AI Prompt Library

Soft {argument name="painting style" default="semi-realistic digital painting"} blended with highly detailed engraving illustration style, combining painterly softness with ultra-fine crosshatching and dotting techniques. Cinematic warm lighting with a strong golden-orange glow illuminating one side of the subject, contrasted by soft cool shadows, enhanced by dramatic chiaroscuro. Skin and textures are rendered through a fusion of smooth luminous digital shading and dense layered engraving lines, creating a balance between soft gradients and intricate linework. Subtle glossy highlights and reflective surfaces are preserved, especially in the eyes, giving a luminous and lifelike appearance. Delicate painterly blending remains visible through soft brush strokes, seamlessly integrated with precise contour lines and micro-detail etching, forming rich textures built from thousands of fine strokes. Edges transition naturally—sharp and clean in focal areas while dissolving into loose sketch-like strokes in unfinished regions. The top of the head and lower body fade into an incomplete sketch effect with soft, disappearing lines and partially dissolved forms blending into the background. Background uses a {argument name="background material" default="textured brown cardboard"} surface with visible matte grain and slightly rough tactile quality, subtly merged with a dark, studio-like atmospheric depth. The composition is minimalistic and elegant, with a calm yet dramatic mood. Color grading leans toward warm, natural tones with a slightly muted and faded palette, maintaining harmony between digital painting warmth and classic engraving aesthetics. High contrast lighting with deep blacks and controlled highlights enhances depth, while maintaining soft transitions in key areas. Ultra-high detail, macro texture emphasis, cinematic shadow depth, museum-quality finish, handcrafted engraving feel, 8K resolution. Ar 9:16!

Highly stylized {argument name="style" default="monochrome fashion illustration"}, expressive {argument name="technique" default="black-and-white ink portrait style"}, ultra-clean grayscale palette with soft tonal shading and sharp dark accents, elegant feminine facial construction, elongated proportions, minimalistic luxury editorial aesthetic. Use flowing organic contour lines mixed with geometric construction lines crossing the face naturally. Combine loose gestural strokes with precise ink detailing around the eyes, eyebrows, lips, and hair strands. Hair rendered with sweeping fluid brush lines and layered ink curves, creating dynamic movement and asymmetrical framing. Skin shading uses smooth cel-shaded grayscale planes with subtle gradient transitions, while maintaining a hand-drawn ink illustration appearance. Thin sketch lines remain visible as part of the composition. Eyes highly detailed and luminous with crisp eyelashes and reflective highlights. Lips softly sculpted with semi-realistic shading and delicate line texture. Use selective contrast: bold black strokes around facial features balanced against large clean white negative spaces. Overall composition resembles a fusion of modern fashion sketch, manga-inspired editorial art, and minimalist ink wash illustration. {argument name="background" default="Background kept plain light gray or off-white"} with uncluttered negative space. High contrast, elegant, refined, cinematic, expressive line-art aesthetic.

[Game Campaign] - Game Title: {argument name="game title" default="Treasure Hunt!"} - Game Overview/Features: {argument name="description" default="Find treasures on a great adventure island!"} - Genre/Subtext: {argument name="subtext" default="RPG Adventure Action!"} [Quality, Production, Composition] - Style: Illustration for event announcements for Japanese mobile RPGs or casual games. A colorful and joyful fantasy world. - Subject: Adorable chibi characters (deformed heroes or mascots) opening a treasure chest with smiles. Golden light and magical particles are overflowing dazzlingly from the chest. - Background: Blue sky, white clouds, and islands or forests in a lush fantasy world. - Typography (for GPT-image / Nano Banana Pro): A fantasy-style decorative logotype of {argument name="game title" default="Treasure Hunt!"} is designed in the center or top of the screen, with {argument name="description" default="Find treasures on a great adventure island!"} and {argument name="subtext" default="RPG Adventure Action!"} added in an easy-to-read layout. - Color/Lighting: Bright, high-saturation fantasy colors, magical gloss, and soft shadow depiction. [Strict Layout and Output Constraints (Required)] - Output the finished design itself, filling the entire screen. Backgrounds and scene descriptions (walls, spaces, shadows, etc.) within the design may follow the instructions in the main text. - Prohibitions: Photos of the finished poster in a frame, photos pinned to a wall, mockup photos placed on a desk or paper, perspective distortion of paper edges, or drop shadows. - Output the finished flat 2D design itself, filling the entire canvas. Scene elements inside the design (walls, rooms, shadows) described above are allowed. Absolutely NO photo-of-a-poster mockups: no picture frames, no poster-on-wall or poster-on-desk shots, no perspective warp or drop shadow around the artwork's edges. - Aspect Ratio: --ar 16:9

Editorial fashion photograph of a young man with {argument name="hair style" default="tousled dark wavy hair"}, tan olive skin, defined jawline, short stubble beard and mustache, thick dark eyebrows, brown eyes, wearing dark sunglasses pushed slightly down. He wears a {argument name="shirt color" default="maroon"} short-sleeve polo shirt tucked into wide-leg cream/off-white trousers with a brown braided leather belt, and brown tassel loafers. He stands in profile, leaning forward with one hand resting on the seat of a wooden bar stool, head tilted downward. Plain soft neutral gray studio background, soft even studio lighting, minimalist high-end fashion campaign aesthetic, shot on medium format camera, shallow depth of field, clean commercial look.

Ultra-detailed blue ballpoint pen illustration translated into monochrome black ink, dense cross-hatching and fine hatch shading, intricate biro sketch texture, obsessive linework, engraved contour rendering, hand-drawn pen illustration aesthetic, expressive organic strokes, editorial surreal composition, high-detail facial rendering, layered sketchbook construction lines, vintage technical scribbles and handwritten notes in pure white only over {argument name="background color" default="bold red background"}, white typographic annotations integrated into backdrop, underground zine poster aesthetic, raw imperfect ink marks, high-contrast black ink subject against vivid red field, experimental graphic design, avant-garde magazine cover style --ar 9:16 --stylize 750.

Transform the reference photograph into a delicate {argument name="style" default="hand-drawn travel journal illustration"} while preserving the original composition, architecture, people, trees, grass, road, and overall perspective. Use a traditional colored-pencil and watercolor sketch aesthetic on warm, slightly aged cream paper. Keep the buildings recognizable but simplify them into expressive hand-drawn shapes, with visible pencil strokes, loose watercolor washes, subtle paper grain, imperfect outlines, and gentle cross-hatching. Preserve the peaceful {argument name="atmosphere" default="rainy-day"} atmosphere, soft overcast sky, warm beige and muted buildings, fresh green lawn, scattered people walking with umbrellas, wet pavement, trees, benches, puddles, and distant cars. Use a muted vintage travel-sketch palette with natural imperfections and understated colors. Place the illustration in the lower portion of the page with generous cream-colored negative space around it. Add elegant handwritten typography above: ‘{argument name="heading" default="Rainy Days"}’, and below: — Quiet moments —. Minimal, nostalgic, artistic travel magazine aesthetic, analog photography transformed into a personal sketchbook memory, sophisticated and authentic, no photorealism.

Create an ultra-detailed dark fantasy gothic illustration of {argument name="character name" default="an undead vampire king"} enthroned inside a ruined cathedral throne room. The central figure is a pale, corpse-like monarch with long flowing {argument name="hair color" default="white hair"}, glowing red eyes, blood running from the mouth, and a jagged black crown. He wears ornate blackened armor covered in skulls, spikes, chains, red jewels, and torn crimson-black royal robes. He sits arrogantly on a skull-encrusted stone throne, one hand resting on the armrest and the other gripping a long ceremonial sword with a skull pommel, gothic crossguard, red gem, and pale blade. Surround him with exactly 9 clearly visible supernatural figures or creatures: 1 large translucent ghostly warrior hovering behind him with a sword, 1 smaller floating ghost near the moonlit archway, 4 misty human spirits on the stairs and balcony in the midground, 2 armored spectral soldiers at the lower right holding weapons, and 1 snarling ghost wolf in the lower left foreground. Set the scene in a vast black stone cathedral with broken pointed arches, towering columns, candles, chains, cracked steps, skulls, and tattered red banners. Include exactly 3 readable banner or stone inscriptions: left hanging banner says {argument name="left banner text" default="BLOOD BEYOND DEATH"}, right hanging banner says {argument name="right banner text" default="KINGS DIE BUT LEGENDS HAUNT FOREVER"}, and the stone block near the lower left says {argument name="stone inscription" default="SWORDS REMEMBER WHAT MEN FORGET"}. Through the huge archway, show a distant spired gothic castle, an arched bridge, flying bats, storm clouds, cold mist, and a huge crimson blood moon. Use cinematic low-angle composition, hyperreal digital painting, intricate concept-art detail, cold blue-gray fog contrasted with deep crimson accents, dramatic moonlight, candle glow, volumetric mist, sharp armor highlights, macabre regal atmosphere, no modern objects, no cartoon style.

{ "title": "The Last Train Home", "image_description": "A breathtaking cinematic scene at an {argument name=\"location\" default=\"abandoned train station lost in the mountains\"}. Thick fog rolls across the empty platform. Vintage lamps cast warm golden light through the mist. A lone traveler wearing a dark wool coat stands beside an old leather suitcase. An ancient train slowly emerges from the fog. Every window glows softly. Snow falls silently around the station. Above the platform hangs a weathered sign that reads: HOME. The traveler's eyes fill with emotion as he realizes the train should not exist.", "story_element": { "twist": "The train only appears once, exactly one hour before a person dies." }, "environment": { "location": "Forgotten mountain railway station", "weather": "Snowfall and dense fog", "time": "Midnight" }, "cinematography": { "shot_type": "Wide cinematic shot", "camera": "ARRI Alexa 65", "lens": "50mm anamorphic", "composition": "Symmetrical storytelling frame" }, "lighting": { "type": "Warm vintage lamps mixed with cold moonlight", "effects": [ "Volumetric fog", "Snow particles", "Atmospheric glow" ] }, "mood": [ "Emotional", "Mysterious", "Bittersweet", "Nostalgic" ], "quality": { "style": "Award-winning cinematic masterpiece", "realism": "Ultra photorealistic", "resolution": "8K", "IMAX_quality": true, "film_grain": true } }

{ "title": "The Museum of Lost Tomorrows", "image_description": "A vast {argument name=\"location\" default=\"underground museum hidden beneath a forgotten city\"}. The architecture is breathtaking, with endless marble hallways illuminated by warm golden light filtering through giant glass ceilings. Thousands of glass display cases stretch endlessly into the distance. Inside each case is a future that never happened. One contains a wedding dress that was never worn. Another holds a Nobel Prize medal that was never earned. Another displays a dusty guitar beside a sold-out world tour poster from a musician who gave up too soon. Visitors walk silently through the museum, staring at the exhibits with tears in their eyes.", "main_subject": { "character": "A young man standing alone", "appearance": "Dark overcoat, slightly worn shoes, tired eyes", "expression": "Shocked and emotional", "focus": "Sharp focus" }, "story_element": { "twist": "At the end of the museum, he discovers an entire room dedicated to his own abandoned dreams.", "question": "What would you do if you could see the life you almost lived?" }, "environment": { "location": "Underground Museum", "lighting": "Golden cinematic lighting", "atmosphere": "Silent, emotional, sacred" }, "cinematography": { "camera": "ARRI Alexa 65", "lens": "50mm anamorphic", "shot_type": "Wide cinematic shot", "depth_of_field": "Shallow", "composition": "Award-winning storytelling frame" }, "mood": [ "Heartbreaking", "Thought-provoking", "Melancholic", "Beautiful" ], "style": { "reference": "Christopher Nolan meets Denis Villeneuve", "quality": "Ultra photorealistic", "resolution": "8K", "film_grain": true, "volumetric_lighting": true } }

Goal: Create a whimsical two-part aesthetic poster about a cute cloud character, combining a real-sky photo scene on top with a hand-drawn scrapbook guide below. Canvas: Vertical 3:4 poster. The top half is a realistic outdoor sky photograph; the bottom half is a cream paper illustration panel with a soft grainy texture. Top scene: A bright blue daytime sky with a few small white clouds. In the center, one fluffy white cloud is turned into a friendly character using simple black graphic features: exactly 2 dot eyes, 1 curved smiling mouth, and 2 raised bone-like arms angled upward from the left and right sides. The mood is light, airy, relaxed, and childlike. Use natural sunlight and keep the sky spacious. Bottom panel title: Handwritten title centered near the top: {argument name="title text" default="Cloud Friend"}. Add a small blue star to the left, a red heart to the right, tiny blue sparkles, and a wavy blue underline beneath the title. Bottom layout: Arrange exactly 9 small illustrated vignettes in a loose 3-by-3 grid, each with a handwritten numbered caption underneath. The style should look like colored pencil, crayon, and ink on warm off-white paper. Nine vignettes and captions: 1. “hello!” — a small smiling cloud character inside a rough blue scribble patch, with two black arms and a tiny red heart. 2. “happy face” — a simple face made of 2 black dot eyes, 1 black smile, and 2 soft pink blush circles. 3. “arms up” — two separate black bone-like arms raised like a cheering gesture, with small blue motion marks and a red doodle accent. 4. “very blue” — a rounded rectangle of textured blue crayon sky containing exactly 2 small white clouds. 5. “soft & fluffy” — a pale gray pencil sketch of one fluffy cloud outline, with a small red heart. 6. “warm sun” — a yellow-orange circular sun with short radiating rays. 7. “gentle breeze” — light blue flowing wind lines with a small swirl and red doodle accent. 8. “daydream view” — a tiny simple landscape with exactly 2 green trees, a green ground line, and a small red-roof house outline. 9. “good mood” — a cheerful doodle cluster containing 1 blue star, 1 pink heart, 1 mint green cloud, small dots, and red accent lines. Footer text: Centered along the bottom in small handwritten lettering: {argument name="footer quote" default="Look up. Little joys are floating around."} followed by a small red heart and blue dots. Visual style: Mix realistic photography in the top half with naive hand-drawn journaling in the bottom half. Use soft blue, cream, black, pastel pink, yellow, mint, and red accents. Keep all text handwritten, imperfect, casual, and charming. Constraints: Preserve the exact two-panel composition, the exact count of 9 numbered vignettes, and the friendly minimalist cloud face. Avoid extra characters, logos, watermarks, or dense text.

Research the poster regulations for presentation at the {argument name="conference name" default="2026 Neuroscience Conference"} and transform the attached paper into a poster accordingly.

Premium technical infographic of {argument name="product" default="[Apple 18 pro ]"}. Use the reference image only to understand the shape and structure of the object, without copying the same photo, angle, composition, or background. Reinterpret the subject in a new professional and realistic photograph, clean and well-lit, with a suitable and more aesthetic background. Keep the object as a real photo, not an illustration. Add a technical blueprint-style overlay with white lines, arrows, dimensions, labels, and small diagrams of parts, materials, measurements, and functionality. Clear, elegant, and informative composition. Include a sketch box in the upper left corner with the title "{argument name="title" default="[Apple 18 pro]"}

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.

[Poster Information] - Main Title: {argument name="title" default="Creative Night."} - Event/ZINE Theme: {argument name="theme" default="Live & DJ ZINE & ART"} - Date/Other Info: {argument name="date" default="2026.11.15"} [Image Quality/Direction/Composition] - Style: Analog texture, DIY culture, punk ZINE or indie label poster art style. - Visual Effects: Multi-layered graphic design featuring a collage of hand-torn paper, newspaper clippings, monochrome halftone photos, hand-drawn graffiti, and spray art. - Color Tone: Primarily monochrome with 1-2 accent colors like neon pink, acid yellow, or fluorescent green, creating high contrast. - Typography (for GPT-image / Nano Banana Pro): The title {argument name="title" default="Creative Night."} is powerfully placed in the center using rough, distorted handwriting or stencil fonts, while the {argument name="theme" default="Live & DJ ZINE & ART"} and {argument name="date" default="2026.11.15"} are pasted as part of the collage on the edges. [Strict Layout Constraints (Required)] - Output the finished flat 2D design itself, filling the entire canvas. Scene elements inside the design (walls, rooms, shadows) described above are allowed. Absolutely NO photo-of-a-poster mockups: no picture frames, no poster-on-wall or poster-on-desk shots, no perspective warp or drop shadow around the artwork's edges. - Aspect Ratio: --ar 3:4

[Ad Message] - Main Copy: {argument name="headline" default="Our Workplace"} - Sub-copy: {argument name="subtext" default="Creating the future together with BtoB partners."} - Company Name/Logo: {argument name="company" default="Future Lab Inc."} [Image Quality/Direction/Composition] - Style: Minimalist and intelligent Japanese corporate visual, like those in major newspapers or on the back covers of economic magazines. - Visual Elements: Futuristic city skyline (glass and steel architecture), clear early morning light, or abstract clean light lines, representing trust and innovation simultaneously. - Layout & Typography (for GPT-image / Nano Banana Pro): In the wide negative space (top or bottom), the headline {argument name="headline" default="Our Workplace"}, the sub-copy {argument name="subtext" default="Creating the future together with BtoB partners."}, and the company name {argument name="company" default="Future Lab Inc."} are orderly arranged in a refined Gothic or beautiful font. - Color/Lighting: A refreshing and reliable color palette based on blue and white, with beautiful lighting contrasts and no excessive decoration. [Strict Layout Constraints (Required)] - Output the finished flat 2D design itself, filling the entire canvas. Scene elements inside the design (walls, rooms, shadows) described above are allowed. Absolutely NO photo-of-a-poster mockups: no picture frames, no poster-on-wall or poster-on-desk shots, no perspective warp or drop shadow around the artwork's edges. - Aspect Ratio: --ar 16:9

[Campaign Information] - Campaign Name: {argument name="campaign name" default="My Favorite Item Giveaway Campaign"} - Prize List: {argument name="prizes" default="Tonkotsu Ramen, Tea, Tissue Box"} - Participation Steps: {argument name="entry steps" default="Follow & Repost"} [Image Quality/Direction/Composition] - Style: Pop, bright, and friendly SNS promotional banner. Eye-catching design. - Subject: Illustrations or realistic product photos of {argument name="prizes" default="Tonkotsu Ramen, Tea, Tissue Box"} popping out of a gift box, surrounded by festive ribbons and star decorations, centered. - Color/Tone: Pastel tones of bright pink, yellow, and light blue to create a sense of excitement. - Text Info (for GPT-image / Nano Banana Pro): The text {argument name="campaign name" default="My Favorite Item Giveaway Campaign"} at the top and the simple steps {argument name="entry steps" default="Follow & Repost"} at the bottom, laid out clearly in a thick, cute, rounded font. - Lighting: Flat, uniform bright lighting with soft shadows. [Strict Layout Constraints (Required)] - Output the finished flat 2D design itself, filling the entire canvas. Scene elements inside the design (walls, rooms, shadows) described above are allowed. Absolutely NO photo-of-a-poster mockups: no picture frames, no poster-on-wall or poster-on-desk shots, no perspective warp or drop shadow around the artwork's edges. - Aspect Ratio: --ar 1:1 or --ar 16:9

Using my picture can you create a woman with long, dark hair styled in a half-up ponytail with face-framing strands sits angled in a modern textured armchair. She leans forward slightly, looking off-camera to her left with a subtle, closed-mouth smile. She wears a {argument name="dress style" default="black sleeveless mini dress featuring spaghetti straps, a fitted corset-style bodice with subtle lace embroidery, and a ruffled, layered lace skirt"}. Her accessories include {argument name="accessories" default="a delicate gold chain necklace, small hoop earrings, thin bracelets on both wrists, and simple rings"}. Lighting & Composition Shot Style: Medium full-length portrait shot outdoors at night using direct flash. Lighting: Direct camera flash, casting bold, high-contrast light on the subject while creating deep dark shadows in the foliage directly behind her. Color Palette: Dominated by deep greens and rich blacks, with warm skin tones highlighted by the flash. Setting & Background Foreground/Seating: A contemporary cream or off-white upholstered accent chair with a textured fabric finish. Background: {argument name="background" default="A dense wall of lush green climbing ivy leaves covering a white fence or wall behind her"}. Don’t change the face

Create a cinematic, ultra-realistic streetwear editorial portrait of me, preserving my exact facial identity, features, skin tone, hairstyle, and natural proportions. Style me in {argument name="outfit" default="premium modern streetwear with an oversized layered outfit, subtle accessories"}, and a confident relaxed pose in an {argument name="urban setting" default="urban setting with concrete architecture, textured walls, and understated city details"}. Use {argument name="lighting" default="dramatic natural lighting, soft shadows, shallow depth of field, realistic skin texture, sophisticated neutral tones, subtle film grain"}, high-fashion magazine composition, professional photography, and cinematic color grading. Make the image feel authentic, effortlessly cool, minimal, aesthetic, and editorial, like a luxury streetwear campaign photographed on a full-frame camera with an 85mm lens. I've attached my image here.

Ultra-realistic high-fashion beauty portrait of an elegant woman in a glamorous vintage-inspired look, wearing an oversized wide-brim {argument name="hat color" default="white"} hat casting a soft shadow over her face. Striking {argument name="eye color" default="light green"} eyes, perfectly shaped dark brows, dramatic winged eyeliner, soft rosy blush, flawless glowing skin, and bold vibrant {argument name="lipstick color" default="red"} lipstick. Large thin gold hoop earrings with pearl studs. She wears long satin red gloves, posing gracefully with both hands delicately framing her chin and face. Luxurious white faux-fur coat with a high-neck white outfit underneath. Soft neutral beige background, dreamy diffused studio lighting, smooth cinematic shadows, sophisticated editorial fashion photography, luxurious old-Hollywood aesthetic, high detail, sharp facial features, realistic skin texture, elegant composition, shallow depth of field, 4K, HD, vertical portrait, 9:16.

[Product and Campaign Info] - Appeal Text: {argument name="appeal copy" default="Exquisite & Selected"} - Brand Copy: {argument name="brand copy" default="Lifelong leather goods created by skilled craftsmanship"} - Target Product: {argument name="products" default="Genuine leather wallet and wristwatch"} [Quality, Effects, and Composition] - Style: Still-life product photography for high-end luxury brand catalogs or luxury magazine spreads. - Subject: {argument name="products" default="Genuine leather wallet and wristwatch"} placed on deep vintage leather or high-quality dark-toned textures. Details that evoke artisanal craftsmanship (such as stitching or metal hairline finishing) are beautifully and richly depicted. - Lighting and Color: A color palette based on deep dark brown, black, and brass gold. Warm amber-toned sidelighting with classic, heavy shadows. - Text Placement (for GPT-image / Nano Banana Pro): Using a thin gold-colored font, the text "{argument name="appeal copy" default="Exquisite & Selected"}" and "{argument name="brand copy" default="Lifelong leather goods created by skilled craftsmanship"}" are subtly placed as typography in a calm position on the screen. [Strict Layout and Output Constraints (Required)] - Output the finished flat 2D design itself, filling the entire canvas. Scene elements inside the design (walls, rooms, shadows) described above are allowed. Absolutely NO photo-of-a-poster mockups: no picture frames, no poster-on-wall or poster-on-desk shots, no perspective warp or drop shadow around the artwork's edges. - Aspect Ratio: --ar 3:4

Where the Wing Remembers Both Shores The dragon does not choose a century. It is the century choosing itself through a body made of postponement and afterglow. One wing trails the last unburned page of a library that fell before paper learned its own name. The other combs holographic rain from towers that have not yet decided whether they will stand or become rumor. Between them the air keeps two calendars and forgets which one is running. Its scales are older than the word for scale. They remember the heat of forges that have not been lit, and the cold of stars that have already gone out in some other telling. Runes surface and sink like thoughts a city has not earned the right to think. Each pulse of light is both relic and prototype. Below, the streets are wet with what has happened and what is still negotiating its arrival. Neon writes on water that was once a glacier’s patience and will be, later, only a rumor of thirst. Foundations rest on the quiet of forests that still dream they are standing. Billboards advertise tomorrows already homesick for the dusk that has not come. The creature’s eyes hold the only honest weather: one the green of a memory that does not yet know it is finished, the other the blue of a question that has not found the mouth that will ask it. They look at us the way time looks at itself when no one is watching without pity, without verdict, only the long courtesy of attention. We live in the brief downdraft of its passing, that strange, merciful interval where the past is still unfinished with us and the future has already begun to miss what we have not yet lost. Nothing is promised except the turning: he slow, luminous hinge of a wing that belongs to every hour at once and to none of them completely. The mist it leaves is neither ending nor beginning. It is the place they briefly recognize each other before the next uncertainty opens its quiet, necessary hand.

A vibrant, cartoonish illustration depicts a {argument name="creature" default="monstrous green creature with bulging eyes and sharp teeth"} driving a souped-up {argument name="car type" default="pink Volkswagen Beetle"}. The car is adorned with flames and the words "BEETLE BOMBER" and "RAT ROD." The creature wears a racing helmet and is shown mid-air, with smoke and flames billowing from the rear tires and exhaust pipes. In the background, a crowd of equally bizarre characters cheers from behind a "DRAG STRIP" sign. Neon signs for "BEETLE JUICE," "COLD BEER," and "NITRO" add to the chaotic, high-energy atmosphere of a drag race. The art style is reminiscent of comic books and graffiti, with bold outlines and saturated colors.

{ "title": "{argument name="title" default="HARRY POTTER AT 80"}", "scene": "A quiet winter evening inside a small countryside cottage. Snow falls gently outside the frosted windows while a warm fireplace softly illuminates the room.", "subject": "An 80-year-old Harry Potter sits alone in a worn leather chair, reading a stack of faded letters collected throughout his life. His face shows wisdom, loss, and peace after a lifetime of adventure.", "detail": "His famous wand hangs untouched above the fireplace, covered in dust. Old photographs of Ron, Hermione, Hagrid, and the Hogwarts years decorate the room. A pair of round glasses rests beside a cup of tea. On a nearby shelf sits a weathered photo album labeled 'Hogwarts'.", "atmosphere": "deeply nostalgic, emotional, bittersweet, peaceful, reflective", "lighting": "warm firelight, soft shadows, golden glow, cinematic winter ambience", "composition": "intimate cinematic shot, Harry positioned beside the fireplace, snow-covered window visible in the background", "style": "photorealistic, cinematic masterpiece, Hollywood movie ending scene, ultra detailed, film grain, shallow depth of field, 8K", "mood": "The boy who lived has become the man who remembers.", "image_text": "Some magic never leaves." }

“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