: Large serif title "Classy Days" with a sub-caption "Classic Sweet Daily with You" and a small bow icon. 2. Center-Top: Small text block reading "A little more myself today... Comfort looks good on you." 3. Right Column: A vertical strip of six square detail shots labeled: HAIR RIBBON, CAMEO EARRINGS, BLOUSE & BROOCH, JACKET & VEST, LACE SOCKS & SHOES, BAG. 4. Bottom Left: A color palette section with four swatches (cream, light grey, medium grey, dark brown) and text "Same me, different day. A gentle style for everyday happiness." 5. Bottom Center: Two smaller figures showing the back view of the dress and a happy chibi version holding the bag. Visual Style: Soft pastel background with delicate lace border patterns. The art style is clean, detailed, and cute, typical of Japanese character concept art.

Generate image
GPT Image 2.5
Dream of Red Chamber Poster
View full prompt & copy

Theme direction: Dream of the Red Chamber themed Oriental Zen minimalist cover poster Style branch: Feminine aesthetic mood type Main content: Lin Daiyu stands by flower path, lightly holding flower bag, looking down at fallen flowers Emotional motif: Spring sorrow, sensitivity, gentleness, sense of fate Scene & Imagery: Fallen flowers, flower path, light-colored railings, white stones, small flower bag, woman Composition & Space: 9:16 vertical composition, person located middle-lower left, flower path extends diagonally, top and right leave complete whitespace title area Color Control: Cream white as background base, light pink and rouge pink only for fallen flowers and bag, tender leaf green for few branches/leaves, person's clothing in pale moon-white or light pink-white; avoid whole-image pink filter effect Lighting & Texture: Bright soft light, petal edges clear, picture light and transparent, low grayscale Aspect Ratio: 9:16 Additional Requirements: Must have recognizability of "Burying Flowers", but picture remains minimalist, quiet, strong cover feel, appropriate text placed in whitespace areas

Generate image
GPT Image 2
Retro Film Portrait of Girl in Sailor Uniform
View full prompt & copy

A vertical medium-full shot of a young Asian woman sitting on a rocky pebble beach, looking directly at the camera with a calm, slightly melancholic expression. She has dark hair tied back in a low ponytail with loose bangs framing her face. She is wearing a traditional Japanese sailor school uniform (seifuku) consisting of a white short-sleeved blouse with a navy blue collar featuring white stripes and a red neckerchief, paired with a dark navy pleated skirt. On her feet, she wears white ankle socks and brown leather loafers. Her pose is relaxed, sitting with her legs extended forward and slightly bent, hands resting near her lap. The background features a bright blue sea with gentle waves crashing against the shore, scattered rocks, and a clear sky with faint clouds. The image has a strong retro film aesthetic, characterized by warm tones, visible grain, soft focus, and light leaks or color shifts along the edges typical of vintage instant film photography.

Generate image
GPT Image 2
Hand-Drawn 2D Cartoon Illustration
View full prompt & copy

Convert the entire uploaded photograph into a clean, colorful, hand-drawn 2D cartoon illustration. Preserve the original composition, camera angle, poses, facial expressions, recognizable identities, hairstyles, clothing, accessories, and all important background elements. ILLUSTRATION STYLE: •Clean black outlines with slightly varied, hand-drawn line weight. •Flat pastel colors with minimal cel shading. •Simplified characters with cute proportions, expressive faces, and natural poses. •Smooth, slightly imperfect lines for an authentic illustrated feel. •Simplify realistic textures into clean shapes while retaining recognizable details. •Recreate the original environment, including buildings, trees, fountains, pathways, and other objects, in the same cartoon style. •Use a soft pastel palette with light blue skies, muted greens, warm skin tones, and gentle pinks. •Add subtle artistic details while maintaining the original scene’s atmosphere. PRESERVE THE ORIGINAL: Keep the same number of people, their positions, body proportions, clothing colors, interactions, and relative sizes. Maintain the original background layout and perspective. Do not add, remove, or reposition important objects. OUTPUT REQUIREMENTS: A polished, full-frame 2D illustration with consistent outlines, flat colors, and a playful, storybook aesthetic. The entire image must be illustrated, with zero photorealistic elements. AVOID: 3D rendering, photorealism, excessive shading, watercolor textures, blurry lines, distorted faces, extra fingers or limbs, changed outfits, altered poses, missing background details, and unwanted text or watermarks. Aspect ratio: Match the uploaded photo exactly. Pro tip: Upload one photo at a time and use this same prompt to transform different photos into a consistent cartoon style.

Generate image
GPT Image 2.5
Vintage Monochrome Halftone Portrait Prompt
View full prompt & copy

A beautiful young woman with long, messy black hair blowing dramatically across her face, eyes closed, lips slightly parted, head tilted back, elegant elongated neck, wearing a simple black V-neck top. Chest-up portrait, slightly right of center. Vintage monochrome halftone print art, tiny black ink dots, stippled shading, high contrast, warm ivory textured paper background, deep black shadows, cream highlights, retro editorial photography, moody, dreamy, melancholic, intricate details, sharp facial features, authentic screen-print texture.

Generate image
GPT Image 2
GPT-Image-2 Wildlife Photography Prompt
View full prompt & copy

[Subject] and [Animal] dynamic interaction photography, person not fully in frame, entering only with partial hands, forearms, or body edges, establishing direct contact with [Animal] through [Interactive Prop]. The animal is captured in the instant of action: pouncing, reaching, holding, grabbing, lightly touching, or approaching the prop, forming a strong decisive moment. Composition emphasizes action connection, prominent subject, minimalist background, realistic environment, natural daylight, high-speed shutter freezing motion, with a sense of authentic snapshot, life feel, and narrative. Background uses large areas of simple natural environment color fields, highlighting the subject and interaction relationship.

Generate image
GPT Image 2.5
Papercraft Cube Model Template Generator
View full prompt & copy

Use the selected landmark as the only source of architectural reference. Create a realistic, printable papercraft cube model of Eiffel Tower, Paris, France, preserving its recognizable identity and unique architectural features: original silhouette, proportions, rooflines, towers, arches, windows, columns, decorative patterns, materials, and signature colors. Transform the landmark into a handmade paper craft 3D model using a low-poly geometric cube style, similar to a professional DIY papercraft kit. Show the complete unfolded cut-out template pieces laid flat on a clean white background, with clearly separated sections for the main structure, towers, roof, entrance, architectural extensions, decorative elements, and supporting base. The template must include: Main structure: A cube-shaped central building featuring the landmark’s authentic façade, recognizable architectural details, original colors, and realistic printed stone, brick, or surface textures. Roof and upper sections: Separate foldable pieces that accurately reproduce the landmark’s distinctive roof shape, domes, spires, ridges, or other defining features. Towers and extensions: Individual papercraft components for recognizable towers, minarets, bell towers, columns, arches, or side structures, depending on the landmark. Windows and entrances: Precisely positioned printed details that preserve the landmark’s original architectural identity. Decorative elements: Small foldable pieces for signature ornaments, railings, clock faces, carvings, or other historically recognizable features. Supporting base: A printable base with subtle ground textures and a small engraved-style label displaying the landmark’s name, city, and country. Printable template design: Every component must be unfolded and arranged flat, with visible solid cutting lines, dashed folding lines, numbered assembly sections, and properly sized glue tabs. All pieces should be logically connected or clearly separated, with realistic dimensions and enough white space to distinguish each component. The template must look like a genuine, usable papercraft kit rather than an assembled model photographed from above. Texture and realism: Print the landmark’s authentic architectural textures and colors directly onto the paper surfaces. Use realistic stonework, weathered brick, aged plaster, ceramic tiles, wood, or other materials appropriate to the actual building. Maintain the landmark’s recognizable proportions and historical character while adapting its structure into clean geometric paper components. Presentation: High-quality product photography, perfectly flat overhead view, pure white background, crisp paper edges, subtle natural shadows, fine printed textures, precise geometric folds, professional printable craft-sheet layout, and exceptional detail. Architectural accuracy is essential. Do not invent architectural features, alter the landmark’s silhouette, change its defining colors, or r

Generate image
GPT Image 2.5
Anime Office Scene: Laughing Girls vs Crying Mascot
View full prompt & copy

A high-resolution anime-style digital illustration depicting a humorous scene inside a modern tech office. In the foreground, two cute young women sit on a beige sofa in front of a coffee table with an open laptop (featuring a stylized flower logo). The girl on the left has long teal hair and wears a white hoodie with black accents; she is laughing while covering her mouth. The girl on the right has orange hair and wears a fluffy cream sweater, also laughing heartily. Above them are speech bubbles containing Chinese text: "我仿佛看到了摔炮爆炸" (I feel like I saw firecrackers explode) and sound effects "啪!" (Bang!). To their right, a small chibi character with messy blue hair sits huddled on the floor, crying under a small rain cloud icon, surrounded by scattered red firecrackers. A sign next to him reads "Argon". He wears a black jacket with a colorful 'G' logo. In the background, a large wall-mounted screen displays a presentation slide titled "Gemini 4 Argon 发布" (Launch) with charts and graphs. Through a glass window on the far left, another character with grey hair peeks in, saying "嘿嘿" (Hehe). The lighting is warm and cozy, contrasting with the cool blue light from the screen.

Generate image
GPT Image 2
Vintage Beach Portrait
View full prompt & copy

A vintage-style photograph of a young woman at the beach, shot on film with visible grain and light leaks. She is looking back over her shoulder with a bright, genuine smile. She wears a large woven straw sun hat with a dark brown trim and a white eyelet lace top. Her hair is styled in two low braids or pigtails. The lighting is warm and sunny, casting dappled shadows from the hat onto her face. In the background, there are blurred figures swimming in the ocean and a green hillside.

Generate image
GPT Image 2.5
Autumn Farm Seek-and-Find Illustration
View full prompt & copy

A highly detailed, vibrant, and busy 'Wimmelbilderbuch' (seek-and-find) style illustration of a bustling autumn farm scene. The image is packed with characters and objects in a warm, golden-hour lighting setting. **Top Left:** A large red barn with white trim. A wooden sign hangs on the front featuring a paw print logo and the text "Shoji" in cursive. Below the barn is a market stall with a red-and-white striped awning, displaying pies and jars. A woman in an apron stands behind the counter. A young girl in a red polka-dot dress reaches for a pie. **Center & Background:** A dirt path winds through the scene. In the distance, there are rolling hills with colorful fall foliage, a silo, and a windmill. To the right, a wooden archway reads "CORN MAZE" leading into tall corn stalks. A red tractor pulls a wagon full of children and hay bales down the center path. A wooden signpost points to "HAY RIDES". **Right Side:** A cheerful scarecrow wearing a plaid shirt and denim overalls stands amidst sunflowers. A brown horse's head peeks in from the far right edge. A black crow perches on a fence post nearby. **Foreground & Mid-ground Characters:** - **Left:** A black and white cow stands near a pile of pumpkins. A golden retriever dog sits next to it. A child dressed as a ghost holds a pumpkin bucket. Another child in a skeleton costume sits on a hay bale holding a pumpkin. - **Center:** A child in a green dinosaur costume walks carrying a pumpkin bucket. Two girls walk away from the viewer; one wears a purple witch outfit, the other a red ladybug costume. - **Bottom Left:** A child in a straw hat and plaid shirt hugs a large orange pumpkin inside a fenced area decorated with autumn leaves. - **Bottom Right:** A wooden cart filled with pumpkins and gourds sits on the grass. **Hidden Elements (Yellow Circles):** There are three distinct yellow circles highlighting specific cats hidden in the scene: 1. Top center: A tuxedo cat sitting on a hay bale near the tractor. 2. Middle left: An orange tabby cat sitting on a crate near the "Pumpkin Patch" sign. 3. Top right: A calico cat peeking out from the corn maze entrance. **Style:** Digital art, hyper-realistic textures but cartoonish proportions, bright saturated colors (oranges, yellows, reds), high detail.

Generate image
GPT Image 2.5
Sleepy Office Cat Sticker Prompt
View full prompt & copy

Die-cut sticker art of a sleepy orange tabby office cat calmly typing on a tiny laptop while surrounded by an exaggerated storm of flying sticky notes, spilling coffee cups, buzzing alarm clocks, and tangled charger cables, caption: "still on track", absurd cartoon style, bold saturated colors, thick black outlines, minimal shading, simplified shapes, playful proportions, expressive posture, humorous contrast between calm behavior and surrounding chaos, clean sticker composition, stark white background, no logo, no watermark, no brand names.

Generate image
GPT Image 2.5
Pink-haired fairy holding phone
View full prompt & copy

A wide-format digital illustration of a beautiful anime-style fairy with long pink hair and black-rimmed glasses, holding a smartphone towards the viewer. The phone screen displays an anonymous confession interface: 'send me anonymous confessions! on...' followed by the message 'you're the most beautiful blue butterfly' and a reply 'The mighty blue monarch~!', with the logo 'UNSAID' at the bottom. The character has large, translucent wings with intricate blue and purple patterns resembling stained glass or butterfly wings. She wears a dark, frilly outfit with ribbons and a choker. The background is a magical, ethereal scene filled with glowing blue butterflies, hanging crystal ornaments, and faint mathematical formulas floating in the air.

Generate image
GPT Image 2.5
Lone Figure Before Ruined Megastructure
View full prompt & copy

A cinematic, wide-angle shot of a lone figure standing with their back to the viewer in the center foreground. The character has short white hair and wears a long, flowing light-grey coat or robe, carrying a dark satchel over one shoulder. They hold a staff topped with a glowing yellow orb. The setting is a colossal, ruined megastructure that blends brutalist industrial architecture with organic overgrowth; massive concrete pillars are covered in vines and moss. Several powerful waterfalls cascade down from the upper levels of this structure into a body of water below. In the background, a bright blue sky with scattered white clouds is visible through the gaps in the ruins, along with distant silhouettes of other skyscrapers. The lighting is natural and bright, suggesting midday sun, creating a contrast between the decayed civilization and the vibrant nature reclaiming it.

Generate image
GPT Image 2.5
Candid Flash Photography Portrait Prompt
View full prompt & copy

Create A candid, flash-photography portrait of a young woman with voluminous, wavy brunette hair tossed slightly in motion. She is laughing candidly with her hand resting gently near her mouth, wearing a sleek black mini dress with a corset-style fitted bodice. She is leaning against a dark matte wall in a moody, dimly lit hallway. Captured with direct camera flash, high contrast, subtle motion blur, and an aesthetic film grain texture.

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.