Comic / Graphic Novel

Explore free Comic / Graphic Novel image prompts from YouMind's AI prompt library, grouped under styles. Every prompt is curated from real creative workflows and ready to copy, adapt, and reuse.

Prompt to ImageImage to Prompt
GPT Image 2
Chibi Beach Ponytail Comic
View full prompt & copy

Goal: Create a square 2x2 manga-style comic announcement about a cute chibi ponytail girl at the beach, titled 「陰みろちゃん」, with a small chibi head icon near the title and a faint CapCut watermark in the upper left. Canvas: Square 1:1 image, clean white background, thick black comic panel borders, playful hand-drawn Japanese manga aesthetic with soft watercolor-like beach scenery. Layout: Top header spans the full width with large handwritten black title text and one small chibi head portrait on the right. Below it, place exactly 4 numbered comic panels in a 2x2 grid, each with a white circular number badge at the bottom right: ①, ②, ③, ④. Panel 1: Wide beach view with turquoise ocean and foamy shoreline on the left, pale sand across the foreground, rocks and greenery in the distance. A chibi young woman with black ponytail hair kneels on the sand wearing a yellow cropped T-shirt and blue denim shorts, holding a stick and writing a celebratory message in the sand. The sand text reads 4周年 祝って. Cute simplified face with closed sideways eyes and small puckered mouth. Panel 2: A dramatic close-up of a huge blue wave crashing forward with white foam and splash details, filling the entire panel. Overlay large bold handwritten Japanese sound effect text どどーん in black with white outline, slanted across the wave. Panel 3: Close-up reaction shot of the same chibi girl from the chest up, shocked and distressed, with messy black bangs covering part of her face, vertical blue-purple manga stress lines in the background, sweat drop on her cheek, tiny closed eyes, and wide open red mouth. She still wears the yellow T-shirt. Panel 4: Return to beach scene from behind the girl. She is crouching on the sand, facing away toward the ocean, with a large sweat drop by her head. The previous message is ruined or changed so the visible sand text reads 呪って. Ocean waves roll along the left side; sand and pebbles fill the foreground. Subject details: The character is a cute chibi/anime girl named Kagemiro-chan, with black hair in a high ponytail, pale skin, simple dot/closed-line facial features, short rounded body proportions, yellow top, blue denim shorts, barefoot or minimally detailed feet. Visual style: Bright, clean, humorous Japanese webcomic look; thick black outlines; expressive manga symbols; soft beach colors; lively wave illustration; handwritten calligraphy-like Japanese lettering. Keep the comic readable and cute rather than realistic. Constraints: Use exactly 4 panels and exactly 4 panel number badges. Include exactly 1 small chibi head icon in the header. Do not add extra captions, speech bubbles, or additional characters. Preserve the specified Japanese text exactly where provided.

Generate image
GPT Image 2
Educational Manga Generation Prompt
View full prompt & copy

Common Character Settings + Drawing Rules: Strictly adhere to the character designs of the two protagonists. Teacher (Midori-sensei): Black straight hair in a ponytail with a single thin green highlight. Wears glasses. Wearing a large, ill-fitting white lab coat over baggy gym clothes. Expressive, energetic, and mischievous but proud of being a teacher. Uses large gestures and speaks passionately with hand movements. Student (Pink-chan): Pale pink hair, slouched posture, with a single cowlick on top of her head. Always looks sleepy with half-closed eyes. Has a laid-back vibe and slow movements. On her desk are a drawing tablet (often used as a pillow), a half-finished strawberry milk, and a rabbit plushie pen case. Style/Finish Specs: Generate in full color (no monochrome or grayscale). Saturation should be bright like a comedy manga; ensure Midori-sensei's green highlight and Pink-chan's pale pink hair are clearly colored. Do not display any panel numbers (1, 2, 3, etc.) inside the panels. Labels like 'Panel 1' below are for instruction only. Adhere strictly to the Japanese commercial manga reading order (right-to-left, top-to-bottom starting from top-right). Speech bubble placement should not obstruct this flow. Thick black panel borders. Large, readable Japanese text. Setting is a manga classroom with a whiteboard, desks, and drawing tablets. [Page 1] Vertical (3:4), 6 panels arranged R-to-L, Top-to-Bottom: Panel 1: Title panel. Large handwritten-style text: "Master the Page-Turn, Master the Manga". Midori-sensei holds a book and exaggeratedly demonstrates turning a page. Pink-chan is leaning on her hand, half-asleep. Panel 2: Pink-chan asks lazily: 'Page-turn...? Does just turning a page really have a name...?' with a '?' above her head. Panel 3: Midori-sensei's glasses glint. 'Yes! From the last panel on the left page to the first on the right. This bridge is called the "page-turn," and manga artists use every bit of their skill on it!' Background has focus lines. Panel 4: Diagram panel. A schematic on a whiteboard showing a book spread: labels for 'Hook' on the bottom-left, 'Turn = time eyes leave the paper' in the middle, and 'Rewarding image/line' on the top-right. Midori-sensei points to it with a marker. Panel 5: Metaphor panel. Midori-sensei speaks with her hand on her heart. 'Panel pacing is like human speech. There are fast parts and slow parts. Within that, the page-turn is—a breath.' Musical rest motifs in background. Panel 6: Pink-chan mutters: 'A breath... my whole life is like one long breath...' Midori-sensei's small bubble: 'Yours is a deep dive! (You're sleeping!)'. [Page 2] Vertical (3:4), 7 panels: Panel 1: Midori-sensei continues. 'Reader focus breaks during the turn. So the last panel on the left must be a "hook" or a natural scene change!' Small example illustration on the side. Panel 2: 'Then the first panel on the right. Because of the gap, reader expectations are up. You need a great line or image. It's the "build-up" before a big scene!' Example showing a double-page spread feel. Panel 3: Midori-sensei starts a demo, placing a book in front of Pink-chan excitedly. 'Try it! Look at this last panel... makes you want to turn it, right?' Panel 4: Pink-chan leans in, eyes slightly wider, reaching for the page. 'Oh... true... I'm curious... about what's next...' A tiny highlight in her eye. Panel 5: Peak of passion. Midori-sensei's coat flutters. 'Exactly!! When that curiosity stacks, you get a work where the reader can't stop turning pages! It's a gift to the reader!!' Warm heat-tone background. Panel 6: Pink-chan is face-down on the open book, fast asleep using it as a pillow. 'Zzz...' The page is slightly folded under her cheek. Panel 7: Midori-sensei collapses. 'Every day!! And using the book as a pillow!!' Small bubble: '...I guess the page-turning stopped.'

Generate image
GPT Image 2
Mbappé Sprinting Soccer Action
View full prompt & copy

Create a high-energy editorial sports action image of Kylian Mbappé sprinting and dribbling a soccer ball on a vivid green grass pitch. The athlete is captured mid-stride in a dynamic low-angle three-quarter view, leaning sharply forward with intense focused expression, one arm swept back and the other bent forward, wearing the blue France national team kit with visible white rooster crest, number 10, matching blue shorts, bright red socks, red football boots, and a white wrist tape. Place a classic black-and-white soccer ball near the foreground under his leading foot, with comic-book style red-and-white impact bursts around the ball and small black turf debris flying through the air. Background: a flat pastel pink stadium-advertising wall with huge bold italic blue uppercase text reading TOAKL across the top, partly obscured by the player. Use crisp photorealistic detail on the athlete and kit, dramatic frozen-motion sports photography lighting, shallow depth of field, saturated colors, vertical 2:3 composition, no extra players, no watermark, no additional readable text.

Generate image
GPT Image 2
Seven-Panel Cyberpunk Manga Alley
View full prompt & copy

Goal: Create a monochrome seinen manga page with exactly 7 numbered panels, gritty cyberpunk back-alley atmosphere, sharp ink linework, heavy screentone, cinematic lighting, and readable vertical Japanese dialogue. Canvas: Tall manga page, black-and-white, about 3:4 aspect ratio, thin black outer border, thick panel gutters, high-detail urban background throughout. Number the panels with small boxed numerals: 3, 4, 5, 6, 7 visible on later panels, matching printed manga page styling. Setting: A dense, wet, claustrophobic Kowloon-style alley at night, packed with pipes, wires, ducts, grime, puddles, stacked signs, vents, trash, barrels, and old shop signboards. Include vertical signs reading 九龍城, 龍城酒家, and 蛇王. The mood is noir, humid, and oppressive. Layout and panel count: Use exactly 7 discrete manga panels. 1. Top-left panel: a tilted, motion-blurred alley view as if the scene is spinning or the viewer is collapsing; intense radial blur. Add a small white vertical speech bubble saying「あれ……?」and large hand-drawn sound effect text「ぐらぁっ」. 2. Top-right panel: a straight-on detailed alley corridor with no character visible, deep perspective into darkness, signs and pipes on both sides. Large white speech bubble at upper right with ああ、もうおしまいだ……。Fableは7/19でサブスクから外れた……従量課金しかないのか……つうかもう週次制限使い切っちまった……. 3. Middle-wide panel: a young man kneels on both hands and knees on the dirty alley ground, exhausted or dizzy, seen from a high diagonal angle. Add small sound effect「よろ…」near him. White vertical speech bubble at right with やべ……Fableのサブスク明日までだからまた帰って開発しなきゃ……. 4. Middle-left narrow panel: mostly white space with one large black oval speech bubble containing white vertical text おやぁ……お兄さん、お困りのようですね. 5. Right-middle wide panel: an elegant androgynous young man in a black Chinese-style changshan/qipao jacket leans in, smiling slyly, holding a long smoking pipe near his lips; smoke curls upward. He has long glossy black hair tied back, pale skin, narrow eyes, and a single round monocle or small round glasses lens with a chain. The kneeling man is seen from behind in the foreground. White speech bubble at upper right says「それ、私にお任せいただけやしませんかね……?」and a smaller bubble near the pipe smoker says「あぁんた……どこのモデルだ……?」. 6. Lower-left close-up panel: extreme close-up of the pipe smoker’s face, half-lidded eyes, confident smile, long bangs, round lens and chain visible; dramatic black hair highlights. Add vertical sound text「にぃ…っ」. 7. Bottom full-width panel: dramatic bust portrait of the pipe smoker against the intricate alley background, holding the smoking pipe gracefully beside his face, smoke curling across the panel in multiple wisps. Large white vertical speech bubble on the left with 私、鳴呼 申し遅れました。最近流行りのちゃっと……しかも、オープンモデルと申します。ベンチマークは……ラブらせる、あなたが欲しいモデルに迫る、とだけ。申し上げておきましょうか。. Add a rectangular caption box at lower right containing「???」. Character details: The pipe smoker is a tall, beautiful, slightly sinister East Asian young adult man with refined features, long black hair, half-lidded eyes, a smug smile, black traditional Chinese frog-button jacket, and a delicate smoking pipe. The kneeling man is a modern young adult male in casual clothes, short dark hair, overwhelmed and slumped. Visual style: Professional black-and-white manga, highly detailed backgrounds, realistic anatomy, glossy hair rendering, deep blacks, strong rim lighting, screentone gradients, hand-lettered Japanese sound effects, crisp readable vertical speech bubbles. Panel 2 must be still and detailed, while panel 1 must be visibly blurred and dizzying. Constraints: Keep exactly 7 panels and all specified speech bubbles. Do not add color. Do not use chibi style. Maintain legible Japanese text and clean manga gutters.

Generate image
GPT Image 2
Noir Manga Alley Encounter
View full prompt & copy

Goal: Create a monochrome seinen manga page in a dark, rain-soaked cyberpunk back alley, with dramatic noir lighting, dense crosshatching, high-detail backgrounds, and Japanese vertical dialogue. The tone is ominous, elegant, and slightly comedic, centered on an unexpected meeting between a frightened ordinary man and a refined pipe-smoking man. Canvas: Tall vertical manga page, approximately 2:3 aspect ratio, black-and-white only, crisp ink linework, heavy blacks, white gutters, no color. Use a printed manga page aesthetic with cinematic perspective, wet reflective pavement, steam, grime, pipes, cables, and many vertical shop signs. Layout: Use exactly 7 panels separated by clean white gutters. Panel 1 is the top-left establishing panel, tilted downward into a narrow alley with dense signs and a small vertical speech bubble. Panel 2 is the top-right establishing panel, a long alley view with a large white oval speech bubble. Panel 3 is a full-width overhead panel showing a lone man crouched or kneeling in the alley, surrounded by tall walls and pipes, with one vertical sound effect. Panel 4 is a mostly blank white horizontal panel containing only a centered black oval speech bubble. Panel 5 is a large confrontation panel showing the back of a nervous short-haired man in a hoodie facing an elegant young man seated in the alley, smoking a pipe, with two speech bubbles. Panel 6 is a very thin horizontal close-up strip of the elegant man's eyes and glasses, with one stylized sound effect on the left. Panel 7 is the final large bottom panel, a dramatic three-quarter portrait of the elegant man seated confidently with pipe smoke curling around him, plus one large speech bubble on the left and one rectangular nameplate at lower right. Characters: The ordinary man is a nervous short-haired Japanese man in a light hoodie, seen from behind or above, sweating and crouched in fear. The mysterious man is a tall handsome young man with messy black hair, pale skin, narrow sharp eyes, a monocle or round glasses over one eye, wearing a black Chinese-style changshan jacket with frog closures, holding a smoking pipe. Make the mysterious man charismatic, smug, and composed; make the ordinary man small and intimidated. Text content: Include exactly 7 speech/text bubbles and 1 rectangular label box. Use vertical Japanese manga lettering. Keep the text legible where possible, but it may look slightly hand-lettered. Bubble 1 in panel 1: 「あれ……?」. Bubble 2 in panel 2: 「あぁ…今月末でFbからのサブスクが……週末に届くかなぁ…」. Bubble 3 in panel 3: 「やべ……帰ってきた瞬間こんな…週末に間に合わえるのに…」. Bubble 4 in panel 4, white text inside black oval: 「おやぁ……お兄さん、お困りのようですね」. Bubble 5 in panel 5 right: 「それ、私にお任せいただけやしませんかねぇ?」. Bubble 6 in panel 5 left: 「あ、あんた……どこの手先だ…?」. Bubble 7 in panel 7 left: 「嗚呼、申し遅れました。私、最近リリースされたばかりなおすけなモデルです。機も性能も期はさせませんよ…とだけ申しておきましょうか」. Rectangular label box in panel 7 lower right: 「???」. Add exactly 3 visible sound effects: panel 1 「ぐらりっあっ」, panel 3 「ヨロ…ッ」, panel 6 「にぃ…っ」. Environment details: The alley is extremely dense and claustrophobic, filled with vertical Japanese and Chinese-style signboards, drainpipes, utility cables, fire escapes, damp brick and concrete walls, litter, puddles, mist, and shafts of light from above. Include wet reflective ground and smoky atmosphere around the pipe in the lower panels. Visual style: Ultra-detailed black-and-white manga, realistic anatomy, dramatic chiaroscuro, dense hatching and screentone textures, cinematic panel composition, gothic urban noir mood, no color, no modern UI elements, no watermark. The final image should look like a finished manga page scanned from print.

Generate image
GPT Image 2
Dark Monochrome Manga Cover
View full prompt & copy

Create a vertical manga cover illustration in a bleak monochrome ink-and-watercolor style with a tall 2:3 canvas. Center a slim androgynous young man with messy pale blond hair tied into a low ponytail, long bangs partly covering one eye, pale skin, narrow tired eyes, and a faint bitter smile. He wears a formal black suit jacket, white shirt, and black tie, holding a pale chrysanthemum-like flower delicately near his chest. From the top of his head grow two fragile insect-like antennae or moth wings, translucent gray-green and veined, being touched and pulled by surrounding hands. Around him place exactly 10 dark charcoal-black hands entering from the left and right edges: 5 from the left side and 5 from the right side, all elongated, clawlike, accusatory, or pinching, with some gripping the insect wings and one holding a drooping stem. The background is a black vertical panel framed by off-white side bands, filled with thin vertical gold lines and dripping white and gold liquid drops. Add distressed white Japanese title text centered near the top reading 黒蟲, with the number 1 underneath. Use muted colors only: black, gray, dirty white, faded gold, pale blond, and gray-green. The mood should be shabby, oppressive, elegant, melancholic, and slightly grotesque, like a dark psychological manga volume cover. Use rough paper texture, scratched ink edges, delicate linework, uneven washes, and no modern digital gloss. Keep the character centered, cropped from upper torso upward, with the hands forming a claustrophobic frame and no extra text or watermark.

Generate image
GPT Image 2
Japanese Webtoon Mecha Battle Page
View full prompt & copy

Goal: Create a vertical Japanese webtoon-style mecha battle manga page with dramatic diagonal paneling, glossy anime rendering, intense motion lines, red and purple sci-fi lighting, and high-contrast cinematic action. Canvas: Tall vertical comic page, approximately 2:3 aspect ratio, full bleed, black gutters between panels, dense detail, polished GPT-image anime/webtoon look. Layout: Use exactly 5 comic panels arranged from top to bottom. Panel 1 is the upper-left character close-up, panel 2 is the upper-right warning screen, panel 3 is a wide middle cockpit/action reaction panel, panel 4 is a large wide battle charge panel, and panel 5 is the bottom close-combat impact panel. Panel details: 1. Upper-left panel: A stern young male officer with blond hair and purple eyes stands in a futuristic cockpit. He wears an ornate red military uniform with black trim, gold epaulettes, medals, straps, and a red peaked cap with a gold crest. Add one vertical white Japanese speech bubble reading 「機体の性能差があるとしても、勝敗を決めるものはスペックではないですよ?大佐!」. 2. Upper-right panel: A red glowing sci-fi monitor in a dark cockpit, displaying the English warning text “THOR SYSTEM ACTIVATED” with a triangular alert icon. Surround it with red UI frames and Japanese sound effect lettering repeated at the top, like 「ピピピピピ」, plus a large red-white alarm sound effect near the bottom. 3. Middle panel: A determined young female pilot with long flowing blonde hair and bright blue eyes lunges forward gripping twin control handles inside a futuristic cockpit. She wears a crisp white military uniform with black collar, gold buttons, medals, shoulder cords, and decorative pins. Her expression is fierce and confident. Add one jagged white Japanese speech bubble reading 「ふふん!スペックだけで勝敗が決まらんことなど百戦錬磨のワシが一番よく知っている!」. 4. Large battle panel: Two humanoid mecha clash at extreme speed in outer-space or a neon battlefield corridor. On the left, a red-and-gold armored knight-like mecha charges with a long red energy lance, followed by a swarm-like trail of red afterimages or allied units. On the right, a blue-purple heavily armored mecha with a large shield and sword braces for impact. Use explosive red and violet speed lines converging at the clash. Add large stylized Japanese impact sound effects such as 「ドォンン!!」 and 「ギュンッ!!」. 5. Bottom panel: Close-up continuation of the duel: the red mecha’s lance pierces or strikes the purple mecha’s shield/armor at point-blank range, scattering sparks and debris. The red mecha is on the left, purple mecha on the right, with extreme motion blur and bright energy streaks. Add one vertical white Japanese speech bubble on the left reading 「もらった!」. Visual style: Japanese webtoon manga, high-detail anime faces, sharp line art, saturated red and purple lighting, metallic mecha rendering, dramatic perspective, dense speed effects, glowing energy weapons, cinematic sci-fi cockpit interiors, bold manga sound effects with white outlines and red/black fills. Key customizable elements: The male officer should be red; the female pilot should be white; the alert screen text should read THOR SYSTEM ACTIVATED; the left mecha should be red and gold; the right mecha should be blue-purple and silver. Constraints: Keep exactly 5 panels, exactly 3 speech bubbles, and preserve the Japanese manga page feel. Do not add extra characters, extra panels, watermarks, page numbers, or English narration outside the monitor text.

Generate image
GPT Image 2
Peanuts Style Football Haaland Poster
View full prompt & copy

A charming classic newspaper comic strip illustration in a nostalgic Peanuts-inspired aesthetic (without directly copying any original character), featuring a cute chibi football superstar with blond hair tied into a short ponytail, oversized round head, tiny smiling face, simplified black line art, wearing a red Norway football jersey with number 9, white shorts, striped socks, and bright pink football boots. The character walks confidently with hands swinging and a playful smile. Beside him are two adorable cartoon companions: a small white beagle-like dog and a tiny yellow bird, both wearing matching Norway football shirts, happily walking alongside him with surprised expressions and floating exclamation marks above their heads. Clean light-gray background, minimal composition, soft pastel colors, hand-drawn ink outlines, subtle paper texture, vintage Sunday comic style, expressive poses, wholesome humor, balanced spacing, crisp vector-like quality, children's book illustration, timeless cartoon charm, ultra-clean, high resolution. At the bottom, include bold vintage serif typography reading "HAALAND", centered with decorative horizontal lines above and below, creating the look of a collectible sports poster.

Generate image
GPT Image 2
Bold Editorial Cartoon Illustration
View full prompt & copy

Create a bold editorial cartoon illustration of [MAIN CHARACTER] with an oversized [CARTOON HEAD], showing [FACIAL EXPRESSION]. The character wears [OUTFIT], performing [POSE], with [HAND GESTURE]. Draw in a clean vector comic style using thick black outlines, flat colors, cel shading, subtle grain texture, vintage print effect, minimal solid background in [BACKGROUND COLOR], centered composition, exaggerated proportions, humorous editorial illustration, urban pop art aesthetic, vibrant colors, high contrast, ultra sharp details, professional vector artwork, poster quality, 8K.

Generate image
GPT Image 2
Spain vs France World Cup Comic
View full prompt & copy

Goal: Create a colorful six-panel comic strip predicting a World Cup 2026 semi-final football match between Spain and France, in an energetic kid-friendly sports-cartoon style. Canvas: Square 1:1 image divided into exactly 6 rectangular panels arranged in a 2-column by 3-row grid, with thick black comic borders and slightly textured print-comic shading. Visual style: Bright saturated colors, bold ink outlines, dynamic motion lines, exaggerated joyful expressions, packed stadium backgrounds, waving red-yellow Spanish flags and blue-white-red French flags, green football pitch, dramatic perspective, speech bubbles, scoreboard banners, and lively crowd confetti. Characters are stylized young male footballers with large expressive eyes and athletic cartoon proportions. Panel layout and required content: 1. Top-left panel: Establishing match panel inside a huge stadium. A large scoreboard reads “WORLD CUP 2026 SEMI-FINAL” with Spanish and French flags and the matchup text “SPAIN VS FRANCE.” Show two main players facing off: a Spain player in a red jersey with number 9 and a France player in a blue jersey with number 10. Add two smaller players and a ball near midfield behind them. 2. Top-right panel: Goal action for Spain. The Spain number 9 player kicks the ball toward the net while a goalkeeper in a green kit dives and misses. Add a speech bubble reading “GOAL!” above the striker. 3. Middle-left panel: France equalizer celebration. Scoreboard reads “1 - 1.” A large speech bubble says “GOOOAL!” Show exactly 5 visible players celebrating: one Spain number 9 at the left edge looking disappointed or surprised, and four France players in blue celebrating, including the central number 10 with both arms raised and one France number 9 at right. 4. Middle-right panel: Intense duel. A banner at the top reads “TENSE ACTION!” Show the Spain number 9 and France number 10 running shoulder-to-shoulder, glaring competitively and chasing a football between them. 5. Bottom-left panel: Last-minute chance. A banner reads “LAST MINUTE CHANCE!” Show the Spain number 9 taking a powerful shot at goal while the green goalkeeper with number 4 leaps across the goalmouth. The ball flies dramatically toward the net with white speed streaks. 6. Bottom-right panel: Final result celebration in front of a stadium with the Eiffel Tower visible in the background. A scoreboard banner reads “FULL TIME” with both national flags and the final score line “SPAIN 1 - 2 FRANCE.” Add a speech bubble reading “WE’RE IN THE FINAL!” Show exactly 6 celebrating players grouped together: one Spain player in red number 9 in the center looking excited, surrounded by five France players in blue with raised fists and smiling faces. Text content to include exactly as visible: “WORLD CUP 2026 SEMI-FINAL”, “SPAIN VS FRANCE”, “GOAL!”, “GOOOAL!”, “1 - 1”, “TENSE ACTION!”, “LAST MINUTE CHANCE!”, “FULL TIME”, “SPAIN 1 - 2 FRANCE”, and “WE’RE IN THE FINAL!” Constraints: Use exactly 6 panels, keep all football jerseys clearly color-coded red for Spain and blue for France, make the final score SPAIN 1 - 2 FRANCE, avoid photorealism, avoid extra panels, avoid watermarks, and keep all text large, legible, and comic-book styled.

Generate image
GPT Image 2
Manga Fashion Line Art Girl
View full prompt & copy

Create a full-body black-and-white manga fashion line drawing of a slim young woman with long straight dark hair and wispy bangs standing alone on a clean white background. She is posed in a relaxed three-quarter view, head turned slightly toward the viewer with a calm, distant expression, one hand tucked into a pocket and the other arm hidden by the oversized sleeve, legs long and slightly crossed. Use delicate hand-drawn ink sketch lines with visible construction-like strokes, fine hatching, loose contour lines, no color, no shading except line texture, and lots of empty white space. The outfit has exactly 5 visible clothing pieces: 1 oversized vertically striped button-up shirt with dropped shoulders and large sleeves, 1 high-waisted plaid mini skirt, 1 pair of scrunched mid-calf socks with vertical ribbing, 1 pair of low heeled loafers, and 1 subtle collar detail at the neckline. Emphasize fabric patterns with dense pen lines: vertical stripes on the shirt, crosshatched plaid on the skirt, ribbed socks, and lightly sketched shoe seams. Keep the figure centered vertically, cropped with generous margins, elegant Japanese illustration style, minimal background, no text, no props, no color fills.

Generate image
GPT Image 2
Rhinoceros Beetle Boy Fashion Sketch
View full prompt & copy

Create a black-and-white manga fashion illustration on a clean white background featuring exactly 2 full-body slim teenage boys with delicate androgynous faces, long legs, tousled short dark hair, and rhinoceros beetle-inspired headpieces worn like masks or crowns. The style should look like fine ink pen line art from a fashion sketchbook: crisp contour lines, expressive cross-hatching, sparse shading, no color, no background objects, no text, no border. Subject 1 on the left: a relaxed boy facing slightly forward-left with one hand in his pocket, calm serious expression, wearing a large beetle horn mask on his head with one tall forked horn rising upward, small insect legs/antennae details, a loose vertically striped button-up shirt with rolled sleeves, a dark scarf or ribbon tied at the neck, high-waisted plaid shorts, a narrow belt with a long hanging strap, slouchy socks, and lace-up ankle boots. Subject 2 on the right: a similar boy standing in a fashion pose facing to the right with one hand in his pocket, wearing a beetle mask with two curved horns and glossy shell detail, a checkered blazer, a dark sleeveless knit vest or shirt, a small bow tie, high-waisted vertically striped shorts, a belt, slouchy socks, and lace-up ankle boots. Keep both figures elegant, youthful, and slightly aristocratic, with the beetle headpieces as the focal point. Use rhinoceros beetle boy, black-and-white manga ink fashion sketch, vertical striped shirt and plaid shorts, checkered blazer and vertical striped shorts, and plain white background.

Generate image
GPT Image 2
Heroic England Footballer Concept Art
View full prompt & copy

Create a full-body heroic character concept illustration of Jude Bellingham as an elite England footballer, standing tall in a confident contrapposto pose with one foot resting on a football. He is a young athletic Black male with short textured black hair, sharp facial features, long muscular limbs, and an intense upward-looking expression. Dress him in a clean white England national team kit: white short-sleeve jersey with blue trim, England crest on the chest, Nike swoosh, red number 10 on the jersey and shorts, white shorts, long white socks with subtle red and blue stripes, and white football boots. Place a realistic patterned football under his forward foot. Surround the figure with dramatic swirling paint strokes in red and blue, forming a dynamic vertical spiral behind and around his body like national colors in motion, with splatters and rough brush edges. Use a polished anime-comic sports concept art style with angular ink lines, painterly shading, exaggerated anatomy, strong calf and arm definition, crisp fabric folds, and a heroic fashion-illustration silhouette. The background should be warm off-white paper with minimal texture, no stadium, no crowd, no text, centered composition, vertical poster format, full figure visible from head to boots, high detail, clean negative space, dramatic but elegant.

Generate image
GPT Image 2
Gothic Bishounen Reads to Hamster
View full prompt & copy

Goal: Create a black-and-white shoujo manga page with exactly 3 horizontal panels showing a beautiful gothic young man reading to a cute hamster in an elegant private library. Canvas: Vertical manga page, portrait orientation, thin black outer border and thick black gutters separating the 3 stacked panels. High-detail monochrome ink, delicate screentone shading, luminous soft daylight, crisp line art, romantic bishounen aesthetic. Main character: A slender, androgynous young man named Sol, with messy wavy black hair falling over his eyes, pale skin, long lashes, calm melancholy expression, ornate dangling earrings, a dark tailored suit jacket, white shirt, decorative cravat or ribbon tie, and celestial star-themed brooch chains on his chest. He holds an ornate hardcover book with a star/compass emblem on the cover. Hamster character: A small round golden hamster with fluffy fur, tiny ears, bead eyes, and soft whiskers, drawn cutely and expressively. The hamster sits on books or a desk and reacts to the reader. Setting: A refined study/library with tall bookshelves full of books, an armillary sphere or celestial globe, stacked books, a writing desk, ink bottle, large bright window with curtains, framed botanical art, and an antique table lamp. Keep the environment elegant, scholarly, and slightly fantastical. Panel layout and exact contents: 1. Top panel: Wide establishing shot. The young man sits at a desk on the left, reading an open book, surrounded by bookshelves and celestial instruments. The hamster sits on a stack of books on the right near a lamp and window. Include exactly 2 speech bubbles: the young man says では今日の物語をはじめようか; the hamster says きゅっ. 2. Middle panel: Closer intimate shot. The young man leans forward behind the open book, smiling softly at the hamster, who faces him from the right in close-up. Include exactly 1 speech bubble from the young man saying むかしむかしあるところにー. 3. Bottom panel: Dreamy close-up. The young man rests his cheek on one hand while continuing to read, gazing fondly toward the hamster. The hamster sits upright, eyes closed, paws clasped, smiling with delight. Add small sparkles, flowers, bubbles, and soft decorative effects around the hamster. Include exactly 1 speech bubble from the hamster saying きゅう〜〜♡. Text constraints: Use vertical Japanese manga speech bubbles matching the defaults. Keep exactly 4 speech bubbles total across the whole page. Do not add extra captions, sound effects, signatures, watermarks, or English text. Style constraints: High-detail grayscale manga illustration, elegant romantic atmosphere, fine hair strands, ornate clothing details, soft highlights, clean panel borders, no color.

Generate image
By @INK
GPT Image 2
Happy Tengu Samurai Concept Art
View full prompt & copy

Create a full-body character concept illustration of a Happy Samurai: a tall, lean, shirtless wandering samurai standing relaxed against a plain warm off-white background. He wears a vivid red tengu/oni-style mask with an extremely long pointed nose, two tall horns, dark expressive eye openings, and a wide laughing open mouth, giving him a mischievous happy expression. Small purple flowers are tucked near the mask and hair. Pose him in a casual contrapposto stance, one arm draped lazily over a long black sheathed katana or staff balanced horizontally across his shoulders, the weapon stretching far beyond both sides of his body; the right end has a black-and-gold diamond-wrapped handle and dangling tassel, the left end is a dark scabbard with subtle fittings. Dress him in tattered layered samurai clothing: a loose pale gray-blue haori slipping off one shoulder, dark green inner robe panels hanging raggedly, oversized dark blue hakama pants cropped above the ankles, a thick tan rope belt tied in a large knot at the waist, and straw rope sandals on bare feet. Use angular painterly brushwork, high-fashion character design proportions, sharp cel-shaded planes, rough ink-like edges, visible fabric tears and folds, earthy muted colors with strong black accents, minimal ground shadow, and lots of negative space. No text, no border, no watermark.

Generate image
GPT Image 2
Rainbow Light Projection Comic Portrait
View full prompt & copy

Create a modern comic-style close-up portrait of a glamorous young woman with black shoulder-length wavy hair, warm fair skin, glossy full lips, subtle winged eyeliner, and a calm confident gaze looking slightly toward the viewer. She is posed in a three-quarter view with one bare shoulder visible and one elegant hand resting under her chin, long manicured nails visible. Cover her face, neck, shoulder, arm, and hand with vivid projected light patterns: concentric contour-like rainbow ripples in neon cyan, magenta, purple, orange, green, and pale yellow, as if a psychedelic moiré or oil-slick topographic projection is cast across her skin and hair. Use the same swirling luminous pattern as the entire background, dense and high-contrast, with many organic oval rings and warped bands flowing diagonally around her silhouette. Style should be a polished modern manga / semi-realistic comic illustration with sharp ink-like linework, painterly shading, high detail in eyes, lips, hair strands, and hands, dramatic saturated lighting, deep shadows, glossy highlights, and a square canvas. No text, no watermark, no border, no extra characters.

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.