GPT Image 2 Prompts

GPT image 2 on chatgpt

Full prompt

image_generation": { "face": { "preserve_original": true, "reference_match": true, "description": "Maintain the same facial structure, skin tone, eye shape, and natural expressions across all frames, with consistent identity in each pose." }, "photo_style": { "type": "golden hour portrait collage", "camera_angle": "varied close-up and medium portrait angles", "lighting": "warm golden hour sunlight casting soft window shadows", "mood": "soft, calm, intimate, aesthetic", "texture": "natural skin texture, soft highlights, gentle contrast", "focus": "sharp focus on face with smooth background falloff" }, "subject": { "poses": [ "looking upward toward light", "soft smile facing camera", "side profile with downward gaze", "over-the-shoulder glance", "direct close-up with relaxed lips", "hand in hair casual pose", "head tilted back toward light", "clean side profile portrait", "thoughtful pose with hand near chin" ], "expression": "natural, minimal, relaxed, emotionally subtle", "hair": { "style": "long straight hair worn loose", "color": "light to medium brown", "details": "natural shine with soft light highlights" }, "clothing": { "type": "casual minimalist outfit", "details": "simple dark t-shirt with no visible branding" } }, "composition": { "layout": "3x3 grid collage", "consistency": "uniform lighting and background across all frames", "framing": "clean portrait framing with slight pose variation" }, "environment": { "setting": "indoor space near a window", "background": "plain wall with warm sunlight and shadow patterns", "atmosphere": "quiet, minimal, artistic indoor ambiance" }, "aesthetic": { "style": "Instagram aesthetic portrait set", "features": [ "golden hour light", "window shadow patterns", "minimal makeup", "natural expressions", "clean editorial portrait look" ] } }

Ultra-realistic cinematic close-up portrait of a strikingly handsome young man in his early 20s, wit…

Description

Prompt collected from YouMind; original author wording has not been independently verified.

Full prompt

Ultra-realistic cinematic close-up portrait of a strikingly handsome young man in his early 20s, with thick naturally wavy jet-black hair styled with soft volume and a slightly tousled side sweep, strong well-defined eyebrows, deep dark-brown eyes, a straight sculpted nose, prominent cheekbones, a sharp masculine jawline, and subtle natural stubble. He gazes slightly upward and toward the side with a calm, confident, mysterious expression. He wears a minimalist dark charcoal crew-neck shirt and a single sleek wireless earbud in one ear. Three-quarter profile, head slightly tilted upward, shoulders relaxed. Dramatic single-source side lighting creates strong highlights across his forehead, cheekbone, nose and jaw while leaving part of his face in deep cinematic shadow. Subtle warm skin tones contrast against a dark navy-black textured studio background. Sophisticated masculine editorial photography, moody luxury aesthetic, realistic skin texture and pores, natural facial imperfections, detailed hair strands, cinematic contrast, soft atmospheric shadows, shallow depth of field, 85mm portrait lens, f/1.8, professional studio photography, subtle film grain, HDR, ultra-detailed, photorealistic, 8K quality, premium fashion campaign aesthetic, no text, no watermark, no logos, no exaggerated muscles, no plastic-looking skin, no AI-looking face.

A photorealistic candid outdoor portrait of a young woman standing outside a cozy urban café on a ra…

Description

Prompt collected from YouMind; original author wording has not been independently verified.

Full prompt

A photorealistic candid outdoor portrait of a young woman standing outside a cozy urban café on a rainy afternoon. She has long dark-brown hair styled in a loose low ponytail, with a few soft face-framing strands naturally falling across her face. She gazes gently toward the side with a calm, dreamy expression. She wears a warm beige oversized knit sweater layered over a delicate white blouse, paired with a long dark-brown pleated skirt. A deep burgundy-red shoulder bag hangs naturally from her shoulder. She holds a transparent umbrella in one hand while the other hand gently adjusts a strand of hair near her face. She stands beside a rain-covered café walkway, surrounded by wet pavement, small green plants, warm café windows, subtle city buildings, and softly glowing street lights in the background. Tiny raindrops are visible on the umbrella, while reflections of the warm lights shimmer beautifully across the wet ground. Natural smartphone photography, candid lifestyle aesthetic, soft rainy-day atmosphere, realistic skin texture, detailed individual hair strands, authentic knit and fabric textures, natural reflections, shallow depth of field, cinematic ambient lighting, gentle vintage film grain, muted earthy color palette with warm café highlights, soft atmospheric contrast, peaceful romantic mood, highly photorealistic, vertical 4:5 composition.

A vertical, full-body photograph of a stylish young East Asian woman sitting at a vintage outdoor ca…

Description

Prompt collected from YouMind; original author wording has not been independently verified.

Full prompt

A vertical, full-body photograph of a stylish young East Asian woman sitting at a vintage outdoor café table, looking down at an open magazine with a soft smile. She is wearing a cream-colored long-sleeved ribbed cardigan and a long, pleated multi-colored brown plaid skirt. Her long wavy brown hair is half-up in a beige bow. On the round wooden table sits a bouquet of dried rust-orange flowers wrapped in newspaper. She wears cream-colored high heels, seated on a wooden chair. The background features a dark Parisian-style café exterior with warm indoor lights glowing through the glass, soft natural daylight, nostalgic atmosphere, highly detailed, photorealistic, 8k resolution.

ULTRA-REALISTIC NATURAL SMARTPHONE PHOTOGRAPH, vertical 3:4, candid winter travel portrait of a youn…

Description

Prompt collected from YouMind; original author wording has not been independently verified.

Full prompt

ULTRA-REALISTIC NATURAL SMARTPHONE PHOTOGRAPH, vertical 3:4, candid winter travel portrait of a young East Asian woman sitting comfortably in a huge snowbank outside a modern mountain-town building. She has medium-length dark brown hair styled in two loose low pigtails with soft strands framing her face. She wears a fluffy cream-white winter hat with a soft pink inner lining and a thick oversized pink-and-white striped scarf wrapped warmly around her neck. She has natural youthful features, rosy cheeks from the cold, and a bright genuine laugh while looking directly at the camera. She is dressed in a warm ivory-white puffer jacket and loose cream-white wide-leg winter pants. She wears thick brown knitted gloves and cozy tan winter snow boots with cream-colored fleece cuffs. Her hands are clasped together naturally between her knees while she sits in the snow, with both legs extending forward. Fresh deep snow completely covers the ground, forming large soft snowdrifts around her. Snowflakes are gently falling through the air, with small flakes visible against her clothing and in the background. Behind her is a modern multi-story building partially covered in snow, featuring dark metal exterior staircases, large windows, green storefront awnings, outdoor vending machines, railings, bare winter trees, and thick accumulated snow along the edges of the property. Soft overcast winter daylight, cool snowy atmosphere, realistic snow texture, subtle shadows, natural ambient lighting, peaceful snowy vacation setting. RAW smartphone photography aesthetic, ultra-realistic skin texture, natural facial details, realistic hair strands, authentic winter clothing textures, physically accurate snow, realistic proportions, natural candid pose, slight smartphone lens softness, no beauty filter, no plastic skin, no CGI appearance, highly detailed environment, authentic winter travel photography, vertical 3:4 composition.

Create a vertical two-panel composite image featuring a white duck wearing a crab shell as a hat. To…

Description

Prompt collected from YouMind; original author wording has not been independently verified. Source is marked reversed by YouMind.

Full prompt

Create a vertical two-panel composite image featuring a white duck wearing a crab shell as a hat. Top Panel: A photorealistic, high-angle shot of a plump white domestic duck standing on a beige woven rug with black leaf patterns. The duck is facing forward and has a large, cooked orange-red crab carapace resting on its head like a wide-brimmed hat. The background shows a bright, sunlit room with light grey tiled floors, soft shadows, and a glimpse of a dark wooden furniture leg in the upper right. Handwritten-style white text overlay on the left reads "A Brighter Day". Small serif text on the top right reads "Small Creatures Big Happiness" followed by a dash. Small serif text on the middle right reads "Same Weird Hat A Kinder Tomorrow" followed by a dash. Bottom Panel: A minimalist hand-drawn illustration on a textured off-white paper background. It depicts the same duck character in a sketchy ink style with watercolor accents—white body, orange beak and feet, and the orange crab shell hat. Two small motion lines appear near the hat. To the left, handwritten black text reads "Good Things Ahead" with a small underline. To the right, small serif text reads "A Softer World For Silly Creatures" followed by a dash and a small blue heart symbol.

A vertical diptych composition. The top half is a cinematic photograph of a woman in flowing pale gr…

Description

Prompt collected from YouMind; original author wording has not been independently verified. Source is marked reversed by YouMind.

Full prompt

A vertical diptych composition. The top half is a cinematic photograph of a woman in flowing pale green Hanfu and a bamboo hat, seen from behind, reaching up to touch white cherry blossoms on a branch while standing next to a saddled white horse. Soft sunlight filters through the trees with falling petals. The bottom half features a vast expanse of textured beige paper negative space (liubai). In the lower right quadrant, there is a small, delicate illustration or cutout echoing the scene above: the tiny figure of the woman and horse under a branch. Next to this small vignette is vertical Chinese text reading "Spring Equinox" and a poetic couplet about walking with flowers.

GPT Image 2 mixed-media portrait

Full prompt

Use the uploaded reference image as the strict identity and outfit reference. Preserve the face, facial features, skin tone, hairstyle, hair colour, accessories, outfit, and overall vibe exactly as shown. Create a high-quality vertical (4:5 or 9:16) mixed-media portrait featuring: A realistic full-body version of the person. A black hand-drawn doodle-shadow of the same person on the wall beside them. The real person should look cute, slightly embarrassed, playful, and naturally copying a new random mischievous pose each generation. The doodle-shadow should perform the same pose idea in a much more exaggerated, chaotic, cartoonish way, with manga motion lines, stars, hearts, and sparkles. Use a clean white/cream studio wall, minimal background, soft natural lighting, and keep both figures fully visible. The doodle should clearly resemble the real person through hairstyle, accessories, outfit silhouette, and pose. Negative Prompt: outfit changes, identity changes, realistic second person, normal shadow, horror, anime human, cluttered background, repeated pointing or finger-gun poses, stiff pose, extra limbs/fingers, distorted body, text, watermark, logo, AI artifacts.

A vertical split-composition image. The top half is a photorealistic landscape of a flamingo flock i…

Description

Prompt collected from YouMind; original author wording has not been independently verified. Source is marked reversed by YouMind.

Full prompt

A vertical split-composition image. The top half is a photorealistic landscape of a flamingo flock in a salt lake at sunset, with snow-capped mountains in the background and perfect reflections on the water surface. The bottom half features a loose, hand-drawn illustration style with soft pastel color blocks (pinks, blues, oranges) depicting a single flamingo standing in shallow water against a backdrop of stylized mountains and a small sun. Large white space surrounds the subject. Above the illustration, there is handwritten Chinese text: '在温柔的世界里，慢慢发光。' (In a gentle world, glow slowly.) Below that, smaller text reads: '一些美，刚好与心相遇。' (Some beauty just meets the heart).

Goal: Create a vertical editorial poster combining a warm cinematic lifestyle photograph with a torn…

Description

Prompt collected from YouMind; original author wording has not been independently verified. Source is marked reversed by YouMind.

Full prompt

Goal: Create a vertical editorial poster combining a warm cinematic lifestyle photograph with a torn-paper collage aesthetic, centered on {argument name="subject" default="a young woman with short wet black hair reading a red book while lying on a brown sofa"}. Canvas: Vertical 3:4 poster, about 900 x 1200 px. Split the composition horizontally into 2 distinct sections: the top half is a full-bleed realistic photograph, and the bottom half is a cream handmade-paper design with a large torn opening revealing the same photograph underneath. Top section: Show the subject reclining diagonally on a textured brown couch near a window, wearing {argument name="outfit" default="a loose sleeveless sky-blue dress with thin side ties"}. She is lying on red patterned cushions with small floral fabric patches, holding a glossy red book close to her face so it partly hides her mouth and nose. Her expression is quiet and absorbed, eyes visible over the book. Use soft afternoon window light from the upper right, warm shadows, natural film photography grain, intimate indoor atmosphere, slightly high camera angle. Bottom section: Create an aged off-white paper background with subtle fiber texture, stains, deckled edges, and handmade stationery feeling. In the center, make 1 large irregular vertical ripped crack/opening with rough layered paper edges, exposing a cropped duplicate of the woman reading beneath it. Add 4 torn colored-paper fragments around the opening: one red fragment near the top, one muted blue fragment at the upper right, one beige fragment along the lower left edge, and one dark fragment near the lower center. The exposed image should look slightly flatter and more printed, like a magazine photo embedded under torn paper. Text content: Add Japanese editorial typography in thin, elegant Mincho-style characters. On the left side of the bottom paper, large vertical/stacked text reads {argument name="main Japanese copy" default="ページの\n向こうに、\nどこかのわたし。"}. Below it, smaller text reads {argument name="small Japanese copy" default="読んでいるのは、\n物語か、\nそれとも、\n少しだけ未来。"}. On the right side, add a small vertical Japanese note reading {argument name="right Japanese note" default="こんな午後が、\nずっと続けばいい。"}. Keep the text sparse and airy, with generous margins. Decorative details: Include exactly 2 pressed dried flower sprigs: one small reddish flower cluster near the lower center-left of the torn opening, and one longer thin-stem flower sprig near the lower right. Add 3 faint pencil-like curved scribble lines across the paper: one large loose curve on the right, one short underline-like stroke below the left text, and one long sweeping line from the lower left toward the center. No logos, no watermarks, no extra text. Visual style: Japanese magazine cover, poetic paper collage, tactile torn paper, wabi-sabi stationery design, warm nostalgic color grading, realistic photography mixed with handcrafted paper texture, calm literary mood.

Goal: Create a two-panel editorial sports artwork about {argument name="tennis player" default="Roge…

Description

Prompt collected from YouMind; original author wording has not been independently verified. Source is marked reversed by YouMind.

Full prompt

Goal: Create a two-panel editorial sports artwork about {argument name="tennis player" default="Roger Federer"} at Wimbledon, combining a rough painterly match scene with a minimalist poster illustration. Canvas: Wide horizontal 16:9 composition split exactly into 2 equal vertical panels. Left panel is a dense, realistic, rough-brush illustration of a grass-court tennis match; right panel is a clean off-white poster with distressed typography and collage-like tennis illustration. No outer border. Layout: Left panel occupies the left half and shows an action moment from behind the near player, lunging low across a worn green grass court toward the net. The far baseline has 1 opposing player in white preparing to return, with 2 ball kids or officials standing near the back wall. A large scoreboard sits high at center-left behind the court, with a packed audience filling the stands above it. Right panel occupies the right half with lots of negative space: large hand-painted green title at upper center-right, small slogan text at mid-left, a running tennis player illustration across the lower center, and a small vertical text block near the lower right. Left panel subject details: Depict exactly 2 tennis players: 1 foreground player in all-white tennis outfit, white headband, white shoes with small red accents, stretched into a dramatic forehand reach with racket extended; 1 distant opponent in white near the far baseline. Include 1 yellow tennis ball visible near the far player. The court is Wimbledon-style grass with scuffed, patchy texture, white boundary lines, a black net with yellow posts, and dark green walls. Use a crowded stadium background with many tiny spectators in hats and summer clothing. The left panel should feel like a photo transformed into thick oil-paint strokes, with visible palette-knife texture and rough edges. Scoreboard text: Include a black-and-green Rolex-style scoreboard with yellow lettering. It should show the names Marin CILIC and Roger FEDERER, with Federer leading; include readable fragments such as "ROLEX", "Marin CILIC", "Roger FEDERER", "PREVIOUS SETS", "SETS", "GAMES", "POINTS", and small challenge remaining lines, but do not worry about perfect numerical accuracy. Right panel visual style: Minimalist off-white paper background with subtle grain. At the top, write {argument name="headline text" default="Still in Motion"} in large dark forest-green, rough dry-brush, slanted hand-lettering. The illustrated player below should match the foreground player from the left panel, drawn as a low-poly paper collage / torn-paper texture in white, tan, brown, gray, and green, sprinting to the right with a black racket and a small yellow tennis ball floating ahead. Add exactly 3 rough green brush-stroke court marks beneath the player. Right panel text content: Add two small serif text blocks: on the left of the illustrated player, stacked lines reading {argument name="left slogan" default="Same Game A Deeper You"} with a short horizontal rule beneath; near the lower right, stacked lines reading {argument name="right slogan" default="TENNIS LIVES DIFFERENTLY HERE."} with a short horizontal rule beneath. Color and mood: Wimbledon greens, white clothing, sunlit grass, dark scoreboard, warm crowd tones, and an elegant vintage sports-magazine mood. The overall finish should be rough, textured, slightly imperfect, artistic, and editorial rather than glossy. Constraints: Use exactly 2 panels, exactly 2 tennis players, exactly 1 visible tennis ball in the left panel, exactly 1 visible tennis ball in the right panel, exactly 1 large scoreboard, exactly 3 green brush-stroke court marks in the right panel. Avoid logos other than the scoreboard-style Rolex reference, avoid watermarks, and keep the right panel spacious and uncluttered.

Goal: Create a two-panel horizontal comparison image showing a real-life nature photo transformed in…

Description

Prompt collected from YouMind; original author wording has not been independently verified. Source is marked reversed by YouMind.

Full prompt

Goal: Create a two-panel horizontal comparison image showing a real-life nature photo transformed into a minimalist needle-felt illustration. Canvas: Wide 16:9 canvas split vertically into two equal halves with a clean straight division down the center. Left panel: A realistic golden-hour forest meadow photograph. Show exactly 5 deer in the foreground: 1 deer walking at far left, 1 deer grazing left-center, 1 deer grazing center, 1 small deer standing upright center-right, and 1 larger deer standing at far right. The meadow is covered in dewy green grass, with warm yellow sunlight and soft morning mist. In the background, dark evergreen trees form a dense forest silhouette, with additional leafy branches at the upper right. Strong sunbeams stream diagonally through the trees from the upper right, creating a serene cinematic atmosphere. Right panel: A soft handmade needle-felt wool reinterpretation of the same scene on a warm off-white textured paper background with generous blank space. Center the felt scene horizontally in the upper-middle area. Show exactly 5 small felt deer matching the left panel arrangement: 1 standing deer at far left, 1 grazing deer left-center, 1 orange-brown grazing deer center, 1 small upright deer center-right, and 1 larger standing deer at far right. Place them on a thin strip of fuzzy pale green felt grass. Above them, include a simple round felt sun and 2 soft horizontal felt cloud wisps. Under the felt grass, add handwritten text reading {argument name="caption text" default="A kinder morning ♡"} in a delicate gray-brown script. Visual style: Combine warm healing aesthetics, generous white space, cozy wool-felt texture, soft edges, muted earthy colors, and a calm poetic mood. The left side should look photographic and atmospheric; the right side should look like a handcrafted felt illustration with visible fibers and a minimal composition. Constraints: Keep the split-screen layout, exactly 5 deer on each side, no extra animals, no border, no watermark, no additional text beyond the caption.

Goal: Create a calm aesthetic diptych wallpaper comparing the same seascape in two visual languages:…

Description

Prompt collected from YouMind; original author wording has not been independently verified. Source is marked reversed by YouMind.

Full prompt

Goal: Create a calm aesthetic diptych wallpaper comparing the same seascape in two visual languages: realistic ocean photography on the left and minimalist charcoal-and-red ink illustration on the right. Canvas: Wide horizontal 16:9 composition, split exactly into 2 equal vertical panels with a sharp center divide and no outer border. Left panel: A realistic telephoto photograph of {argument name="seascape subject" default="deep blue ocean waves with a pale full moon half-rising on the horizon"}. Use layered rolling waves in the foreground, white sea foam, a dark horizon line slightly above center, and a muted blue sky. The moon is a single pale cream disk, partially hidden behind the horizon, centered slightly right within the left panel. Color palette: teal blue, cyan, deep navy, white foam, soft cream moon. Mood: quiet, early morning, still and contemplative. Right panel: Warm off-white textured paper background with a small minimalist charcoal drawing positioned slightly right of center and slightly below mid-height. The drawing contains exactly 3 main visual elements: 1 red semicircle sun, 1 thin black horizon band, and 1 group of rough black wave strokes beneath it with sparse red accents. The illustration should feel hand-drawn with dry brush, charcoal pencil, and ink scratches, leaving large negative space. Text content: Add exactly 1 small italic serif caption beneath and left of the illustration reading “{argument name="caption text" default="same sea\ndifferent light"}” in dark gray or black, split across 2 lines. Add exactly 1 short thin red underline below the caption. Style: Quiet editorial art print, red-and-black charcoal aesthetic, subtle paper grain, poetic minimalism, balanced asymmetry, muted colors, no people, no boats, no extra text, no watermark.

Create a refined editorial travel-art composition based on a reference photograph. The image is divi…

Description

Prompt collected from YouMind; original author wording has not been independently verified.

Full prompt

Create a refined editorial travel-art composition based on a reference photograph. The image is divided vertically into two parts: the upper section is a realistic cinematic travel photograph, while the lower section transforms the exact same scene into a delicate hand-painted watercolor illustration. Upper section: authentic candid travel photography, natural daylight, soft shadows, subtle film grain, realistic textures, sophisticated European atmosphere, documentary-style composition, people naturally walking through the scene, beautiful architectural details, slightly muted elegant colors, high-end travel magazine photography. Lower section: a {argument name="art style" default="minimalist handmade watercolor painting"} of the exact same scene, preserving the recognizable composition, architecture, people, poses, perspective and major visual elements from the photograph. Loose translucent watercolor washes, delicate ink details, visible paper texture, soft edges, imperfect brushwork, subtle pigment bleeding, airy negative space, understated pastel tones, artistic but realistic. Leave generous warm {argument name="background texture" default="ivory/off-white textured paper"} space surrounding the watercolor illustration. Add a small elegant handwritten caption near the bottom, such as {argument name="caption" default="“summer days”"} or “a quiet afternoon”, with a thin minimalist horizontal line underneath. Overall aesthetic: luxury travel journal, fine-art watercolor postcard, contemporary editorial design, nostalgic European summer, understated elegance, tactile handmade paper, sophisticated and serene. Portrait orientation, clean composition, premium art direction, no clutter, no borders, natural proportions, highly detailed photograph transitioning into an airy watercolor illustration.

Create a refined, high-end PHOTO + MINIMAL WATERCOLOR VIGNETTE artwork based entirely on the uploade…

Description

Prompt collected from YouMind; original author wording has not been independently verified.

Full prompt

Create a refined, high-end PHOTO + MINIMAL WATERCOLOR VIGNETTE artwork based entirely on the uploaded photograph. Use the photograph as the only visual reference and preserve the exact subject, composition, environment, clothing, objects, lighting, colors, and mood. FORMAT: Vertical {argument name="aspect ratio" default="3:4"} editorial composition. TOP SECTION — ORIGINAL PHOTOGRAPH: Place the original photograph in the upper 55–60% of the canvas. Keep it photorealistic and naturally detailed. Do not alter the identity, pose, proportions, objects, architecture, scenery, or important visual details. Give it a subtle premium editorial photography finish with natural cinematic light and gentle tonal balance. BOTTOM SECTION — HAND-PAINTED INTERPRETATION: Transform the same exact scene into a delicate minimal watercolor and fine-ink illustration. Recreate the main subject, pose, perspective, key objects, and recognizable background elements from the photograph. Use loose watercolor washes, subtle pencil/ink outlines, imperfect hand-painted edges, soft paper texture, and restrained pastel tones. Keep the illustration airy, elegant, and slightly imperfect rather than digitally polished. The illustration should feel like a fashion/lifestyle magazine sketchbook page, with plenty of clean negative space and a warm off-white textured paper background. Do not introduce new subjects or details. TYPOGRAPHY: Add a short elegant handwritten brush-script phrase underneath or integrated naturally into the illustrated section, similar to a premium lifestyle editorial poster. Underneath it, add a tiny minimalist lowercase serif/sans-serif subtitle. Typography should be subtle, sophisticated, thin, and balanced with the artwork. AESTHETIC: Scandinavian editorial design, quiet luxury, nostalgic travel journal, soft watercolor, delicate ink drawing, handmade paper texture, muted natural palette, sophisticated minimalism, emotional storytelling, premium art-book layout. IMPORTANT: The photograph and illustration must clearly represent the same exact moment and scene. No collage of unrelated images, no dramatic redesign, no excessive watercolor, no cartoon appearance, no heavy outlines, no saturated colors, no clutter. Output: photorealistic upper section + matching delicate watercolor illustration below, seamless premium editorial composition, vertical {argument name="aspect ratio" default="3:4"}, high detail. For different photos, just change the text phrase Examples: •{argument name="phrase" default="Good Days — a kinder me"}

“using this json as reference, generate a person holding my product [attach product image]” > GPT-Im…

Description

Prompt collected from YouMind; original author wording has not been independently verified.

Full prompt

“using this json as reference, generate a person holding my product [attach product image]” > GPT-Image 2.5 generates the photo with that person holding your product compare it with a version generated without the reference and look at the difference in the lighting and color grading > save the generated character photo you’re happy with as your reference > for future generations, attach the character photo each time and ask it to preserve the same facial features now you have a reference character you can use across multiple product photos you can also iterate the base json prompt and chat back and forth with GPT-6 Astra based on what you want, then repeat the same process.. i like this because it gives you much more direction over the color grading instead of leaving everything up to the model the basic colours and grainy look are some of the things that can make an image feel AI-generated, so pay attention to those when comparing your results this is how you can start building a library of high quality ugc images around your own products the json gives GPT-Image 2.5 the lighting and color direction, your character reference helps with consistency, and you control the product placement once you have that starting point, you can keep creating variations without writing everything from scratch GPT-Image 2.5 Sunburst & Flare are available on Higgsfield. try this with your own product and reference images there

Goal: Create a vertical smartphone screenshot-style composition showing an AI image generation conve…

Description

Prompt collected from YouMind; original author wording has not been independently verified. Source is marked reversed by YouMind.

Full prompt

Goal: Create a vertical smartphone screenshot-style composition showing an AI image generation conversation and its generated anime music-video storyboard result. Canvas: Tall portrait mobile screen, approximately 9:16, white background, clean social-chat interface look, with a thin gray scroll indicator on the far right edge and small bottom UI icons. Top subject area: In the upper right, place exactly 2 small full-body anime characters standing together: 1 tall purple-haired schoolgirl and 1 tiny pink-haired mascot girl. The schoolgirl has short spiky lavender-purple hair, red eyes, gold round earrings, a white sailor school uniform with orange collar and orange necktie, orange pleated skirt, white knee socks, and brown loafers. The mascot girl is much shorter, pink-haired with blue eyes, wearing a simple white bodysuit with a tiny red bow and two small antenna-like hair accessories with gold tips; she waves cheerfully. Chat bubble: Under the characters, centered slightly right, draw one large rounded light-gray message bubble containing Japanese text in black. Use the exact visible message: {argument name="chat bubble text" default="このキャラクターのボカロmv\nの様々なカットを3x3で出力\nして。16:9"}. Keep the text large, simple, and aligned like a phone chat message. Generated result card: Below the chat bubble, create one rounded-corner 16:9 image card containing a 3x3 grid, exactly 9 cinematic anime music-video frames. The grid has thin white dividers and soft rounded outer corners. Grid frame count and contents, left to right, top to bottom: 1) close-up of the purple-haired schoolgirl leaning on her arms beside a window with melancholic expression, warm sunset light, small handwritten Japanese lyric text. 2) wide sunset rooftop or city overlook, purple-haired girl standing while the tiny pink mascot is nearby, orange-pink sky, lyric text. 3) close-up of the pink mascot reaching both hands toward the viewer, bright sakura-like pink background, happy expression. 4) concert stage shot of the purple-haired girl singing into a microphone, neon blue and magenta lights, one hand extended toward viewer, lyric text. 5) airy white-blue scene with both characters floating or jumping together among papers or light fragments, minimal lyric text. 6) dramatic side-profile close-up of the purple-haired girl against blue-violet lighting and glowing highlights. 7) cozy overhead or close shot of both characters lying together happily amid warm pastel clutter, smiling with eyes closed. 8) back view of both characters sitting under a starry night sky and Milky Way, quiet city silhouette, lyric text. 9) cheerful close-up of both characters posing together with peace signs, pastel blue background, small lyric text. Visual style: Polished Japanese anime, cute late-2000s slice-of-life character design, soft cel shading, expressive eyes, saturated music-video color grading, gentle bloom, clean line art, varied camera angles, nostalgic Vocaloid MV mood. Use {argument name="main character hair color" default="lavender purple"} for the schoolgirl and {argument name="mascot hair color" default="pink"} for the tiny mascot. The main school uniform accent color is {argument name="uniform accent color" default="orange"}. The overall generated storyboard mood is {argument name="music video mood" default="bittersweet, nostalgic, and uplifting"}. Interface details: Around the generated image card, leave generous white margins like a mobile app screenshot. Add a small share icon near the lower left, a three-dot menu near the bottom, and a translucent circular upload/share overlay button near the lower right of the 3x3 grid. Do not add extra characters beyond the 2 main characters. Do not add extra grid panels beyond exactly 9.

Goal: Create a single square character reference sheet showing {argument name="character name" defau…

Description

Prompt collected from YouMind; original author wording has not been independently verified. Source is marked reversed by YouMind.

Full prompt

Goal: Create a single square character reference sheet showing {argument name="character name" default="MiniMax H3"} as a chibi anime girl in 16 different dance poses, arranged like a numbered pose grid. Canvas: Square 1:1 image, off-white paper background, divided into an exact 4 by 4 grid with thin dark brown lines. Each panel is clean and uncluttered, with one full-body chibi character centered in the panel. Add small dark red panel numbers 1 through 16 in the top-left corner of each cell. Character design: The same cute chibi girl appears in all 16 panels: large head, small body, peach-blonde bob haircut with blunt bangs, one long curved ahoge strand looping above the head, purple eyes, rosy cheeks, small mischievous smile. Add a decorative dark brown flower-and-gear hair ornament on the viewer’s right side of her hair and a small circular gear clip near the bangs. Outfit: oversized {argument name="hoodie color" default="warm brown"} hoodie with long sleeves and a pale emblem printed on the chest, black choker, layered brown plaid pleated skirt with a tied plaid shirt or sash around the waist, black knee-high socks, chunky black loafers. Use consistent colors and proportions across all panels. Visual style: polished kawaii chibi illustration, clean thick brown line art, soft cel shading, warm muted brown palette, expressive anime face, subtle pink oval shadow under the feet in most panels. Add simple motion lines, sparkles, flowers, hearts, or bubbles where appropriate, but keep the background blank. Layout and exact 16 panel contents: 1. Wide-legged energetic stance, one fist raised forward, determined expression. 2. Loose zombie-like sway, both arms drooping outward, sleepy half-lidded face. 3. One knee lifted, one arm raised overhead, small motion lines around the body. 4. Body tilted dramatically sideways with one leg crossed behind, arms bent above and across the head. 5. Graceful dance step with eyes closed, arms extended softly, two small flower doodles. 6. Low squat pose, hands held near cheeks like paws, confused expression with one question mark. 7. Back-facing spin pose, head turned slightly, one arm extended forward, skirt flaring. 8. One-leg cute pose, both arms overhead forming a rounded shape, winking, small star doodles. 9. Deep side lunge with one hand on the floor and one arm arched high, sly face. 10. One knee lifted, eyes closed, both hands forming small horns or a crown shape above the head, tiny accent marks. 11. Confident wide stance, both hands pointing outward like finger guns, sparkles nearby. 12. Sleepy backward lean, eyes closed, arms hanging loosely, bubbles and motion arcs. 13. Shy over-the-shoulder pose, one hand near mouth, hip turned, small heart doodle. 14. Crawling or low all-fours pose, one leg lifted slightly, playful sideways gaze, motion marks. 15. Joyful midair jump with both arms spread wide, smiling with closed eyes, flower doodles and motion lines. 16. Sassy finishing pose, one hand making a V sign near one eye, the other hand on hip, one eye winking, sparkles around her. Constraints: Use exactly 16 panels and exactly one character per panel. Keep the grid numbering visible and sequential from 1 to 16. Maintain the same outfit, hairstyle, hair accessories, and color palette in every pose. No extra text besides the panel numbers and optional simple symbols like the question mark.

Using the provided reference image, create a coherent multi-view scene reconstruction with the same …

Description

Prompt collected from YouMind; original author wording has not been independently verified. Source is marked reversed by YouMind.

Full prompt

Using the provided reference image, create a coherent multi-view scene reconstruction with the same person and retail warehouse environment. Generate a {argument name="aspect ratio" default="16:9"} image divided into an exact {argument name="grid layout" default="3x3"} contact sheet. In all 9 panels, keep the subject’s identity, clothing, sunglasses, display table, and store setting consistent, but redraw the surrounding scene from varied camera angles and distances so the person’s standing position and environment remain spatially plausible. Required 9 views: 1. Front-facing medium view from across the sunglasses table. 2. Rear view showing the subject’s back and the table ahead. 3. Right-side profile view beside the display. 4. Left-side profile view from closer to the table. 5. Three-quarter front view similar to the reference. 6. Three-quarter front/right view with shelves behind. 7. Rear-left view looking over the table. 8. Rear three-quarter view with the subject centered near the display. 9. Wide elevated view showing the full sunglasses table, subject, and surrounding warehouse aisles. Use {argument name="model or style note" default="GPT-image-2.5 Sunburst"} style photorealistic synthesis. Emphasize front, back, left, and right views as mandatory. Do not add captions, speech bubbles, borders beyond the clean white grid dividers, or any extra people.

Using the provided reference image as the base scene, regenerate it as a more polished hyperrealisti…

Description

Prompt collected from YouMind; original author wording has not been independently verified. Source is marked reversed by YouMind.

Full prompt

Using the provided reference image as the base scene, regenerate it as a more polished hyperrealistic editorial photograph while preserving the same retrofuturistic Paris watchmaker workshop, rainy evening mood, young short-haired watchmaker, brass desk lamp, clock-filled interior, small brass robot assistant, wet shop-window reflections, and French storefront identity. Transformation: Recompose the scene from a slightly wider, lower, front-window viewpoint, as if looking through rain-streaked glass from just outside the shop. Shift the watchmaker to the lower-right/center, make her hands and the watch mechanism the focal point, and place the robot assistant on the lower-left side of the workbench reaching toward the repair area. Increase the sense of depth by showing more of the Paris street on the left through the window, including exactly 1 cyclist holding an umbrella, wet cobblestones, warm café lights, and blurred car tail lights. Text and signage: Keep the main storefront text legible and centered high on the glass: {argument name="shop name" default="L’ATELIER DU TEMPS"}. Keep the subtitle below it: {argument name="subtitle text" default="Réparations depuis 1927"}. Move the open sign so it hangs beneath the subtitle inside the window, reading {argument name="open sign text" default="OUVERT"}. Interior additions and layout: Add more antique wall clocks and shelves in the background, emphasizing a dense old-world horology workshop. Include exactly 5 prominent clock faces visible in the interior: 1 large round wall clock, 1 medium round wall clock, 1 small round wall clock, 1 rectangular mantle clock, and 1 tall cabinet clock. Keep the sleeping orange cat on the right-side shelf. On the workbench, show exactly 4 small watchmaking tools lined up near the watch mechanism, plus an open sketchbook on the right and a chipped white coffee cup at the far right. Style: Hyperrealistic 4K editorial photography, vertical {argument name="aspect ratio" default="4:5"}, cinematic warm interior light contrasted with cool blue rainy exterior, detailed water droplets on glass, soft bokeh, realistic reflections, shallow depth of field, retrofuturistic brass-and-wood materials, no extra people inside, no logos or watermarks.

Create a premium editorial art poster for every uploaded photograph, treating each image as its own …

Description

Prompt collected from YouMind; original author wording has not been independently verified.

Full prompt

Create a premium editorial art poster for every uploaded photograph, treating each image as its own independent composition and never merging multiple photos together. Use a strict {argument name="aspect ratio" default="3:4"} vertical format with the canvas split into two perfectly equal horizontal halves: the upper half should remain a faithful, photorealistic presentation of the original image, preserving the subject’s exact identity, facial features, proportions, pose, clothing, objects, composition, lighting, shadows, mood, and natural colors, enhanced only with sophisticated editorial color grading and seamless environmental extension where necessary; the lower half should transform the visual story into an entirely different artistic interpretation—a tiny, carefully composed {argument name="style" default="handmade mixed-media"} artwork centered within expansive {argument name="background" default="warm ivory"} negative space, occupying no more than 10–20% of the lower section, using expressive ink sketching, layered gouache-like color fields, subtle collage textures, torn-paper edges, imperfect brushwork, visible fibers, soft pigment variations, and charming human imperfections while retaining the most recognizable silhouette, gesture, objects, and emotional narrative from the original photo. Extract up to four dominant harmonious colors from each photograph and reinterpret them in a muted, sophisticated palette. Add only occasional understated editorial typography when it genuinely enhances the composition, such as a poetic title, place, date, or single word. The overall result should feel like a collectible contemporary art publication cover—minimal, poetic, tactile, elegant, emotionally quiet, visually distinctive, and unmistakably connected to its original photograph.