GPT Image 2Prompts

Transform the person in the photo into a {argument name="style" default="grotesque and humorous fashion caricature sketch"}, keeping only the {argument name="subject" default="close-up of the person's head"}, as if improvised by a street sketch artist, with strongly exaggerated anatomy, elongated proportions, dramatic facial expressions, awkwardly elegant poses, sketchbook style.

Based on the understanding of the "{argument name="character name" default="character name"}" generate a unique and fully developed worldview, including scene style, cultural background, and spatial design. The composition should have an epic scale and cinematic framing. Feature the "{argument name="defend-type character" default="defend-type character"}" as the main protagonist in a high-quality anime art style, with clear facial features and natural body proportions (not chibi). The character should be shown in a full-body composition, standing slightly forward at the center of the frame, with a confident runway-like presence and posture. The character’s outfit style, materials, and overall color palette should be automatically derived from the generated worldview, featuring a premium design aesthetic with cohesive color layering. Position an exclusive "{argument name="guardian spirit beast" default="guardian spirit beast"}" behind the character on the left side. The AI should automatically generate the beast so it fully aligns with both the character and the worldview. The beast must be enormous, far larger than the character, with a structurally believable design. It should appear as a hybrid of physical form and energy, with intricate textures and layered lighting effects. The guardian occupies the upper portion of the composition, creating an overwhelming sense of pressure while advancing alongside the character. The character, guardian beast, and environment must share a unified artistic style while maintaining clear color contrast to avoid visual blending. Lighting should adapt naturally to the worldview while remaining bright, clean, and cinematic with high-end animated film quality. The overall aesthetic should resemble epic anime art combined with premium AAA game key visuals, featuring ultra-high detail, high resolution, and a clean composition. Negative requirements: no additional characters, no multiple spirit beasts, no chibi or low-quality cartoon styles, no text or watermarks, no blurry faces, and no deformed anatomy or structures.

Dreamy Busan Korea travel journal illustration, cozy vintage scrapbook aesthetic, watercolor and ink art style, red-haired girl sitting at a seaside café writing in a notebook, cream knitted cardigan, floral dress, cinematic ocean view, colorful Gamcheon Culture Village houses on cliffside, Korean signs, travel stamps, boarding pass, handwritten notes, postcards, maps, tape stickers, seashells, coffee cup, retro camera on wooden table, soft pastel tones, warm sunlight, detailed paper textures, whimsical travel diary composition, nostalgic Korean coastal vibe, artistic collage layout, highly detailed, hand-painted aesthetic, soft ocean breeze, aesthetic travel memories, vertical composition –ar 4:5 –stylize 700 Busan South Korea aesthetic travel scrapbook illustration, watercolor sketchbook style, beautiful red-haired girl standing near seaside promenade sketching in notebook, cozy oversized cream sweater, flowing hair in ocean breeze, colorful coastal village, Gamcheon Culture Village, Songdo Beach, Gwangan Bridge, Korean café street, vintage postcards and stamps, handwritten journal entries, maps and travel ephemera layered on textured paper, warm beige and pastel palette, dreamy vacation mood, nostalgic wanderlust aesthetic, soft painterly details, cozy Korean seaside atmosphere, handmade collage journal look, cinematic composition, highly detailed watercolor travel diary art –ar 4:5 –stylize 750

Create a nostalgic corkboard collage of exactly 10 pinned Polaroid-style photographs featuring {argument name="character name" default="Kurage-chan"}, a dreamy faceless anime-inspired girl or ball-jointed doll with {argument name="hair color" default="silvery white"} bobbed hair, a soft white beret, pale skin, and an ethereal jellyfish-themed white outfit with fluffy translucent sleeves, lace, pearls, ribbons, and trailing tentacle-like fabric. The overall mood should be cinematic, muted, emotional, and slightly melancholic, like faded film photography. Arrange the 10 Polaroids on a warm brown corkboard, each with a thick white instant-film border and held by small clear round pushpins; allow slight overlaps and tilted angles. The exact 10 photo contents are: 1) top left, close-up indoor portrait of the girl in white, face softly obscured, moody window light; 2) top center, full-body shot by a waterfront promenade with hazy ships in the distance; 3) top right, rear view on a rooftop or balcony overlooking a blurred city skyline at sunset; 4) middle left, still life by a window with a vase of flowers, a teacup, and berries on a plate; 5) middle center, intimate bedroom shot of the girl lying on white sheets in soft morning light; 6) middle right, the girl sitting at a desk or cafe table reading an open book with an iced drink beside her; 7) middle far right, back view of the girl standing among white flowers in a sun-dappled garden; 8) bottom left, the girl reaching upward in a dim convenience store or shop aisle; 9) bottom center, close-up night portrait with blurred city lights and bokeh behind her; 10) bottom right, distant back view of the girl at a gray beach with flying birds and waves. Use {argument name="photo style" default="analog Polaroid film"} aesthetics: soft focus, shallow depth of field, slight blur, muted grays and creams, warm shadows, subtle grain, imperfect exposure, and no visible text. Keep the character consistent across all photos, keep the faces blank or softly obscured, and make the collage look like physical prints pinned to a real corkboard.

A medium-wide shot of the uploaded person standing inside a realistic {argument name="location" default="Seoul subway station"}, proudly pointing and smiling at a massive wall-mounted LED billboard behind them. The giant billboard displays a stylized fan-support advertisement featuring the exact same uploaded person, designed with a {argument name="theme" default="[THEME COLOR & MOOD]"} aesthetic. On the billboard, bold and clean typography prominently displays "{argument name="slogan" default="[MAIN SLOGAN]"}" and "[SUB SLOGAN / DATE]". The real-life version of the uploaded person wears a casual stylish outfit and stands naturally in front of the screen, creating the illusion that the real person and the billboard celebrity version coexist seamlessly in the same physical environment. Authentic Korean subway environment with realistic tiled walls, natural floor textures, believable architectural depth, and subtle commuter motion blur in the background. Ambient fluorescent station lighting blends naturally with soft LED billboard glow, creating realistic reflections and cinematic light spill across the floor, walls, and skin. Perfect facial identity consistency between the uploaded person and the billboard portrait. Realistic environmental shadow integration, authentic perspective alignment, documentary-style realism blended with premium Korean commercial photography. Shot on a 35mm lens, eye-level camera angle, medium-wide cinematic composition, shallow depth of field, ultra realistic skin texture, hyper detailed, masterpiece quality.

Vintage monochrome {argument name="city" default="city"} travel poster illustration, detailed urban sketch aesthetic, clean architectural line art mixed with soft watercolor shading, modern Southeast Asian city atmosphere, minimalist {argument name="color palette" default="green-and-cream"} color palette, elegant travel poster typography, large bold city name at the top, bilingual typography with Asian characters, highly detailed street life scene, busy urban crossroads, flyovers, buses, motorcycles, cafes, local restaurants, pedestrians crossing streets, shopping malls and modern buildings, tropical city energy, documentary-style urban storytelling, soft paper texture background, intricate ink drawing details, calm atmospheric perspective, retro tourism poster design, hand-drawn cityscape illustration, realistic urban composition, cozy {argument name="culture" default="Indonesian"} street culture, collectible city print aesthetic, refined editorial travel artwork, ultra detailed linework, modern vintage fusion, Pinterest-worthy city poster style, 8k.

High-end fantasy minimalist fashion editorial inside a snow-covered celestial ryokan floating above frozen mountains. Shot on Pentax 67II, 105mm lens, Portra 400 film pushed to 800. Medium three-quarter shot, quiet documentary realism with cinematic negative space. A {argument name="subject" default="young woman"} wearing an oversized {argument name="brand style" default="cream Loro Piana knit"} layered under a flowing {argument name="coat style" default="Rick Owens-inspired ceremonial coat"}, soft dark hair with silver frost-tipped strands, delicate silver talisman rings glowing faintly, sitting in seiza beside a floating black tea bowl. Muted white-grey palette, snowfall diffusion, realistic skin texture, steam haze, imperfect realism, ancient glowing sigils on the floor. Typography Logo: ✦ FROSTBOUND ORACLE ✦ “Silence Is A Form Of Magic”

Create a photorealistic, slightly unsettling 1970s–1980s American Thanksgiving family dinner scene in a cozy but old-fashioned dining room. Use a 4:3 horizontal composition, warm dim indoor lighting, muted brown and cream tones, and a documentary snapshot aesthetic with realistic imperfections. Show exactly 9 people seated around a round table: 1 young adult man in a white shirt at far left, 1 woman beside him in brown, 1 middle-aged man in a white shirt and dark tie, 1 middle-aged woman in a pale floral blouse at the center, 1 young girl in a plaid dress and headband, 1 elderly man in a dark suit, 1 elderly woman in a dark patterned dress at far right, 1 boy seated with his back to the camera in the foreground, and 1 partially obscured person near the left side of the table. Make all human faces deliberately anonymized with soft rectangular blur blocks, increasing the uncanny realism. The table should be covered with a white lace tablecloth and crowded with exactly 8 visible food items: a large roasted turkey in the center, a bowl of green beans, a bowl of cranberry sauce, a bowl of mashed potatoes, a basket of dinner rolls, a rectangular baked casserole, a stuffing dish, and small plates of sliced food around the place settings. Include plates, forks, knives, spoons, drinking glasses, and napkins arranged realistically. Add exactly 3 pets: a gray tabby cat sitting on a small wooden stool at the lower left, a large German shepherd lying on the carpet in the foreground, and a brown hound dog standing in the kitchen doorway at the right rear. Background details: floral wallpaper, lace curtains glowing from a window on the left, a wooden china cabinet filled with plates and glassware centered on the back wall, autumn harvest decorations on top of the cabinet, small framed pictures, a black wall cross to the right, and a view into a wood-cabinet kitchen through the doorway. Add a faint blurred watermark-like block in the bottom-right corner. No readable text, no modern objects, no clean studio lighting; keep the image realistic, nostalgic, and subtly eerie.

Create a photorealistic documentary-style street photograph of the entrance to a Chinese electronics factory in Shenzhen on an overcast day. Show a wide horizontal 4:3 view from across a concrete driveway, with a slightly dated early-2000s digital camera look, natural muted colors, soft gray sky, realistic perspective, and no cinematic grading. The main subject is a white ceramic-tile industrial building complex with pale blue horizontal trim, three stories at the front and a long two-to-three-story wing receding diagonally into the background. Place a covered entrance canopy at the front-left center, glass doors beneath it, many rectangular windows with greenish glass, and a few external air-conditioning units on the side wall. On the upper facade, include red Chinese wall text reading {argument name="facade slogan" default="质量第一 客户至上"}. Stretch a red safety banner across the driveway in front of the building with yellow Chinese text reading {argument name="banner text" default="安全来自长期警惕 事故源于瞬间麻痹"}. On the right, place a tall dark red-brown vertical gate pillar topped with a white globe lamp, with gold vertical Chinese company lettering reading {argument name="company sign" default="深圳市富恒昌电子有限公司"}. In front of the pillar and along the entrance, include a closed silver accordion-style metal retractable gate. Add exactly 6 visible people: three adult male workers walking out from the entrance in the foreground, one in a light blue short-sleeve shirt, one in pale work clothes, one in a white shirt and jeans; plus three smaller figures standing farther back near the doorway. Add exactly 5 visible vehicles or bikes: one white van at far left, one dark sedan with a blue license plate parked in front-left, one dark vehicle partly hidden inside the gate, one black bicycle leaning near the gate, and one motorbike/scooter parked at the far right near blue planters. Include a wooden utility pole near the left foreground with overhead power lines crossing the upper-left corner and small posters pasted on the pole. Add low shrubs in blue-tiled planters on the right, gray concrete pavement with cracks and seams, and surrounding tiled factory walls. Make the image convincingly real, like an ordinary factory entrance snapshot, with slight lens softness and mundane environmental detail. Avoid modern luxury architecture, dramatic lighting, crowds, logos other than the described Chinese signage, and any surreal or illustrative style.

Goal: Create a warm minimalist interior design collage celebrating clean design, smooth forms, natural textures, and functional elegance, with a calm organic luxury mood. Canvas: A 4:3 horizontal image divided into exactly 4 equal rectangular panels in a 2x2 grid, separated by thin white gutters. Use soft natural daylight, beige plaster walls, warm wood, cream upholstery, woven rugs, olive greenery, and a serene editorial photography style. Visual style: Photorealistic high-end interior photography, neutral earthy palette, Japandi and organic modern influence, rounded forms, tactile materials, matte finishes, subtle shadows, no people, no visible branding, no text. Panel 1, top left living room: Show a cozy living room with exactly 1 curved cream bouclé sofa, 1 round low wooden coffee table, 1 large potted olive tree on the left, 1 framed abstract beige artwork centered above the sofa, 1 arched brass floor lamp with a woven shade on the right, 1 small ceramic vase with greenery on the coffee table, 1 shallow wooden bowl on stacked books, and 1 woven natural rug. Include an arched doorway in the back right with dim shelves beyond it. Panel 2, top right kitchen: Show a refined kitchen with exactly 1 pale stone island with vertical fluted wood front, exactly 3 wooden bar stools, exactly 2 dome pendant lamps hanging above, 1 tall window or glass door on the left with leafy outdoor greenery, 1 white vase filled with branches on the island, 1 bowl of green fruit, 1 black faucet and cooktop, and a slim floating shelf on the back wall with minimal ceramics and a small framed landscape print. Panel 3, bottom left bedroom: Show a tranquil bedroom with exactly 1 low wooden bed frame, cream bedding, exactly 4 visible pillows, 1 olive green throw blanket draped across the bed, 1 wooden nightstand on the left, 1 rounded beige table lamp, 1 framed delicate botanical artwork above the bed, 1 small vase with leafy stems near the window, 1 large floor-to-ceiling window on the right, and a woven rug under the bed. Panel 4, bottom right bathroom: Show a spa-like bathroom with exactly 1 freestanding oval cream stone bathtub, 1 white towel draped over the tub rim, 1 recessed illuminated wall niche holding minimal bottles, bowl, and plant, 1 wall-mounted black faucet with two knobs, 1 small round wooden side table with ceramics, 1 large potted olive tree near the right window, and 1 round woven rug in the foreground. Customizable direction: Maintain the overall aesthetic as {argument name="design style" default="warm organic modern Japandi minimalism"}, use {argument name="main color palette" default="cream, beige, warm oak, olive green, and soft taupe"}, set the lighting to {argument name="lighting mood" default="soft natural morning daylight"}, keep the material focus on {argument name="material focus" default="bouclé, plaster, oak wood, stone, linen, ceramic, and woven fiber"}, and make the space feel {argument name="emotional tone" default="calm, warm, elegant, and quietly luxurious"}. Constraints: Use exactly 4 panels and the specified object counts, keep the composition clean and uncluttered, avoid saturated colors, avoid harsh contrast, avoid people, pets, logos, captions, and extra decorative clutter.

Transform the attached image into a drawing that looks like it was made by a {argument name="child age" default="very young child, around 3 to 4 years old"}, using crayons. The drawing should feel silly, clumsy, and adorably bad, as if the child was trying to draw what they saw but only vaguely understood the subject. The lines should not be straight or clean. Avoid adult-level composition, realistic proportions, accurate anatomy, detailed shading, or polished illustration. Make it look awkward, naive, uneven, and a little random, like it was drawn from a toddler’s point of view. It is okay if the result looks messy, strange, funny, and not fully accurate to the original image. Style: {argument name="style" default="childish crayon drawing"}, rough scribbly lines, uneven shapes, simple colors, imperfect proportions, loose interpretation of the attached image.

Ultra-realistic luxury magazine cover featuring a {argument name="subject" default="rugged man with stylish hair"}, sharp jawline, thick beard, intense eyes, heavily tattooed neck, face, and hands, wearing a fitted white t-shirt under a {argument name="outerwear" default="distressed blue denim jacket"} and layered silver necklaces with a blue pendant, dark jeans with chain accessories. Confident masculine pose, hand gripping leather shoulder strap, cinematic lighting, editorial fashion photography, premium men’s lifestyle magazine aesthetic. Torn paper collage effect with extreme close-up facial fragments around the composition, {argument name="background" default="deep navy blue background"}, bold oversized typography, modern luxury branding, gritty rebel energy, high contrast skin texture, ultra detailed tattoos, photorealistic, sharp focus, dramatic shadows, 8k, hyper-detailed, Vogue x GQ x streetwear campaign style, premium color grading, collectible magazine cover design.

Create a premium educational “scientific anatomical visualization poster” focused on the {argument name="subject" default="human circulatory system"}, designed more like a modern medical museum display and biological atlas page rather than a typical infographic. The composition should feel elegant, immersive, and medically artistic, blending anatomical realism, scientific illustration, and cinematic educational design. Visual Direction: • Vertical poster composition or clean square format • Soft medical-grade background with subtle paper textures, anatomical sketch overlays, and faint scientific grid lines • Refined medical color palette using ivory white, deep crimson red, arterial blue, soft pink tissue tones, muted gray, and subtle gold accents • Clean editorial typography with elegant anatomical labeling • Minimal UI-style information panels — focus more on visual storytelling and anatomical beauty • Thin precision annotation lines with museum-style labels • Soft realistic lighting and premium biological rendering • Highly detailed semi-transparent human body illustration revealing the circulatory network beneath the skin • Realistic vascular textures with glowing arteries and veins flowing throughout the body • Sophisticated educational aesthetic inspired by high-end medical textbooks and anatomy exhibitions Main Subject Presentation: A breathtaking ultra-detailed anatomical render of the human circulatory system placed centrally, featuring: • semi-transparent human anatomy • hyper-detailed arteries and veins • visible heart chambers and aorta • capillary branching networks • realistic blood-flow coloration • glowing oxygenated vs deoxygenated circulation pathways • anatomically accurate vessel placement • subtle organ visibility beneath the vascular system • premium medical illustration realism Surround the anatomy with elegant educational visualization modules such as: • enlarged realistic heart anatomy • pulmonary circulation diagram • systemic circulation flow visualization • artery vs vein comparison • capillary exchange illustration • heartbeat cycle sequence • microscopic blood-cell closeups • blood composition visualization • major vessel identification map • oxygen transport explanation Add sophisticated scientific visual elements like: • blood-flow directional arrows • vascular cross-section diagrams • anatomical side callouts • circulation pathway diagrams • microscopic tissue exchange visuals • transparent organ overlays • ECG/heartbeat waveform accents • subtle medical chart graphics • biological texture overlays • anatomical scale comparisons Style Keywords: “museum-quality anatomical poster” “scientific medical atlas page” “premium biology visualization” “high-end anatomy illustration” “medical education artwork” “editorial anatomical design” “cinematic biological rendering” “ultra-detailed circulatory anatomy” “luxury medical textbook aesthetic”

For the image to be generated, pass only the prompt instructions to GPT image2. {argument name="Aspect Ratio" default="3:4 vertical composition"}. Draw it as a scene from a cinematic anime. Do not inherit the composition, pose, or screen layout of the reference image; refer only to the character design, costume, face, colors, and worldview. Depict a highly dynamic and striking moment that matches the reference character's personality, emotions, occupation, combat style, and worldview. Make it a direction that captures the middle of an action, emotion, or movement, rather than a mere pose. Use strong perspective, wide-angle lens style composition, depth, foreground occlusion, movement of hair and clothes by the wind, rack focus, bokeh, aerial perspective, and cinematic lighting. Emphasize horizontal eye guidance and wide spatial presentation. Make it work as a "single cut of a video work" including the background. The background information volume is high but organized, suppressing visual noise. Debris is prohibited. Characters other than the main character are minimal. Static poses, symmetry, empty backgrounds, poster compositions, and social game style standing pictures are prohibited. {argument name="Anime Style" default="Japanese TV anime style"}, anime screenshot, 2020s anime series, clean cel shading, flat anime coloring, polished anime lineart, no painterly rendering, clean digital anime finish, highly readable silhouette, cinematic anime depth of field.

Using the provided reference image as the character base, transform it into a nostalgic monochrome Japanese woodblock-print illustration on textured cream paper. Change the composition from vertical portrait to a wide horizontal postcard layout, keeping the same cute sea-themed girl and outfit concept but redrawing her smaller in the center, facing forward, with one hand raised in a friendly wave. Convert the blue-and-cream print into black ink linework only, with rough carved edges, uneven stamped texture, visible paper grain, and hand-printed imperfections. Layout: Add a thick hand-carved rectangular border around the entire image. Fill the surrounding space with playful decorative motifs while keeping the center character readable. Added motifs: Include exactly 3 jellyfish around the character, 4 ribbon bows placed near the four corners, 5 musical notes, 2 hearts, multiple bubbles, wavy water lines near the bottom, and scattered stars/sparkles in a cute handmade style. Style: Make it look like an old children’s picture-book woodcut or linocut print, simple black ink on off-white paper, charming, slightly rough, nostalgic, with no color fills other than black ink. Avoid realistic shading, gradients, or modern digital polish. Optional customization: Use {argument name="ink color" default="black"} ink on {argument name="paper color" default="cream"} paper, with the character in a {argument name="pose" default="one-hand waving pose"} and a {argument name="print style" default="nostalgic Japanese woodblock print"} finish.

Using this character, create a story-driven illustration themed around {argument name="Event" default="participating in a doujin circle at Comic Market"}. Use the reference image only for character reference; do not reuse the composition, background, pose, or framing of the original image. The character is working as a seller at their own circle space. On the desk, there are original doujinshi, posters, acrylic goods, can badges, flyers, price tags, and menus that suit the character. The AI should naturally conceive the content and worldview of the distributed items based on the character's personality. Emphasize the realistic atmosphere of a doujin circle that could actually exist. The character is wearing {argument name="Outfit" default="a cosplay-style arranged outfit inspired by their new publication"}. Create an atmosphere like "they are selling while dressed as a character from their own book." Appropriately place cardboard boxes, duct tape, half-empty plastic bottles, luggage, chairs, and small items in the circle space to give it a lived-in feel typical of an event venue. Introduce randomness to the situation and atmosphere each time. Naturally express different event atmospheres each time, such as a huge success, slightly bored, right after opening, right before closing, exhaustion, sense of accomplishment, emptiness, chaos, quiet time, unexpected popularity, or a time when no one comes. Add a speech bubble to the character and have them say a short comment fitting the situation. The dialogue in the speech bubble should emphasize a realistic otaku-like tension, a slightly surreal atmosphere, and a lived-in feel typical of an event participant. Keep the dialogue short and naturally amusing. Avoid excessive effects, glaring lighting, and unnatural glamorous presentations. Emphasize a realistic atmosphere that makes you feel "this doujin circle could really exist somewhere."

Use the {argument name="reference" default="uploaded portrait"} only as the identity and hairstyle reference. Preserve the real face shape, facial features, skin tone, and hairstyle. Do not copy the original portrait’s clothes, background, pose, or lighting. Create a realistic dreamy soft-focus balcony photo of an {argument name="subject" default="adult young woman"} sitting by an old metal railing, gently playing an acoustic guitar. She wears a {argument name="clothing" default="loose white knitted cardigan, simple light inner top, casual shorts, and white socks"}. Natural relaxed pose with one leg crossed, head slightly lowered, eyes looking at the guitar, quiet and candid mood. Old apartment balcony, green leaves and vines outside, warm afternoon sunlight, dappled shadows on skin and clothes, soft haze, slight overexposure, film-like glow, real camera texture, natural skin, realistic hands and guitar details, no watermark, no text, no logo.

Generate a candid selfie of a {argument name="famous person" default="historically famous person"} just moments before a {argument name="historic event" default="historic event"}, and add a {argument name="style" default="Snapchat-style"} caption.