GPT Image 2 prompts

Create a realistic travel-fashion street photo of {argument name="subject" default="a young blonde woman"} sitting on the rough stone ledge of the Trevi Fountain in Rome on a bright sunny day. She is posed leaning forward slightly with one knee bent up and one leg extended, long straight strawberry-blonde hair falling over her shoulders, and her face intentionally covered by a flat tan square privacy blur. She wears exactly 6 visible outfit/accessory elements: {argument name="outerwear" default="an oversized cream blazer"}, a white lace mini dress with scalloped lace hem and lace bodice, white knee-high socks, chunky black Mary Jane platform shoes, a small silver pendant necklace, and a black quilted shoulder bag with a chain strap hanging at her left side. The background shows the ornate white marble architecture and statues of the Trevi Fountain, pale turquoise fountain water, carved rock formations, a tall black decorative streetlamp rising near the center-right, narrow old stone buildings on the left, and a vivid blue sky with scattered white clouds. Use a casual tourist snapshot composition in vertical 4:5 aspect ratio, wide-angle phone-camera perspective, natural daylight, crisp architectural detail, soft shadows, realistic skin and fabric texture, and no text or watermark. Keep the subject centered-left in the foreground, with the fountain filling the right background and the black streetlamp visually separating the subject from the fountain.

Create a realistic fashion travel photo of a young adult woman with {argument name="hair color" default="long wavy brown hair"} sitting on the stone ledge beside the turquoise water of the Trevi Fountain in Rome, with the ornate white Baroque fountain facade, statues, columns, carved stone, and surrounding narrow cobblestone streets visible in the background under a vivid blue sky with scattered white clouds. She is posed leaning back on one hand with both legs extended diagonally toward the camera, giving a wide-angle street-photography perspective. Her face is intentionally obscured with a smooth rectangular blur while the rest of the scene remains sharp and natural. Outfit: exactly 7 visible gothic fashion elements — 1 black puff-sleeve lace-trim peplum top with a silver cross-like ornamental design on the chest, 1 layered black choker, 1 long black beaded necklace with cross pendants, 1 pair of distressed black denim shorts with straps and metal rings, 1 black studded wrist cuff, 1 pair of tall slouchy black leather boots, and 1 set of dark bracelets on the opposite wrist. Use bright midday natural light, crisp architectural detail, realistic skin and fabric textures, shallow but readable background depth, high-resolution editorial travel style, vertical 4:5 composition, no text, no watermark, no extra people in the foreground.

Goal: Create a high-energy Roblox fantasy game thumbnail for {argument name="game title" default="SUMMON DASH"}, styled like a premium mobile RPG advertisement with bold comic action graphics.

Canvas: 16:9 widescreen thumbnail, 1200x675 composition, vibrant and highly saturated, designed to be readable at small YouTube/Roblox thumbnail size.

Layout: Place the huge game logo in the upper left, taking about one third of the image width. The logo has two words: “SUMMON” in chunky beveled gold fantasy lettering with black jagged shadow, and “DASH” underneath in bright electric-blue brush lettering. In the center foreground, show one Roblox-like armored runner charging toward the viewer on a stone path. On the right side, show a glowing circular summoning portal with a floating golden spear in front of it. Use diagonal motion lines, flying sparks, blue energy, and arrows to guide the eye from left foreground to the portal and then to the bottom-right success label.

Subject details: The central character is a short, blocky Roblox-style knight wearing a black hood, dark leather shoulder armor, brown gauntlets and boots, chainmail sleeves, and a yellow tabard with black fleur-de-lis heraldry. The character is mid-run with one fist forward and one arm back, kicking up dust behind the feet; the face is mostly hidden in shadow under the hood. The environment is a fantasy dungeon-city made of blocky stone ruins, torches, distant castle silhouettes, purple-blue evening sky, and glowing magical accents.

Counted visible elements: Include exactly 1 central running knight, exactly 1 giant summoning portal, exactly 1 floating spear, exactly 4 blue crystal objects with gold winged mask emblems, exactly 1 skull banner on the right, exactly 1 green checkmark badge, and exactly 3 blue arrow tiles on the stone path. The 4 crystal/emblem objects are: one large crystal cluster in the lower-left foreground, one small floating emblem near the center-right path, one small floating emblem near the portal, and one larger floating emblem on the far right.

Text content: Use exactly 5 text groups. Text group 1 is the main logo: {argument name="game title" default="SUMMON DASH"}. Text group 2 near the top center-right on a black brush-stroke label says “SUMMON” in white and {argument name="summon target text" default="THE ARBITER!"} in yellow, with a white curved arrow pointing toward the spear/portal. Text group 3 in the lower left says “COLLECT” in white and {argument name="collectible text" default="CRYSTALS!"} in cyan, with a white arrow pointing to the large crystal. Text group 4 in the lower right says “DELIVER” in white and {argument name="delivery target text" default="TO DEATHKNIGHT!"} in yellow, with small white arrows toward the banner. Text group 5 at the bottom right says {argument name="success text" default="LEVEL CLEAR!"} in glowing neon green next to the green checkmark badge.

Visual style: Exaggerated fantasy-action illustration, crisp 3D game-promo rendering, thick black outlines, dynamic perspective, strong rim lighting, electric blue portal glow, gold highlights, painterly sky, cinematic depth, high contrast, saturated colors, polished Roblox-inspired proportions, no photorealism.

Constraints: Keep all text large, legible, and spelled exactly as specified. Do not add extra text, UI panels, watermarks, logos, or additional characters. Maintain the thumbnail as a single dramatic action scene rather than a collage.

Goal: Create a widescreen screenshot-style image of a dark ComfyUI node graph demonstrating GPT image editing from a text instruction embedded in a mask.

Canvas: 1200×580 horizontal frame, dark charcoal grid background, cropped like a real workflow editor screenshot. Use crisp UI panels with rounded corners, subtle shadows, small sans-serif interface text, and colored connection cables.

Layout: Arrange exactly 7 visible workflow nodes from left to right across the canvas. Include 4 nodes on the left, 1 large central processing node, and 2 output/preview nodes on the right. Show blue image sockets and green mask sockets connected by curved wires.

Nodes and contents:
1. Top-left node titled “Load Image (from Outputs)”. It shows a green rectangular preview filled with a repeating circle/arc geometric pattern, size label “1536 × 1024”, and small controls including image selector, auto-refresh toggle, and refresh button.
2. Upper-middle-left node titled “Load Image”. It shows a white rectangular preview with thin black repeating overlapping circle pattern, size label “1536 × 1024”. Connect its blue IMAGE output to the central node image input.
3. Lower-middle-left node titled “Load Image (as Mask)”. It shows a dark preview with red pixel-like text reading “hello chatgpt” on the first line and “please make the image green” on the second line. The channel dropdown says “red”. Connect its green MASK output to the central node mask input.
4. Bottom-left node titled “Load Comfy Clipspace Mask”. Include controls labeled clipspace_file “latest” and invert_mask toggle, plus small image and mask sockets. This node is visible but not the main connection.
5. Center node titled “OpenAI GPT Image Direct”. It has inputs labeled image and mask; outputs labeled images, mask, and revised_prompts. The prompt textbox contains {argument name="instruction prompt" default="follow the instructions in the mask"}. Settings visible: model {argument name="model" default="gpt-image-2"}, quality {argument name="quality" default="medium"}, size {argument name="image size" default="1536x1024"}, custom_width 1024, custom_height 1024, n 1, output_format png. Connect its blue images output to Save Image, and its gray/green mask or revised prompt output down to Preview as Text.
6. Upper-right node titled “Save Image”. It shows filename_prefix “ComfyUI” and a result preview: the same circular pattern now colored bright green, with the black text instruction overlaid in the upper-left reading “hello chatgpt” and “please make the image green”; size label “1536 × 1024”.
7. Lower-right node titled “Preview as Text”, partially cropped at the bottom edge, connected from the central node’s revised_prompts output; show a small “source” label and a “Preview” area.

Visual style: Realistic UI screenshot, dark theme, subtle grid, rounded black-gray panels, white and gray interface labels, blue and green socket dots, curved blue/green connector lines. The generated image previews should look flat and procedural rather than photorealistic.

Constraints: Keep the exact workflow concept readable: a white patterned input image plus a mask containing text instructions produces a green patterned output. Do not add people, branding outside ComfyUI/OpenAI labels, extra nodes, or decorative elements.

Using REFERENCE_0 as the source materials, transform the photographed craft supplies into a cheerful Japanese baby-toy concept sheet for a DIY robot toy. Do not simply reproduce the photo; infer a finished toy made from the visible materials and present it as a polished parent-facing instruction poster.

Goal: Create a cute concept sheet titled {argument name="main headline" default="たっちできる やさしいロボちゃん"}, showing a handmade standing robot baby toy made from the paper cups, milk carton, small drink bottles, and colored tape in the reference.

Canvas and style: Vertical 4:5 educational poster, warm cream background, soft pastel colors, rounded boxes, hand-drawn stars and doodles, friendly nursery/baby-product design. Use a clean Japanese magazine layout with large playful pink and green headline lettering.

Main toy design: Build one central robot from the reference materials: milk carton body, paper-cup head, paper-cup arms, small-bottle legs, colorful tape edges and joints. Give it a simple smiling face, rosy cheeks, a blue square chest panel with a yellow heart, colored button dots, and stable wide feet. Make it look safe, soft, handmade, and suitable for supervised baby play.

Added imagery and layout: Include exactly 1 large hero image of the completed robot on the left, 1 small lifestyle photo-style panel on the upper right showing a baby and parent playing with the robot, and 1 labeled diagram panel explaining which material forms each body part. Blur or simplify any human faces.

Text sections to include in Japanese:
- Subtitle under the headline: {argument name="subtitle" default="身近な材料でつくる 赤ちゃん向けDIYおもちゃ"}
- Age badge in the upper right: {argument name="age range" default="対象月齢：10か月〜18か月（保護者と一緒に）"}
- Two speech bubbles: one saying the robot is sturdy even if touched or gently shaken, and one saying it is fun for standing practice.
- Materials section labeled 「材料」 with exactly 4 listed items: 「紙コップ（白）8〜10個」, 「ミルクパック（1L）1本」, 「小型ボトル（飲むヨーグルトなど）2〜4本」, 「カラーテープ（布テープやビニールテープ）」.
- Making section labeled 「つくり方（4ステップ）」 with exactly 4 numbered steps: 1 body, 2 head, 3 feet and legs, 4 attach arms and finish.
- Diagram section labeled 「つくりのイメージ（材料と役割）」 with arrows to exactly 5 parts: head paper cup, hand paper cups, body milk carton, feet small bottles, foot cups.
- Play section labeled 「あそび方」 with exactly 4 bullet ideas: touching/standing support, knocking it down and setting it back up, gentle rolling or movement, observing balance.
- Development aims section labeled 「ねらい（育ちのサポート）」 with exactly 4 bullets: seeing, touching, hand movement, cause-and-effect understanding.
- Safety section labeled 「安全ポイント（必ず守りましょう）」 with exactly 6 short icons/cautions: do not use small parts, secure caps, cover cut edges, use soft materials, make stable feet, always play with an adult watching.

Constraints: Keep the poster visually cute and practical, like a real printable DIY handout. Use the reference materials as the basis for the robot and material thumbnails, but replace the floor-photo setting with the clean designed concept sheet. Avoid adding unrelated materials, avoid extra steps or extra sections, and keep all Japanese text legible.

Create a realistic cinematic portrait of an elegant young woman with {argument name="hair color" default="long silky chestnut-brown hair"}, standing on a luxurious stone terrace at a historic European villa during golden hour. She wears a {argument name="dress style" default="soft beige embroidered traditional dress with delicate pink floral details, lace-trimmed sleeves, and a sheer matching dupatta draped over one shoulder"}. Her left hand rests gently on a carved stone balustrade while she faces the camera in a relaxed three-quarter pose; her face is covered by a plain soft-edged rectangular skin-tone privacy blur centered over the facial area. The setting includes an old stone building with an arched doorway on the right, cobblestone paving, carved terrace railings, tall dark green cypress trees, terracotta pots filled with vibrant pink flowers, and a distant countryside view framed by a stone archway in the background. Use warm golden sunlight, natural highlights in the hair, soft shadows, shallow depth of field, romantic Mediterranean villa atmosphere, high-resolution photorealism, refined natural beauty, and a softly blurred background. Keep the composition vertical portrait, waist-up framing, no text, no watermark, no extra people.

Using the provided reference image, enhance and restore it into an ultra-premium photorealistic 8K cinematic-quality photo. Preserve 100% of the original subject identity, pose, framing, composition, and color relationships: the kitten remains centered behind the same foreground ledge against the same blue background. Recover realistic micro-details lost in the low-resolution source: sharp glossy eyes, natural fur texture, fine whiskers, ear hairs, subtle skin and nose detail, clean edges, and realistic depth of field. Remove pixelation, blur, noise, color blotches, and compression artifacts while keeping the image natural, high-contrast, studio-quality, and believable. Do not change the kitten’s expression, position, markings, or background layout.

Create a cinematic dark sci-fi battle scene in a devastated muddy wasteland at sunset, wide 16:9 frame. In the left foreground, show a towering futuristic armored knight/cyborg warrior in heavy scratched gunmetal exosuit armor, crouched and bracing forward while gripping a long black spear or staff diagonally across the bottom of the image; the helmet has a Roman-style black crest, narrow glowing blue eye slits, and small cyan light accents on the chest and gear. In the right midground, show one feral female humanoid attacker with wild dark hair, athletic body, ragged dark clothing and bandaged striped forearms, lunging toward the armored warrior through an explosion of mud and debris; her face is obscured by a soft square blur/censor block. Surround her with vivid branching red lightning and crimson energy arcs, making the mud and particles glow red. The environment is a ruined battlefield with shallow reflective puddles, churned mud, scattered wreckage, burning dead trees or industrial ruins in the distance, orange fires, smoke columns, ash, sparks, and a stormy cloud-filled sky. Use ultra-detailed photorealistic concept art, high contrast, gritty texture, dramatic rim lighting, volumetric smoke, motion blur on debris, wet reflections, cinematic color grading with cold steel blues against fiery orange and electric red. Emphasize two discrete characters: 1 armored cyber-knight with spear, 1 red-lightning attacker. No text, no watermark.

Create a high-quality cinematic double-exposure paper-tear collage portrait of a beautiful young South Asian woman with {argument name="hair color" default="long silky dark brown hair"}, wearing an elegant {argument name="outfit" default="deep teal embroidered traditional salwar kameez with gold detailing, matching trousers, and a sheer teal dupatta"}. The image is a vertical 3:4 composition split by one jagged torn-paper horizontal edge running diagonally across the middle. The upper half shows a large ethereal close-up portrait filling the frame from shoulders upward, with the woman turned slightly downward and to the side, soft natural skin tone, glossy center-parted hair, ornate gold jhumka earrings, and a softly blurred neutral city background. The lower half shows the same woman as a full-body figure walking toward the camera in the center of a wet urban street at golden hour, with blurred cars, glowing headlights, misty buildings, and warm sunlight in the distance. Preserve realistic proportions, cinematic depth of field, moody warm lighting, reflective asphalt, subtle bokeh, and a refined fashion editorial look. Include exactly 2 depictions of the woman: 1 oversized close-up portrait in the upper torn-paper layer and 1 full-body walking figure in the lower street scene. No text, no watermark, no extra people, no cartoon styling.

Create a hyper-realistic cinematic full-body fashion portrait of {argument name="character description" default="a stylish fair young Pakistani woman"} standing in a modern upscale café lounge, shown from head to shoes in a relaxed three-quarter side pose with her hands gently clasped at waist level. Her face is softly anonymized/blurred, and her dark hair is tied back in a neat low ponytail. She wears exactly 7 visible outfit and accessory elements: a blue-green oversized plaid cropped button-up shirt with rolled sleeves, a fitted white inner top, a sheer white dupatta with pale pink edging draped around her shoulders and flowing down her back, high-waisted light-wash wide-leg jeans, clean white low-top sneakers, a gold wristwatch, and small stud earrings. Use {argument name="fashion style" default="ultra-modern 2026 modest streetwear fashion"} with premium fabric texture and realistic stitching. The setting is a warm beige café interior with large bright windows on the left, soft sofas and seated customers in the background, a curved cream counter on the right, shallow depth of field, golden ambient lighting, and a polished tiled floor. Include exactly 4 blurred background people: one seated woman at the left foreground table, one seated person near the left window, and two seated men near the counter on the right. Shoot like a high-end editorial lifestyle photograph using an {argument name="camera lens" default="85mm lens"}, natural window light, creamy bokeh, realistic proportions, detailed denim texture, soft shadows, and a warm cinematic color grade. Avoid text, logos, watermarks, extra limbs, distorted hands, or exaggerated facial features.

Create a realistic close-up portrait of {argument name="subject" default="a beautiful young Pashtoon Pakistani woman"} from the chest up, seated indoors in soft natural window light. She wears {argument name="dress color and fabric" default="an elegant soft pink satin traditional Pashtoon dress"} with richly embroidered Afghan-Pakhtun cultural patterns: dense gold threadwork, vertical decorative panels on the bodice, small floral motifs in green, red, teal, and magenta, and a rounded neckline with ornate trim. Include exactly 4 visible jewelry elements: 1 delicate silver head chain with a small forehead ornament partly visible in her dark brown hair, 2 large matching silver dangling jhumka-style earrings with circular filigree tops and tassel chains, and 1 silver coin necklace around her neck. Her long dark hair is parted near the center and falls loosely over her shoulders. The face should be intentionally obscured by a flat vertical rectangular privacy block in a warm skin-tone gradient, covering the entire facial area from forehead to chin while leaving hair, ears, jewelry, neck, and clothing visible. Use shallow depth of field with a softly blurred warm interior background, pale curtains, bokeh highlights, and hints of red patterned textiles. Photorealistic editorial fashion photography, vertical 4:5 composition, gentle highlights on satin sleeves, culturally respectful styling, no text, no watermark.

Create a photorealistic medium-shot portrait of a {argument name="subject" default="beautiful young Indian woman"} standing indoors in a luxurious dressing room during an Eid celebration. She has very long straight {argument name="hair color" default="warm chestnut-brown hair"} parted in the center, falling over both shoulders, and her face is intentionally obscured by a smooth rectangular skin-toned blur with no visible facial features. She wears a shimmering {argument name="outfit colors" default="maroon, antique gold, and bronze"} traditional salwar suit with intricate silver embroidery, a V-shaped embroidered neckline, small floral motifs across the kameez, ornate metallic silver borders on the cuffs and hem, and a matching maroon-gold translucent dupatta draped over one shoulder with heavy embroidered edging. Add delicate jewelry: exactly 3 visible accessories, consisting of dangling earrings, thin gold bangles on one wrist, and a small bracelet on the other wrist. Pose her with one hand resting on a white marble vanity counter and the other hand lightly touching the front of her outfit. The background should be a softly blurred glamorous makeup vanity area with large mirrors framed by warm round bulbs, cream walls, white cabinetry, and golden bokeh lighting. On the counter include exactly 5 visible decorative items: a tray with perfume bottles, a small pink perfume bottle, a taller amber perfume bottle, crescent moon Eid ornaments, and a plate of dates or sweets. Use warm golden lighting, shallow depth of field, elegant festive styling, realistic fabric texture, high detail, square 1:1 composition, no text, no watermark.

Create a cinematic wide-angle fashion editorial scene inside a narrow immersive corridor completely covered with oversized glossy magazine covers and fashion advertisements on the walls, ceiling edges, floor, and side panels. A stylish adult man, {argument name="central model" default="a confident male fashion model"}, walks toward the camera down the center of the corridor wearing {argument name="outfit" default="an all-black tailored double-breasted suit with a black turtleneck, slim trousers, polished black dress boots, and a silver wristwatch"}. Use dramatic luxury-showroom lighting, strong perspective lines, and a high-fashion mood, as if inside a surreal magazine archive installation. Include exactly 12 clearly recognizable large editorial brand or magazine panels: Vogue, Chanel, Gucci, Dior, GQ, W, Harper's Bazaar, Tom Ford, Louis Vuitton, The Untold, Bvlgari, and Vanity Religion. Surround them with many smaller fashion portraits, model spreads, typography blocks, and product-ad-style layouts, but keep the 12 named panels dominant and legible. The corridor floor should be tiled with full-page magazine spreads, including photographs of models, article columns, and cover headlines, creating a collage path under the model's feet. Add two additional large male fashion posters on the side walls, one on the right resembling a GQ cover and one on the left embedded among Vogue and W spreads. Faces on posters and the central model may be softly anonymized or blurred, while clothing, pose, magazine typography, and luxury branding remain crisp. Color palette: warm beige, cream, black, white, tan, muted orange, and deep shadows, with glossy paper reflections. Shot as a realistic editorial photograph, ultra-detailed, 16:9 landscape composition, low-to-mid camera height, 24mm wide lens look, shallow but readable depth, no cartoon style, no empty walls, no extra logos beyond the visible magazine-fashion collage, no watermark.

Goal: Create a professional film storyboard sheet for {argument name="project title" default="CLOCKRUNNER"}, a monochrome pencil-and-ink cinematic storyboard set in a steampunk fantasy world of floating clockwork cities above clouds.

Canvas: Wide horizontal storyboard sheet, approximately 16:9, off-white paper texture, thin black panel borders, hand-drawn production-board aesthetic. Add a top header with PROJECT: {argument name="project title" default="CLOCKRUNNER"} on the left, SCENE: {argument name="scene number" default="01"} near the top center, and DURATION: {argument name="duration" default="~15 SEC (24 FPS)"} on the right.

Layout: Use exactly 15 numbered storyboard panels arranged in a clean grid: three rows of five panels. Each panel has a small boxed number in the upper-left corner and a caption block underneath with shot type plus action description. Beneath the 15 panels, add a bottom production strip containing: one character portrait box on the left, a character design notes text box beside it, a visual style notes text box, several full-body/action pose sketches of the heroine across the bottom center, and two detailed chronometer/clock device sketches on the bottom right.

Storyboard panels, exactly 15:
1. Wide establishing shot: a colossal floating city of gears and clock towers drifts above an endless sea of clouds; a narrow metal rail stretches between two suspended platforms.
2. Tracking shot: a young time-smuggler sprints along the rail, mechanical debris raining from above as warning sirens echo.
3. Medium shot: she leaps over broken sections of track; a giant clock mechanism collapses behind her.
4. Close-up: determined eyes and a glowing pocket chronometer spinning in her hand; no panic, only focus.
5. Wide shot: ahead, the rail ends abruptly; a massive gap separates her from the next platform.
6. Medium wide: she accelerates toward the edge; steam erupts from vents beneath the track.
7. Action shot: she launches into the air, coat billowing behind her as she reaches forward.
8. Wide shot: she falls through open sky, far below, clouds swirl around ancient machinery.
9. Close action: a retractable energy tether fires from her wrist; the cable streams toward a rotating clock tower.
10. Medium shot: the tether locks onto a moving gear; the sudden pull swings her across the void.
11. Close shot: she races along the tether; blue sparks trail behind her boots.
12. Wide tracking shot: the camera follows as she glides between giant rotating clock faces, narrowly missing gears spinning all around her.
13. Medium close: she lands briefly on a spinning gear; without stopping, she launches again.
14. Dynamic angle: she bursts through a ring-shaped time portal; fragments of glowing clockwork spiral around her.
15. Wide final shot: she emerges above a luminous city hidden inside the clouds; the horizon glows with golden light as she races toward her destination.

Character: The heroine is {argument name="character name" default="The Clockrunner"}, a female mid-20s athletic agile time-smuggler with short silver hair and asymmetrical bangs, long weathered coat with mechanical details, utility belt filled with time-tech gadgets, glowing pocket chronometer as signature item, steampunk sci-fi aesthetic, fast, fearless, highly resourceful.

Bottom strip details: Include exactly 1 character portrait box, exactly 2 text note boxes, exactly 5 small full-body/action pose studies of the heroine, and exactly 2 chronometer/clock device drawings. The character portrait may have a soft blurred or shaded face area but must still show hair, coat collar, shoulder armor, straps, and clockwork accessories.

Visual style: Cinematic storyboard illustration, ultra-detailed ink sketch, dynamic action composition, steampunk fantasy world, floating cities and giant clockwork structures, high motion energy, monochrome pencil rendering, concept-art quality, 16:9 storyboard panels, film-production storyboard layout, consistent character design across all shots. Use dense hatching, graphite shading, weathered paper, tiny technical details, dramatic perspective, clouds, gears, rails, towers, chains, smoke, and sparks.

Constraints: Keep everything black, gray, and sepia-toned like a scanned pencil production sheet. Make the text legible and in English. Do not add extra panels beyond the 15 listed. No color painting, no photorealism, no modern city elements, no watermark.

Goal: Create an ultra-premium 4:5 Instagram streetwear campaign poster for {argument name="brand collaboration" default="Nike × Billie Eilish"}, titled {argument name="campaign title" default="RAW MOTION"}, with high-contrast kinetic energy, a gritty underground urban setting, and a volt-green-on-black color system.

Canvas: Vertical 4:5 poster, 768×1024 style composition, Behance front-page quality. Dark concrete parking-garage or tunnel environment with dramatic low-angle perspective, motion blur light streaks, wet asphalt reflections, heavy grain, scratches, grunge texture, and cinematic contrast.

Main subject: A low-angle full-body fashion shot of {argument name="featured artist" default="Billie Eilish"} walking toward the camera in oversized black technical streetwear: glossy black bomber jacket, baggy black track pants, and neon volt-green sneakers. The nearest shoe is extremely close to the lens and exaggerated by wide-angle perspective, with visible tread and a gray Nike swoosh. Add green rim lighting along clothing folds. The face is intentionally obscured by a soft square blur/censor block while hair remains visible around it.

Primary graphic system: Place a massive oversized volt-green NIKE wordmark across the upper background, spanning almost the full width, with a giant volt swoosh sweeping behind the figure from left to right. The figure overlaps and partially covers the typography. Use distressed ink texture on the logo, slightly weathered and gritty.

Layout and text content: Include exactly 10 distinct text/logo zones:
1. Top-left small Nike logo in volt green.
2. Top-center small text: “NIKE × EILISH” followed by “VOLT COLLECTIVE”.
3. Top-right text: “LIMITED DROP” with a small globe icon.
4. Center background: huge “NIKE” wordmark and oversized swoosh in volt green.
5. Right-middle artist identification block with a small person icon: “BILLIE EILISH”, large “001”, “BE / BE-1”, “COLLECTION”, and four tiny circular technical icons.
6. Left-lower numbering block: large “23”, then “VOLT”, “COLLECTIVE”, “SERIES”, “0023_BE”.
7. Far-left lower translucent product/spec card with “BE-1” and “23” plus tiny diagram lines and icons.
8. Main headline at lower right in huge distressed white condensed type: “RAW” stacked above “MOTION”.
9. Small horizontal label below the headline: “ENGINEERED FOR IMPACT” with a Nike swoosh on a volt label, plus tiny barcode-like stripes and microcopy “MOVEMENT IS FREEDOM. FREEDOM IS YOU. JUST DO IT.” with a scribbled signature.
10. Bottom-right product pouch or tag object reading “VOLT COLLECTIVE” and “PROPERTY OF NIKE”, with tiny text such as “UNITED BY MOVEMENT”, “DRIVEN BY ENERGY”, and a small Nike swoosh.

Additional visual details: Add bottom-left small copyright/microtext and globe icon, diagonal volt hazard stripes near the bottom, painted volt-green floor arrows and road markings, subtle neon glow around shoes, and a black rectangular product pouch angled in the bottom-right corner. Use typography that is bold, condensed, athletic, and distressed, mixing large display type with tiny technical UI labels.

Color palette: Dominant black, charcoal gray, concrete gray, dirty white, and electric volt green {argument name="accent color" default="#B6FF00"}. Keep all highlights, shoes, logos, stripes, and technical labels in the same volt-green tone.

Constraints: Make the poster look like a premium Nike streetwear social media hero image, not a clean product catalog. Keep the composition crowded but readable, with exactly one human figure, exactly one oversized background NIKE wordmark, exactly one giant swoosh, exactly one bottom-right pouch object, and exactly the 10 text/logo zones listed above. No extra brand names, no extra people, no watermark.

Goal: Create an ultra-premium 4:5 Instagram streetwear campaign poster for {argument name="brand name" default="PUMA"} and {argument name="campaign title" default="STREET FORCE"}, with gritty urban action, neon yellow energy, concrete textures, and Behance-front-page-quality sportswear art direction.

Canvas: Vertical 4:5 poster, 1024×1280 feel, dark high-contrast underground parking garage or concrete tunnel at night. Use black, charcoal gray, dirty concrete, white spray paint, and electric volt yellow as the dominant accent color. Add film grain, dust, scratches, halftone texture, worn ink, and subtle print distress.

Main layout: A huge monolithic yellow {argument name="brand name" default="PUMA"} wordmark fills about 70% of the upper background, cropped close to the edges and sitting behind the athlete. Center foreground: one male street-football athlete crouching low, wearing a black hoodie with a small yellow cat logo, black pants, white socks, and bright volt-yellow sneakers. His hands are tattooed, one hand resting on a black football with a yellow cat logo. The face is intentionally covered by a plain medium-brown square censor block, while short curly hair and ears remain partly visible. Strong yellow fluorescent tube lights glow in the garage background and reflect on the wet/dark concrete floor.

Subject details: The athlete is crouched wide and powerful, elbows forward, looking toward camera despite the face block. Outfit count: exactly 5 main visible outfit/accessory pieces — 1 black hoodie, 1 pair black pants, 1 pair white socks, 1 pair volt-yellow sneakers, and 1 black football. Keep the shoes sharply lit and saturated yellow, with realistic fabric folds and streetwear styling.

Graphic system and visible text: Include exactly 16 distinct visible text/logo/label elements arranged like a premium fashion magazine cover: 1 large top-left yellow leaping cat logo; 2 small top-left lines reading “PUMA” and “STREETWEAR”; 3 top-right issue text elements reading “VOL.”, “01”, and “2024”; 1 tiny right-side vertical label reading “FOREVER FASTER.”; 1 right-side vertical barcode; 1 left-middle stacked slogan reading “BUILT DIFFERENT”; 1 right-middle athlete caption reading “NEYMAR JR. | STREETS WON’T FORGET.”; 1 yellow signature scribble under that caption; 1 lower-right product card reading “VOLT COLLECTION” with a barcode and “P. / 20 24”; 1 large lower-center stencil title reading “STREET FORCE”; 1 bottom-left boxed issue number reading “01”; 1 bottom-center yellow button reading “SHOP ONLINE”; 1 bottom-center website reading “PUMA.COM”; 1 bottom-right footer reading “VOLT COLLECTION”.

Additional graphics: Add exactly 7 non-text decorative street graphics — 1 white graffiti tag across the lower-left wall/floor, 1 yellow spray-painted crown above the word STREET, 1 yellow underline drip beneath FORCE, 1 small globe icon near the left slogan, 1 crosshair icon near the left slogan, 1 thin crosshair/target icon in the top-right corner, and 1 small globe icon inside or beside the SHOP ONLINE button. Add thin editorial border lines, small crop marks, micro grid lines, and barcode details without cluttering the poster.

Typography and style: Use massive condensed bold sans-serif typography for the background brand word, rough white stencil lettering for “STREET FORCE,” tiny technical editorial labels for the side and footer text, and high-fashion sports campaign spacing. The poster should feel like a Puma × {argument name="athlete name" default="Neymar Jr."} streetwear drop called {argument name="collection name" default="Volt Collection"}. Avoid extra people, extra balls, additional large text, or clean studio backgrounds.

Black-and-white fashion casting contact sheet of the attached image with black hair, arranged in a clean 2x2 grid of four close portrait frames against city background, wearing the same as the attached picture. Each frame shows a different expression and angle. Soft studio lighting, crisp monochrome contrast, natural skin texture, visible facial details, clean plain backdrop, subtle film grain, high-end editorial test shoot, minimal styling, intimate camera distance, professional portrait photography, aspect ratio 4:5.

Create image featuring a young Korean woman with mid-length brown hair styled with {argument name="hair clip color" default="lime green"} hair clips on both sides, posing against a plain white wall while wearing a cropped black long-sleeve top, black high-waisted pants, and a vibrant {argument name="bag color" default="lime green"} snakeskin-patterned saddle bag slung over her shoulder.

Use the uploaded face image as the exact facial reference and preserve facial identity, facial features, skin tone, hairstyle, eyes, smile, and natural proportions with maximum accuracy. Create an ultra-realistic classroom portrait with EXACTLY the same composition and pose as the reference image. A young man stands on the left and a young woman stands on the right, both leaning lightly against a classroom chalkboard with their arms folded across their chests. The male slightly tilts his head downward with a soft smile and looks toward the floor, while the female slightly tilts her head toward the camera with a gentle smile and direct eye contact. Their shoulders are close together, creating a cute and natural Korean drama feeling. The male wears a black bomber jacket covered with white cat prints over a layered casual outfit. The female wears a bright red bomber jacket covered with white cat prints over a dark school-style outfit. Behind them is a large dark green chalkboard with a hand-drawn smiling umbrella made of white chalk. The umbrella is perfectly centered, with the top directly above their heads and the handle positioned between them, creating the illusion that they are standing under the umbrella. The camera is straight at eye level, medium full-body framing, vertical composition, both subjects occupying the lower center of the frame exactly like the reference image. Warm sunlight enters from the left side, creating soft cinematic shadows. Korean drama aesthetic, cute romantic atmosphere, photorealistic, natural skin texture, professional photography, 85mm lens, shallow depth of field, HDR, ultra detailed, masterpiece, 8K UHD. Negative Prompt: different pose, hands not crossed, wrong composition, looking away, extra people, bad anatomy, extra fingers, extra limbs, duplicate face, cartoon, anime, blurry, low quality, watermark, logo, text, cropped.

Forced perspective photography, human hand holding vintage travel ticket, miniature high-speed train emerging from ticket onto paper, tiny detailed city scene with famous cathedral with tall spires, sketch style buildings and architecture drawings surrounding the scene, handwritten cursive text labels,

Ultra-realistic portrait of a beautiful young woman with long, voluminous {argument name="hair color" default="deep red"} hair, soft waves flowing over her shoulders, fair skin with natural freckles, expressive {argument name="eye color" default="hazel"} eyes, subtle natural makeup, soft pink lips, warm sunlight streaming through a window, cinematic lighting, gentle shadows on the face, {argument name="dress" default="black off-shoulder dress"}, elegant pose, highly detailed skin texture, photorealistic, shallow depth of field, professional photography, 85mm lens, ultra HD, sharp focus, realistic colors, masterpiece, 2:3 portrait ratio.

subject": {"person": "woman","appearance": {"hair": "dark brown, styled in a sleek, pulled-back bun","pose": "standing, one leg lifted slightly with the knee bent, looking downwards with a soft expression","outfit": {"style": "monochromatic, utilitarian chic jumpsuit","color": "deep coffee brown","details": "short-sleeved shirt top with collar and chest pockets, belted waist with a gold-toned buckle, wide-leg trousers"},"footwear": "pointed-toe high heels in a matching deep brown color"}},"setting": {"background": "minimalist, soft-focus draped fabric backdrop","lighting": {"type": "studio portrait lighting","quality": "soft, diffused, dramatic shadows","effect": "creates a gentle gradient and highlights the silhouette"}},"technical_specifications": {"image_quality": "4k resolution, high definition","style": "fashion photography, editorial","color_palette": ["#4B3621","#6F4E37","#D2B48C"],"composition": "full-body shot, centered","atmosphere": "elegant, sophisticated, modern"}}

Semi-realistic anime style young woman in the uploaded image, full-body fashion editorial, sitting casually on sunlit rooftop ledge, futuristic blue pilot jacket, white t-shirt, black tactical cargo pants, fingerless gloves, giant RX-78-2 Gundam towering behind, hyper-detailed mechanical armor, graphic anime overlay elements, HUD graphics, futuristic text, cinematic HDR lighting, urban skyline background, white blue red yellow palette, 8K.

A young woman with long wavy blonde hair and green eyes sipping a {argument name="beverage type" default="berry smoothie"} through a red straw with a playful, wide-eyed expression, looking directly at the camera. She is holding a clear plastic cup filled with a thick dark purple-pink berry smoothie with both hands, bringing it close to her face. The cup has a white circular logo sticker featuring a {argument name="logo symbol" default="green hummingbird"} with a red head on a white background. She is wearing a light {argument name="sweater color" default="lavender-purple"} chunky knit oversized sweater and bright pink pants visible at the bottom. The background is a soft, blurred white paneled wall. Studio-style lifestyle photography with warm, even artificial lighting, shallow depth of field, close-up portrait framing, face and upper body in focus, vibrant colors, commercial beverage advertisement style, photorealistic.