YouMind
Sign in

Infographic / Edu Visual

Explore free Infographic / Edu Visual image prompts from YouMind's AI prompt library, grouped under use cases. Every prompt is curated from real creative workflows and ready to copy, adapt, and reuse.

Prompt to ImageImage to Prompt
GPT Image 2.5
AI Beauty Consultant & Hairstyle Advice Prompt
View full prompt & copy

Act like an aesthetic/beauty consultant and analyze my appearance from the attached photo. Identify the highest-impact changes that would make me look more refined and harmonious, including hairstyle/cut/color, eyebrows, eye makeup, skin/makeup placement, lips, and overall facial balance. Provide specific advice based on my actual features rather than generic suggestions. Then, generate a realistic "after" version of this exact photo, showcasing the recommended refreshed effect. Keep me recognizable as the same person and preserve my facial anatomy unless you specifically recommend subtle structural adjustments. Maintain the same pose, camera angle, expression, lighting, clothing, and background as much as possible. Make these changes sophisticated and realistic, not exaggerated beauty filters. Prioritize high-impact, low-risk styling adjustments. Do not automatically slim my face, shrink my nose, enlarge my lips, enlarge my eyes, or make my skin unrealistically perfect. For hair, choose a hairstyle, color, parting, volume, and framing that best complements my personal proportions. For makeup, optimize brow shape, eyeliner/lashes, blush/contour placement, lip definition, and skin tone while maintaining naturalness. Generate a before-and-after comparison photo with annotations explaining each change, similar to a professional beauty consultation.

Generate image
GPT Image 2
Manga Infographic: AI Prompt Engineering
View full prompt & copy

A vertical, highly detailed manga-style infographic page with a parchment-like background. The layout is divided into three main sections: a top illustration area, a middle diagrammatic breakdown, and a bottom text-heavy conclusion. Top Section: - A large, ethereal illustration of a woman with long white hair and fox ears (a kitsune) standing on a mountain peak at sunset. She wears flowing white robes. - Below her, an elderly man with long black hair tied back, wearing dark blue traditional Chinese robes, sits cross-legged holding a calligraphy brush, looking up thoughtfully. - To his right, a younger man in grey robes kneels, sketching the kitsune onto paper. - Surrounding this scene are blocks of Japanese text explaining the concept of 'Prompt' (プロンプト). - On the left side, there are four small square character portraits labeled with descriptions like 'Beautiful Woman', 'Dancer', etc., showing variations of female characters. - Large vertical Japanese text on the right reads 'Introduction to Prompts'. Middle Section: - A horizontal flow diagram titled 'Verbalizing features to compose a picture'. - It shows a sequence of six small square images connected by plus signs (+), leading to an equals sign (=) and a final result image. - The sequence includes: 1. Long silver hair, 2. Blue eyes, 3. White clothes, 4. Mountain sunset, 5. Looking back pose, 6. Soft backlighting. - The final result is the complete image of the kitsune from the top section. Bottom Section: - A large, bold Japanese headline in red and black ink style: "Listing hundreds of words loses one stroke" (百語を並べて一画を失う). - Surrounding the headline are torn pieces of paper with handwritten notes listing negative effects of over-prompting, such as '8K resolution', 'ultra-high quality', 'complex composition', 'unnatural lighting', 'film-like lighting', 'large scale', 'highest quality'. - At the very bottom, a concluding sentence in a box states that words are tools, but too many obscure the essence of the single stroke.

Generate image
GPT Image 2.5
Stray Cat Rescue Before & After
View full prompt & copy

Create a vertical split-screen comparison image showing the transformation of a stray cat. Top half: A scruffy, thin tabby and white cat with matted fur sits on rough concrete outdoors near a stone wall, looking wary and unkempt. Bottom half: The same cat, now healthy, plump, and fluffy with clean fur, rests comfortably on a soft beige fleece blanket indoors with a blurred background of houseplants and wooden furniture. Add a dark rectangular label in the top-left corner of each section reading 'Before' and 'After' respectively in white serif font.

Generate image
GPT Image 2.5
Advanced Female Lead Expression Sheet
View full prompt & copy

Create a photorealistic character expression sheet featuring a young East Asian woman with black hair tied back in a low bun, wearing a simple beige linen shirt. The image must be arranged in a strict grid of 4 rows and 5 columns, containing exactly 20 individual portrait panels. Each panel should show the same character from the chest up against a blurred neutral background, maintaining consistent lighting and framing across all tiles. Below each portrait, include a small caption label consisting of a number (1-20) followed by a specific emotion or action in Chinese characters. The expressions for the 20 panels are as follows: Row 1: 1 Calm Observation (neutral face), 2 Focused Listening (attentive eyes), 3 Slight Confusion (furrowed brow), 4 Noticing Anomaly (sharp gaze to side), 5 Suspicion (skeptical look). Row 2: 6 Vague Dissatisfaction (slight frown), 7 Suppressing Emotion (tense jaw), 8 Sneaky Observation (eyes looking sideways), 9 Reaction to Hearing Someone Speak (looking off-camera), 10 Suddenly Realizing Something (wide-eyed realization). Row 3: 11 Relief (soft exhale expression), 12 Gentle Smile (warm closed-mouth smile), 13 Truly Happy (broad open smile), 14 Can't Help Laughing (laughing expression), 15 Shy (blushing, looking down). Row 4: 16 Surprised but Restrained (mouth slightly open, controlled), 17 Worried (concerned brows), 18 Disappointed (sad, downcast eyes), 19 Thinking (hand near chin or pensive look), 20 Knowing Smile (subtle smirk). Ensure the style is high-quality cinematic photography suitable for an acting reference guide.

Generate image
GPT Image 2.5
Fictional country map generation prompt
View full prompt & copy

Generate a map of a fictional country. Based on the national settings below, generate a map that fits the setting and enclose it in a border. Do not include any explanatory text; list only place names. With regard to place names, describe only those that are below; do not describe the names of places not mentioned in the text. Depict the terrain in a way that makes it easily recognizable. Map colors should be chosen to match the terrain, and areas should not be distinguished by color. [Country Name]:[Summary and geographical description of the country]

Generate image
GPT Image 2.5
Fantasy World Building Sheet Generator
View full prompt & copy

A high-quality fantasy world-building sheet. Descriptions of the town and related Terms. The town description goes in the top-left corner, general descriptions of Terms go in the right half, and an illustration goes in the bottom-left corner. The borders and background color should match the atmosphere of the Reference Image. All text must be written in Japanese, and only the specified text should be included. Town Description: Name is "[Town Name]". General Description is "[Town Summary]". Terms: Draw a small, stylized illustration next to each term to represent it. "[Term 1]";"[Term 1 Description]" "[Term 2]";"[Term 2 Description]" ...(add more terms as needed) Illustration: Use the reference images to create illustrations that fit the world-building. The atmosphere should also match the world-building. Blur the Outlines of an Illustration.

Generate image
GPT Image 2
Dark Fantasy Hell Hound Character Sheet
View full prompt & copy

Goal: Create a dark fantasy character design sheet for a 'Hell Hound' guardian creature, featuring a small cat companion named Stinky. Canvas: Vertical infographic layout with a parchment-style background and gothic typography. Layout: Top section features the main illustration; middle sections contain detail panels and skeletal studies; bottom section displays behavioral poses and a poetic oath. Subject details: The Hell Hound is a massive, terrifying beast made of living shadow and charcoal-black fur. It has a skeletal, ancient skull head with glowing white eyes, long spindly limbs, and sharp claws. Despite its monstrous appearance, it is crouching protectively around a tiny, cute grey cat wearing a pink hoodie (Stinky). The atmosphere is moody, magical, and protective. Text content: Include specific labels and lore text: - Title: "HELL HOUND" in large gothic font. - Subtitle: "FOREST GUARDIAN & PROTECTOR". - Stats block: Type: Noble Protector, Habitat: Kolby's World, Skin: Charcoal Black - Guardian's Oath, Coat: Shimmering Void, Behavior: Protective • Loyal • Gentle, Primary Mission: Protect the innocent — especially Stinky. - Quote: "You will never harm what I swear to protect." - Detail Panels: "COLOR VARIANTS" (Charcoal Black, Ash Gray, Corpse Gray), "SKIN DETAIL", "EYE DETAIL", "HEAD DETAIL", "TEETH", "CLAW / HAND". - Skeletal Study: Front, Left, Back, Right views of the hound's skeleton. - Movement & Behavior: Resting/Watching, Protecting, Sheltering, Gentle. - Common Hiding Places: Forests, Abandoned Places. - Odor: Smells like rain, moss, and ancient oaths. - Bottom Section: "THE GUARDIAN'S OATH" poem starting with "I do not hunt her..." ending with "I am her forever." Footer text: "STINKY IS PROTECTED. ALWAYS. NO HARM SHALL TOUCH HER. EVER." Visual style: High-fantasy concept art, dark academia aesthetic, detailed textures, dramatic lighting with golden sparks surrounding the hound.

Generate image
GPT Image 2
Anime Character Design Sheet: Traditional Hanfu Couple
View full prompt & copy

A high-resolution character design sheet featuring two anime-style characters dressed in traditional Chinese Hanfu, set against a plain white background. The layout includes full-body front and back views for both characters, along with detailed close-ups of their heads, accessories, and clothing textures. Left Character (Male): - Appearance: Young man with short black hair wearing a tall, structured black official's hat (Guan) with ribbons hanging down. He has blue eyes and a gentle expression. - Outfit: A dark navy/black cross-collar robe (Yi) with wide sleeves, trimmed with a patterned reddish-brown border. Underneath is a white collar. He wears a long skirt-like lower garment (Shang). A belt with a gold buckle secures the waist, from which hangs a jade pendant ornament (Pei) with red tassels. He holds a sword in a black scabbard with red accents. - Views: Front full-body view holding the sword; back full-body view showing the drape of the robe; headshot close-up; isolated detail shots of the hat, belt buckle, jade pendant, and sword. Right Character (Female): - Appearance: Young woman with light brown/auburn hair styled in an elaborate updo with loops and side bangs framing her face. She has blue eyes and a calm expression. Her hair is adorned with a hairpin featuring a jade disc and red tassel. - Outfit: A layered ensemble consisting of a peach/light orange outer robe with a subtle floral pattern and deep red trim at the collar and cuffs. Underneath is a cream-colored pleated skirt (Qun) with a reddish-brown patterned panel visible at the hem. A pink sash is tied around the waist, also featuring a hanging jade ornament. - Views: Front full-body view; back full-body view showing the long hair and robe details; headshot close-up; isolated detail shots of the hairpin, collar texture, and waist sash knot.

Generate image
GPT Image 2.5
SF Gear Beginner's Guide Infographic
View full prompt & copy

Goal: Create a Japanese educational infographic slide explaining OpenClaw architecture. Canvas: Vertical 4:5 slide with a clean blue-and-white corporate tech style. Layout: Top headline area, central flow diagram, three capability cards, and a bottom summary section. Text content: Preserve key Japanese labels such as 「ゲートウェイ」 and 「交通整理役」 where they appear in the design. Constraints: Use exactly the visible section count, keep icons simple, avoid extra text, no watermark.

Generate image
GPT Image 2.5
AI Model Leaderboard Podium Cartoon
View full prompt & copy

Goal: Create a humorous, two-part cartoon illustration depicting an AI model leaderboard as a sports podium ceremony. Canvas: Square aspect ratio with a solid teal background featuring a subtle silhouette of a crowd at the top edge. The style is flat vector art with thick black outlines and vibrant colors. Layout & Sections: 1. Top Row (Close-ups): Three distinct panels showing the characters from positions 8, 9, and 10 celebrating wildly. - Left Panel: A bald man in a blue and white tracksuit with a 'G' logo and 'Gemini' text on his chest. He wears a gold medal and points both index fingers upward while shouting joyfully. - Center Panel: A bearded man with curly brown hair in a green and white tracksuit with an 'M' logo and 'Muse' text. He wears a gold medal and is spraying champagne from a green bottle into his mouth. - Right Panel: A man with wavy brown hair in an orange and white tracksuit with an 'M' logo and 'Mistral' text. He wears a gold medal, holds a rolled-up diploma, and flexes his bicep confidently. 2. Bottom Row (Wide Shot): A full view of a beige winner's podium with 10 steps, labeled 1 through 10. Ten male figures stand on the steps, wearing different colored outfits representing AI companies. - Step 1 (Highest): Label 'GPT-6 Astra'. Figure wears a white hoodie with a black OpenAI swirl logo, green pants, and a gold medal. Standing calmly. - Step 2: Label 'Claude Fable 5.1'. Figure wears a pink/red hoodie with a square 'Ai' logo, red pants, and a silver medal. Looking to the side. - Step 3: Label 'GPT 5.6'. Figure wears a white hoodie with a black OpenAI swirl logo, yellow pants, and a bronze medal. - Step 4: Label 'Kimi 3'. Figure wears a dark navy/black hoodie with a large white 'K', dark pants, and a gold medal. - Step 5: Label 'Grok 4.6'. Figure wears a light green hoodie with a black 'x1' logo, green pants, and a gold medal. - Step 6: Label 'GLM 5.3'. Figure wears a purple hoodie with a white geometric flower logo, purple pants, and a gold medal. - Step 7: Label 'Qwen 3.8'. Figure wears an orange hoodie with a white circular arrow logo, orange pants, and a gold medal. - Step 8: Label 'Gemini 3.6 Flash'. This is the same character from the top-left panel (blue/white Gemini suit), now seen full-body, pointing up and cheering. - Step 9: Label 'Muse'. This is the same character from the top-center panel (green Muse suit), now seen full-body, spraying champagne. - Step 10: Label 'Mistral'. This is the same character from the top-right panel (orange Mistral suit), now seen full-body, holding a scroll and cheering. Text Content: Ensure all labels under the podium steps are legible and match the specific names provided above exactly.

Generate image
GPT Image 2.5
Autumn Bookstore Event Presentation Slide
View full prompt & copy

Create a high-resolution, professional presentation slide (16:9 aspect ratio) with an 'Autumnal Literary' aesthetic. The background is a clean off-white paper texture. **Visual Elements:** 1. **Main Typography:** Large, expressive Chinese calligraphy in the center-left reading "把秋天装进书店" (Put Autumn into the Bookstore). The font style should be rough brush strokes in a burnt orange/terracotta color. 2. **Geometric Shapes:** A large diagonal block of solid burnt orange cutting across the right side of the canvas from top-right to bottom-center. 3. **Photography:** In the upper right corner, overlay a realistic photo of golden ginkgo leaves on a branch against a white wall, casting soft shadows. This image should blend naturally with the orange geometric shape. 4. **Stamp Element:** A red circular stamp graphic in the top right corner containing the text "五周年" (5th Anniversary). 5. **Secondary Text:** Below the main calligraphy, include smaller black sans-serif text: "山海秋集" and "独立书店五周年企划路演". Further down, add small grey text: "五周年活动命题 / 秋日阅读市集". 6. **Decorative Details:** Add scattered single autumn leaves floating around the text. Include vertical English text on the far left edge: "BOOKS PEOPLE A KINDER AUTUMN". Include vertical Chinese text on the far right edge: "书 · 人 · 秋天 · 更好的日常". Bottom right corner has page number "01 / 09".

Generate image
GPT Image 2.5
LAV-25 with Mounted M2 Machine Gun
View full prompt & copy

Using the provided reference image of the M2 Browning machine gun, generate a photorealistic multi-view technical illustration of a LAV-25 armored vehicle. The key transformation is to mount the specific M2 Browning machine gun from the reference onto the turret of the vehicle. Layout: Arrange the output in a 2x2 grid with four distinct views labeled 'RIGHT', 'LEFT', 'TOP', and 'FRONT 3/4'. Subject Details: 1. Vehicle: A 4x4 wheeled armored car (LAV-25) painted in a woodland camouflage pattern (greens, browns, and blacks). 2. Turret: An open-topped turret equipped with gun shields on either side. 3. Weapon: Mount the exact M2 Browning heavy machine gun shown in the reference image onto the turret ring, complete with its ammunition box and perforated barrel shroud. 4. Accessories: Include a shovel mounted on the rear, side mirrors, headlights, and an antenna on the front left fender. Style: Clean studio lighting on a white background, high-resolution texture for the metal and rubber tires.

Generate image
GPT Image 2.5
Mechanical Keyboard Encyclopedia Poster Prompt
View full prompt & copy

A 3:4 vertical mechanical keyboard encyclopedia information poster, blending Bauhaus functionalism, industrial design archives, and modern digital lab visuals. The top displays a compact mechanical keyboard in a diagonal composition, alongside exploded views of keycaps, switches, plate, PCB, and stabilizers, with studio hard-soft lighting creating clear micro-shadows; the title "Mechanical Keyboard" is arranged along the left grid, with the English subtitle "Mechanical Keyboard", accompanied by circular category tags "Input Device / Mechanical Switch", structural explosion diagrams, and keyboard size scales. The middle section uses restrained accent colors of red, yellow, and blue with modular geometric cards, fully presenting nine types of information: common layouts (60%, 65%, 75%, 80%, 96%, 100%); tactile curves for linear, tactile, and clicky switches; pre-travel and total travel; actuation force; common keycap materials and profiles; connection methods (wired, 2.4GHz, Bluetooth); differences between hot-swap and soldered PCBs; internal structures like plates, sandwich, and gasket mounts; latency, polling rate, N-key rollover, and usage scenarios. Each module retains only one main graphic to avoid visual clutter. Uses a 12-column grid, 48pt margins, 8pt baseline, and uniform 2pt linear icons. Background is near-white light gray, text is dark gray, data uses monospaced fonts. The bottom includes glossary and parameter source bars, stating "differences exist across brands and models", prohibiting fabrication of specific model performance or non-existent technical standards.

Generate image
GPT Image 2.5
Snow Leopard Encyclopedia Card Prompt
View full prompt & copy

A 2:3 vertical minimalist art style snow leopard encyclopedia info card, museum exhibit level visual quality, adopting Swiss International Style and premium natural history atlas language. Top ~30%: Adult snow leopard cutout studio-style full-body side close-up on pure white background, realistically retaining grey-white fur, black ring patterns, thick long tail, wide paws and facial details, not anthropomorphic; paired with super-large thin-line title "Snow Leopard", small italic "Panthera uncia", capsule tags "Mammalia/Felidae/Panthera", Asia distribution mini-map and altitude activity range axis. Middle ~60%: Based on 12-column and 8pt grid, clearly arranging nine major modules - basic parameters of body length, weight, tail length and lifespan; body structure and high-altitude adaptation features; food composition and typical prey; diurnal/nocturnal activity patterns; breeding cycle and cub growth; habitat types and altitude distribution; comparison with other large felids; population threat factors; conservation status, actions and ecological value. Charts use outline proportion diagrams, footprint size charts, altitude distribution maps, prey network graphs and concise timelines. Bottom ~10% marks conservation status, data year, source and update time. Main colors glacier grey, snow white, rock brown and graphite black, with minor cold blue accents; Source Han Sans Light, DIN and Roboto Mono, 2pt linear icons, 0.5pt light dividers, large whitespace. All biological data must be accurate and verifiable, no fabricated population numbers, no exaggerated descriptions, Chinese clearly readable, no garbled text.

Generate image
GPT Image 2.5
Cute Pastel Character Sheet Infographic
View full prompt & copy

Goal: Create a cute, pastel-colored Japanese character sheet infographic featuring three distinct characters stacked vertically. Layout & Content: 1. Top Section (Pink Theme): Features 'Azusa-chan', a girl with black hair in a side ponytail, wearing a white t-shirt and pink skirt. Include a large portrait on the left, three smaller turnaround poses (front, side, back) in the center, and a row of three facial expressions (smiling, surprised, winking) on the right. Below the expressions, show her belongings: a blue flower hair tie, pink sneakers, and a heart-shaped bag. 2. Middle Section (Blue Theme): Features 'Koma-chan', a girl with short brown hair and an ahoge, wearing a navy t-shirt with a chick graphic that says 'Perfect' and denim shorts. Layout mirrors the top section: large portrait, three turnarounds, three expressions (laughing, excited, angry), and belongings: a plush chick, a star wand, and a backpack. 3. Bottom Section (Yellow Theme): Features 'Tori', a round yellow chick mascot. Layout includes a large illustration, three small variations, three expressions (happy, dizzy, shocked), and belongings: a nest, a feather, and a ribbon. Visual Style: Use a soft, hand-drawn aesthetic with rounded fonts, pastel backgrounds (pink, light blue, yellow), and decorative elements like hearts, stars, and sparkles scattered throughout.

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.