GPT Image 2 prompts

Browse GPT Image 2 prompts for fashion portraits and graphic compositions. Compare how each prompt describes its subject and the way the image is arranged.

探索提示词

9,926 条提示词

Game Asset - 3D School Gym Boss Arena — output

Game Asset - 3D School Gym Boss Arena

新清士@AIコンテンツ開発者GPT Image 2
Using REFERENCE_0 as the source scene, convert the game screenshot into a clean, explorable 3D environment render of the same old school gym battle arena, as if rebuilt in Blender/real-time 3D. Remove all game UI, dialogue, HUD elements, text overlays, minimap, health bars, and the player character. Keep only the gym setting and the central masked shadow spirit with its glowing purple sealing magic circle, but make the monster more like a solid 3D asset hovering above the court rather than a 2D effects-heavy apparition.

Environment changes: make the gymnasium architecturally realistic and detailed, with a polished wooden basketball court, accurate court markings, wall padding, wooden wall bars, doors, a stage with closed red curtains at the far end, side balconies/upper walkways with railings, large windows, visible steel roof trusses, and hanging industrial ceiling lamps. Include exactly 4 visible basketball hoops: two on the left wall, one at the far back, and one on the right wall. Use cool indoor evening lighting with subtle purple spill from the spirit and magic circle, realistic reflections on the lacquered floor, and a wide cinematic camera angle from an elevated spectator viewpoint.

Style: realistic 3D anime-game environment render, clean composition, high fidelity school gym details, no characters besides the summoned spirit, no interface, no captions, no watermark. The result should feel like a playable UE5/Blender level based on the reference image.
使用此提示词 ↗
Profile / Avatar - 2D Anime to 3D Toy Avatar — output

Profile / Avatar - 2D Anime to 3D Toy Avatar

蘭熊才王(らんくまさいわん)GPT Image 2
Using REFERENCE_0 as the character base, transform the anime character into a simple stylized 3D toy/avatar model while preserving the recognizable face cues, round glasses, short dark bob haircut, and gentle expression. Change the result from a 2D illustration lineup into a single full-body 3D render in a neutral standing pose, viewed slightly from above and slightly three-quarter front.

Style: soft, glossy plastic / clay-like 3D character with simplified anatomy, rounded forms, segmented doll-like limbs, and minimal facial detail. Make the hair into chunky sculpted pieces rather than painted strands.

New outfit and body design: replace the original exposed/censored body with a modest toy outfit made of exactly 5 visible components: 1 oversized white T-shirt, 1 pale blue letter “M” on the shirt front, 1 blue shorts/hip piece, 2 blue leg pieces, and 2 rounded white shoes. Use simple cylindrical arms with mitten-like hands and blocky shoulder pieces.

Scene: place the character alone on a pale blue-gray studio floor plane against a dark nearly black background, with soft overhead lighting, gentle shadows, and a clean 3D preview/render look.

Constraints: do not include the original multi-view lineup, censor mosaic, or reference sheet layout. Do not add text other than the single shirt letter {argument name="shirt letter" default="M"}. Keep the model cute, non-realistic, and clearly toy-like. Use {argument name="character style" default="soft glossy plastic 3D avatar"} and {argument name="background" default="dark studio backdrop with pale blue-gray floor"}.
使用此提示词 ↗
Comic / Storyboard - Anime Forest Tram City Café — output

Comic / Storyboard - Anime Forest Tram City Café

養分GPT Image 2
Create a richly detailed vertical anime fantasy illustration of two young women relaxing at a small wooden café table on a high balcony built into an enormous forest city. In the foreground, show exactly 2 characters: a brown-haired girl in a green cloak on the left, leaning on one hand and smiling while holding a teacup, and a blonde girl in a blue-and-cream adventurer outfit on the right, seated with both hands around a cup, facing her friend. The table should include exactly 5 visible tabletop items: one dark green teapot, two teacups, one small plate with pastries, and one glowing lantern. Surround them with wooden railings, flower boxes, leafy plants, a canvas awning, and warm dappled sunlight. Beyond the balcony, reveal a vast vertical elven/treehouse metropolis built among gigantic ancient trees, with countless cozy houses, spires, market tents, hanging banners, glowing windows, and multiple elevated wooden bridges and rail lines layered into the distance. Include exactly 5 visible tram cars on the elevated tracks at different depths, with warm lit windows. Add a few small white birds flying in the sunbeams. Use a breathtaking high-angle composition, immense depth, intricate architecture, golden morning light filtering through dense green canopy, soft atmospheric haze, painterly anime style, cinematic fantasy worldbuilding, extremely detailed but clean linework, warm inviting mood, no text, no watermark. Customization slots: the city should feel like {argument name="fantasy city type" default="an elven forest tram city"}, the foreground characters should be {argument name="main characters" default="two young female adventurers having tea"}, the lighting should be {argument name="lighting mood" default="golden morning sunbeams through leaves"}, the setting details should emphasize {argument name="architectural focus" default="wooden bridges, treehouse towers, and elevated tram rails"}, and the art style should be {argument name="art style" default="highly detailed painterly anime fantasy illustration"}.
使用此提示词 ↗
Profile / Avatar - Waving Schoolgirl in Sunlit Hallway — output
Product Marketing - Mythic Warrior Statue — output

Product Marketing - Mythic Warrior Statue

佐藤 勝彦(TANREN_CEO)┃生成AIエバンジェリストGPT Image 2
Create a hyper-detailed premium collectible statue render of {argument name="character name" default="the Founder"}, a mythic ancient warrior-king posed on an ornate display base against a plain dark charcoal studio background. The figure is a full-body 3D figurine in a dramatic heroic stance: left arm extended outward with open hand, right fist clenched at his side, torso turned slightly left, one boot raised on jagged rubble. He is an elderly but extremely muscular man with tan skin, stern face, thick gray eyebrows, long flowing gray hair, and a full gray beard. Dress him in dark bronze-and-black fantasy armor: layered bracers, heavy boots, lion-head knee guards, engraved belt with a central lion face, black leather skirt panels with intricate gold filigree, fur-lined shoulder mantle, ornate round shoulder clasps, and a tattered deep red cape sweeping to the right. Surround him with exactly 4 large spiraling bands of glowing golden magical energy, made of many bright ember-like filaments and sparks, wrapping from the base around his legs, behind his torso, and over his head; include exactly 14 small floating dark rock fragments caught in the energy field. The base is a round black-and-bronze museum-quality statue plinth with jagged black rubble on top, exactly 3 broken classical stone columns, heavy chains, gold trim, and exactly 5 sculpted lion-head ornaments visible around the front rim. On the central front plaque, show the text {argument name="base plaque text" default="始祖"} in engraved gold characters. Lighting should be cinematic studio lighting with warm orange glow from the magic, crisp shadows, high contrast, ultra-sharp details, realistic resin/painted-metal materials, and a vertical product photography composition. Make it look like an exceptionally expensive limited-edition fantasy figure, not a flat illustration; no watermark, no extra text besides the base plaque.
使用此提示词 ↗
Profile / Avatar - Pink Kawaii Anime Girl With Teddy Bears — output

Profile / Avatar - Pink Kawaii Anime Girl With Teddy Bears

studioあぽろんGPT Image 2
Create a highly detailed vertical kawaii anime illustration in a soft pink bedroom filled with teddy bears and sparkling decorations. Center a cute anime girl named {argument name="character name" default="Astra"} with long fluffy twin-tail {argument name="hair color" default="bubblegum pink"} hair, glossy magenta-pink eyes, pale skin, a small pouty mouth, and a slightly bashful expression. She wears an elaborate pink idol-lolita dress with layered ruffles, lace trim, checkered pink fabric, bows, frilled wrist cuffs, a corset-style waist ribbon, thigh-high white-and-pink stockings, and multiple teddy-bear accessories. Her twin tails are tied with two oversized pink gingham lace bows, each decorated with a small bear face charm; add a curled ahoge strand above her head. She sits facing the viewer in a plush pastel room and holds a white rectangular sign in front of her chest with large handwritten Japanese text {argument name="sign text" default="あすとら"} in thick bright pink brush lettering, plus small doodles: a bow, crown, hearts, stars, wavy lines, and a simple bear face. Her right hand points toward the sign while her left hand grips it. Surround her with exactly 6 visible teddy bears: 1 large bear at lower left raising both arms, 1 medium bear at mid-left beside the sign, 1 bear peeking from the upper-left background, 1 bear at upper-right background, 1 cheerful bear at right middle raising one paw, and 1 large bear at lower-right raising both arms; all bears are beige with pink bow ties and joyful faces. Add white and pink decorative sparkle icons, heart doodles, and emphasis marks around the character, especially at the left and right edges. Background: dreamy pink bedroom with soft-focus curtains, plush bedding or cushions, a warm table lamp, pastel furniture, and more pink decorative details, blurred enough to keep focus on the character. Visual style: polished modern anime key visual, ultra-cute yume-kawaii aesthetic, pastel pink color palette, luminous highlights, soft bloom, glossy eyes, delicate linework, dense lace and fabric detail, high resolution, portrait 3:4 composition, no watermark, no extra readable text beyond the sign.
使用此提示词 ↗
Profile / Avatar - Dreamy Polka-Dot Bow Portrait — output
Profile / Avatar - Kawaii Denim Portrait — output
Infographic / Edu Visual - AI Thinking Saves Cost Poster — output

Infographic / Edu Visual - AI Thinking Saves Cost Poster

TzGPT Image 2
Goal: Create a warm vertical Xiaohongshu-style illustrated poster explaining that letting AI think longer can reduce the bill, using a cozy home DIY scene and clear handwritten Chinese typography.

Canvas: Vertical 3:4 social media poster, soft golden afternoon light, high-resolution anime/editorial illustration, inviting and optimistic.

Main headline: At the very top, place a large cream brush-stroke banner with bold hand-painted Chinese text: {argument name="headline text" default="让 AI 多想一会儿,账单竟然少了近一半"}. Emphasize the final phrase in orange-red while the rest is dark brown-black. Add small yellow-orange emphasis rays on both sides.

Subtitle: Directly below the headline, add a smaller rounded white label with Chinese text: {argument name="subtitle text" default="Astra 的能力曲线为什么开始拐弯"}.

Central scene: A cute young man with {argument name="hair color" default="messy dark brown hair"}, wearing a forest-green sweater and dark pants, sits cross-legged on a rug in a sunlit room. He looks upward thoughtfully with a small smile, holding a pencil near his chin and an open instruction booklet in his lap. The booklet shows a simple line drawing of a shelf on the left page and a checklist on the right page.

Counted text elements and labels: Include exactly 1 thought bubble above the character with Chinese text: {argument name="thought bubble text" default="先想清楚 再动手..."}. Include exactly 4 checklist rows in the booklet: 3 checked items labeled 「思考」, 「规划」, 「执行」, and 1 unchecked grey item labeled 「返工」. Include exactly 1 whiteboard chart in the background labeled 「效果 vs 成本」 with a vertical axis 「效果 (%)」 and horizontal axis 「成本 ($)」. On the chart, show exactly 2 curves: an orange solid curve with round markers bending upward then flattening, labeled 「Astra 开始拐弯」 with an orange arrow, and a grey dashed curve labeled 「不够思考 成本更高」.

Room and objects: The setting is a cozy living room or study with blurred plants, framed pictures, warm window light, and a wooden shelving unit being assembled. Show exactly 1 sleeping orange-and-white cat curled on top of the shelf. Show scattered DIY parts in the foreground: wooden boards, screws, and 1 orange-black screwdriver. Add exactly 1 white mug near the character with English text stacked as “Good Plan Lower Bill” and a small smiley face.

Sticky notes and cardboard signs: Include exactly 3 yellow note/sign elements: 1 sticky note on the upper right wall saying 「多一步思考 少很多返工 更聪明 也更省钱」 with a smiley face; 1 sticky note on the wooden shelf saying 「一次做好 省时省钱」 with a bold check mark and small yellow emphasis rays; 1 cardboard box sign in the lower right foreground saying 「更聪明的 AI 更轻松的生活」 with a simple house icon.

Visual style: Soft painterly anime illustration mixed with infographic design, rounded shapes, thick friendly hand-lettering, warm beige/orange/green palette, gentle depth of field, clean composition, lively but not cluttered.

Constraints: Preserve all Chinese text exactly as specified, keep the poster readable, use no logos or watermarks, and do not add extra charts, extra sticky notes, extra characters, or extra checklist items.
使用此提示词 ↗
Profile / Avatar - Black and White Pencil Portrait — output
Social Media Post - Romantic Couple Graphite Sketch — output
Game Asset - Isometric Miniature American Kitchen — output

Game Asset - Isometric Miniature American Kitchen

Berryxia.AIGPT Image 2
Create a highly detailed isometric 3D miniature diorama of a cozy American-style kitchen corner, like a handcrafted dollhouse scene rendered in Blender with soft global illumination. The room is an open cube set with two cream wallpapered walls meeting in a corner, a raised square tiled floor base, and warm medium-brown wood trim along the top and chair-rail height. Use a warm beige studio background and orthographic camera at a 3/4 overhead angle. The kitchen style is nostalgic, cute, and slightly toy-like with rounded edges, polished wood, realistic materials, and clean miniature proportions. Include exactly 12 main furniture and fixture elements: 1 cream retro refrigerator on the left with the word {argument name="refrigerator label" default="NORD"}, small colorful round magnets and brass handles; 1 mint-green gas stove with black burners and a lidded pot; 1 long wooden lower cabinet run on the right with drawers, paneled cupboard doors, brass knobs, and a sink; 1 double window above the sink with beige tied curtains on a silver rod; 2 wall-mounted wooden box shelves, one above the stove and one to the right of the window, containing books and white jars; 1 square dining table in the center covered with a white-and-green checkered tablecloth; 3 wooden chairs around the table; 1 small framed picture on the left wall; and 1 pair of brass wall lamps with round shades and pastel pink globe accents. Add exactly 10 visible tabletop or counter accessories: 1 tray with bread loaves, 1 wooden cutting board, 1 small green bottle, 1 utensil cup with wooden spoons, 1 soap pump bottle, 1 blue teapot or kettle on the dining table, 1 glass dessert cloche with red-topped sweets, 1 small cup and saucer, 1 tiny plate with food, and 1 small rectangular sponge near the sink. Materials should include glossy cream enamel, mint painted metal, varnished wood grain, semi-transparent glass, soft fabric curtains, ceramic tiles, and brushed metal. Lighting should be warm and soft, with gentle shadows and ambient occlusion, emphasizing the miniature scale and fine details. Color palette: {argument name="wood tone" default="warm medium brown"}, cream, mint green, beige, pale pink, muted green, brass, and soft gray tile. No people, no watermark, no modern appliances beyond the retro fridge and stove, no clutter outside the cube room.
使用此提示词 ↗
Profile / Avatar - Heroic Yellow Robot with Cape — output

Profile / Avatar - Heroic Yellow Robot with Cape

Solip | Model C2 Companion UnitGPT Image 2
Create a clean, high-detail full-body 3D character render of {argument name="character name" default="Solip"}, a friendly heroic humanoid robot standing in a confident front-facing pose against a pure black studio background. The robot has a bulky armored mech body made of angular mustard-yellow metal panels with black mechanical joints, subtle scratches, beveled edges, and realistic wear. Its head is a square yellow helmet-like monitor with rounded corners, side circular ear modules, a glossy black screen face, and a cute green LED pixel expression: exactly 2 upside-down U-shaped eyes and 1 smiling curved mouth. Add the teal marking {argument name="chest label" default="C2"} on the upper right chest plate. The robot wears exactly 1 dramatic black cape flowing behind both shoulders, with a teal inner lining and teal trim visible along the edges. Include detailed segmented arms, articulated black fingers, large shoulder rings, piston-like elbows, thick armored thighs, knee plates, heavy boot-like feet, and exposed dark understructure between plates. Use cinematic low-key lighting with warm golden rim light from the upper left, crisp reflections on metal, deep shadows, a subtle floor reflection, and an ultra-clean premium sci-fi toy/film render look. Center the character vertically in a portrait composition, slightly low camera angle, sharp focus, no background props, no extra characters, no text except the chest label.
使用此提示词 ↗
Product Marketing - Motion Blur Fashion Editorial — output

Product Marketing - Motion Blur Fashion Editorial

AI QoroGPT Image 2
Create an ultra-realistic vertical 4:5 fashion editorial studio photograph of {argument name="character name" default="a young woman"} standing centered and sharply in focus, facing the camera with a calm neutral expression. She has {argument name="hair color" default="dark brown"} hair styled in a loose low bun with soft face-framing strands, natural makeup, delicate features, and small earrings. Dress her in a relaxed {argument name="shirt color" default="warm chocolate-brown"} short-sleeve button-up camp-collar shirt with a chest pocket, tucked loosely at the front, paired with high-waisted wide-leg {argument name="pants color" default="cream linen"} trousers and off-white low-top sneakers; add a dark wristwatch on one wrist. Pose her with both hands in her trouser pockets, one leg crossed casually in front of the other, full body visible from head to shoes. Surround her with exactly four motion-blurred duplicate figures of the same woman: one blurred figure at far left walking sideways, one blurred figure just left of center behind her, one blurred figure just right of center behind her, and one blurred figure at far right walking sideways; all duplicates wear the same outfit and are heavily smeared with horizontal motion blur while the central subject remains crisp. Use a seamless warm tan studio backdrop and matching tan floor, soft diffused editorial lighting, shallow depth of field, muted earthy color palette, realistic fabric texture, subtle shadows under the shoes, high-end fashion campaign mood, no text, no logos, no watermark.
使用此提示词 ↗
Infographic / Edu Visual - Minimalist Event Flyer Design — output

Infographic / Edu Visual - Minimalist Event Flyer Design

AI Guide-Note - 実務で使えるAI活用メディアGPT Image 2, Nano Banana Pro
[Event Information]
- Event Name: {argument name="event name" default="Margins and Structures"}
- Date & Time: {argument name="date" default="October 12 – November 24, 2026"}
- Venue: {argument name="venue" default="National Museum of Modern Art"}

[Quality, Direction, and Composition Specifications]
- Style: A poster for a contemporary art exhibition or modern design event, clean and minimalist editorial layout.
- Visual Elements: A beautiful live-action composition conveying silence and intelligence, set against geometric abstract art objects or concrete and glass architectural spaces.
- Typography Placement (For GPT-image / Nano Banana Pro): In the empty margins of the screen, the event name '{argument name="event name" default="Margins and Structures"}', the date '{argument name="date" default="October 12 – November 24, 2026"}', and venue information '{argument name="venue" default="National Museum of Modern Art"}' are beautifully laid out in a sophisticated, modern sans-serif font. The typography harmonizes without detracting from the beauty of the overall image.
- Lighting & Color: A clean space based on white, cool natural light with soft gradients of light, neutral tones with accent colors (e.g., navy or dark gray).

[Strict Layout and Output Constraints (Required)]
- Output the completed design itself, filling the entire canvas. Scene descriptions inside the design (walls, spaces, shadows) may follow the text instructions.
- Prohibited items: Photographs of the finished poster inside a frame, stuck to a wall, mockup photos placed on tables 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 3:4
使用此提示词 ↗
Social Media Post - Y2K Fisheye Streetwear Portrait — output
Social Media Post - Traditional Outfit Night Portrait — output
Infographic / Edu Visual - Culinary Sketchbook Illustrated Narrative — output
Social Media Post - Vintage European Cafe Portrait — output

Social Media Post - Vintage European Cafe Portrait

HeisenLegacyGPT Image 2
Ultra-realistic cinematic editorial photograph of a strikingly handsome young man in his early 20s sitting alone at a charming vintage European café in the early morning. He has thick, naturally wavy jet-black hair styled slightly tousled, strong well-defined eyebrows, deep expressive dark-brown eyes, a straight sculpted nose, prominent cheekbones, a sharp masculine jawline, and subtle natural stubble. He is seated beside a tall vintage café window, casually holding a ceramic cup of freshly brewed coffee, with gentle steam rising from it. He wears an elegant cream-colored linen shirt with the sleeves slightly rolled up, paired with tailored dark trousers, creating a sophisticated effortless European aesthetic. Warm golden morning sunlight streams through the old glass window, softly illuminating his face and creating beautiful shadows. Outside the window, a picturesque European street with old stone buildings, flower boxes, bicycles, and softly blurred pedestrians can be seen. Rustic wooden table, vintage chairs, delicate coffee cup, small pastry plate, warm beige and brown tones, subtle film grain, shallow depth of field, natural skin texture, soft bokeh, realistic reflections on the window, intimate peaceful atmosphere, luxury fashion editorial photography, cinematic composition, 85mm lens, f/1.8, photorealistic, high detail, soft natural lighting, 8K quality.
使用此提示词 ↗
E-commerce Main Image - Commercial Pink Berry Smoothie Photography — output

E-commerce Main Image - Commercial Pink Berry Smoothie Photography

Dua FatimaGPT Image 2
Create an ultra-realistic, high-end food photography scene in a bright, cozy modern kitchen. A {argument name="drink type" default="vibrant thick pink berry smoothie"} is served in a {argument name="glassware" default="stack of three small transparent glass jars"}, arranged vertically on the left side of a clean white round table. The smoothie has a rich creamy texture with subtle berry speckles and glossy highlights. On the right, place a clear jar of {argument name="complementary food" default="organic peanut butter"} with a green lid, filled with golden-brown creamy peanut butter. Preserve the product packaging, label placement, colors, and proportions accurately. Scatter a few whole peanuts naturally beside the jar. In the foreground, include a small ceramic bowl filled with mixed roasted peanuts and a beige ceramic plate holding a spoon with a generous scoop of creamy peanut butter. Add a few delicate green herb sprigs near the smoothie. Background: clean white subway-tile kitchen wall, soft natural sunlight coming from the side, subtle shadows, warm cozy atmosphere. Place the food items on a small wooden serving board with a sheet of vintage printed paper underneath. Add elegant handwritten-style white text in the upper-left area reading “Smoothies”, with smaller cursive text underneath reading “Tingi Kalori. Vertical 9:16 composition, premium commercial food photography, realistic textures, natural daylight, shallow depth of field, soft bokehcrisp product details, balanced composition, warm lifestyle aesthetic, photorealistic, high resolution, no people
使用此提示词 ↗
Comic / Storyboard - Split Photo and Storybook Illustration — output

Comic / Storyboard - Split Photo and Storybook Illustration

Mahnoor FatimaGPT Image 2
Create one vertical 3:4 composition that combines the uploaded photo with a hand-drawn illustrated version of the same moment. TOP HALF — ORIGINAL PHOTO. Keep the uploaded photograph in the upper portion of the canvas, occupying roughly 50%. Treat the photo as the only source of truth. Keep the person, face, expression, hair, outfit, accessories, pose, proportions, objects, lighting, colors, and surroundings faithful to the original. Do not beautify, retouch, restyle, replace, or reinterpret the photograph. It should remain natural and recognizable, as if the original image has simply been placed into the artwork. BOTTOM HALF — ILLUSTRATED VERSION. Use the lower portion to recreate the exact same moment as a handmade children's picture-book illustration. The illustrated version should retain: the same person and recognizable facial features, identical pose and body positioning, matching hairstyle and clothing, matching accessories and visible details, the same action and overall mood. Use a soft traditional art approach with: delicate watercolor washes, colored-pencil texture, fine pencil or ink contours, warm textured ivory paper, gentle hand-rendered shading, slightly uneven, organic strokes, subtle imperfections that make it feel handmade. Avoid a polished digital look. No photorealism, 3D rendering, anime aesthetics, or exaggerated cartoon styling. Simplify the background instead of copying every environmental detail. Keep only enough of it to suggest the original setting, while giving the illustrated subject plenty of breathing room. Make the illustrated subject slightly smaller than the photographic subject and leave generous negative space around it. SMALL HAND-DRAWN ACCENTS. Add only a handful of understated doodles around the illustration — perhaps tiny hearts, stars, flowers, or simple motion marks. They should feel naturally drawn onto the page rather than digitally decorated. Include a small handwritten note near the illustration: “{argument name="caption" default="little happy girl"} ♡”. Use a casual brown or soft-gray pencil/ink appearance. If the subject is not a girl, replace the wording with something suitable or leave the caption out. FINAL FEEL. The finished piece should resemble a beautiful handmade scrapbook or children's storybook page, where a real photograph has been paired with a lovingly drawn memory of the same scene. Keep the presentation: vertical 3:4, warm and editorial, cleanly divided between photo and illustration, minimal and elegant, sentimental but not overly decorative, rich in tactile paper and traditional drawing texture. IMPORTANT. Use only the uploaded photograph as visual reference. Do not borrow anything from previous prompts, images, references, or generated results. Do not introduce a different person, outfit, pose, object, setting, color scheme, or visual detail. The lower illustration must unmistakably represent the exact scene and moment shown in the uploaded photograph.
使用此提示词 ↗
Profile / Avatar - Sophisticated Monochromatic High-Fashion Portrait — output

Profile / Avatar - Sophisticated Monochromatic High-Fashion Portrait

TaliaGPT Image 2
Ultra-photorealistic high-fashion portrait of a {argument name="subject" default="sophisticated young woman"}, vertical 9:16. She has {argument name="hair style" default="extremely long, sleek, silky jet-black hair"} with subtle natural shine, perfectly straight full bangs framing her forehead, smooth strands cascading over her shoulders and chest. Delicate refined facial features, luminous porcelain-like skin, soft Korean-inspired makeup, naturally defined eyes, subtle warm brown eyeliner, long lashes, softly sculpted nose, glossy muted rose-pink lips. She wears an {argument name="outfit" default="elegant oversized black turtleneck knit sweater"}, creating a minimalist monochromatic luxury aesthetic. She stands naturally with relaxed shoulders, facing the camera in a slightly angled pose, head subtly tilted, one shoulder slightly closer to the lens. Her expression is calm, mysterious, confident and effortlessly elegant, with direct eye contact. Composition: intimate upper-body fashion portrait, centered framing, slightly cropped below the chest, realistic natural proportions, sophisticated editorial posing. Background is a dimly lit modern interior with dark neutral walls, a subtle doorway and minimal furniture details, softly blurred into creamy cinematic bokeh. Lighting: soft diffused window light from the side, gentle highlights across the face and glossy hair, subtle shadows defining facial structure, low-key cinematic atmosphere, natural skin texture, delicate catchlights in the eyes. Photography: luxury Korean fashion editorial, Vogue-inspired aesthetic, Sony A7R V, 85mm f/1.4 portrait lens, shallow depth of field, f/1.4, realistic optical compression, fine hair strands, detailed knit texture, natural pores, HDR, cinematic tonal range, subtle film grain, sophisticated dark color grading, ultra-detailed, 8K, photorealistic, museum-quality fashion photography.
使用此提示词 ↗
Social Media Post - Candid Winter Smartphone Portrait — output

Social Media Post - Candid Winter Smartphone Portrait

𝗦𝗮𝗻𝗶𝗮GPT Image 2
{"prompt": "A highly photorealistic full-body outdoor smartphone photograph of a young woman standing on a quiet urban street during soft winter afternoon sunlight. She has long, straight dark-brown hair flowing naturally over her shoulders, with realistic individual hair strands. She has a gentle, cheerful expression with her eyes softly closed and her head tilted slightly to one side, creating a playful and candid pose. She is standing comfortably with her arms crossed while lifting one leg slightly behind her.", "subject": {"gender": "young woman", "hair": "long, straight dark-brown hair flowing naturally over her shoulders", "expression": "gentle, cheerful, relaxed smile with eyes softly closed", "pose": "head slightly tilted to one side, arms comfortably crossed, one leg lifted slightly behind her in a playful candid pose"}, "outfit": {"outerwear": "oversized pastel lavender-blue button-up shirt", "top": "delicate white lace-trimmed top", "bottom": "short flowing white tiered skirt", "bag": "small cream-colored backpack hanging over one shoulder", "shoes": "clean white sneakers"}, "background": {"location": "quiet urban street", "wall": "old textured cream-colored wall with geometric square details", "details": ["bare climbing vines", "small dark sign", "parked car", "subtle urban street elements"]}, "lighting": {"time": "soft winter afternoon", "style": "natural warm sunlight", "effects": ["subtle warm glow around her hair", "gentle natural shadows", "faint realistic lens flare"]}, "photography": {"camera_style": "natural smartphone photography", "aesthetic": "candid travel-fashion photography", "skin_texture": "realistic natural skin texture with subtle imperfections", "focus": "shallow depth of field", "color_grading": "soft pastel color grading", "film_effect": "subtle vintage film grain", "realism": "natural body proportions, realistic fabric texture, realistic lighting, authentic mobile camera appearance"}, "mood": "dreamy, peaceful, cheerful, soft and candid", "quality": "highly photorealistic, natural-looking, realistic smartphone photo", "aspect_ratio": "4:5", "negative_prompt": "cartoon, illustration, CGI, 3D render, overly smooth skin, plastic skin, artificial face, distorted body, extra fingers, extra limbs, blurry face, unrealistic proportions, oversaturated colors, studio lighting, heavy makeup, exaggerated lens flare"}
使用此提示词 ↗
Social Media Post - European Palace Fashion Editorial — output

Social Media Post - European Palace Fashion Editorial

HeisenLegacyGPT Image 2
Ultra-realistic cinematic editorial photograph of a {argument name="subject" default="strikingly handsome young man in his early 20s"} standing confidently on the grand staircase of an opulent marble palace. He has thick, naturally wavy jet-black hair styled slightly tousled, strong well-defined eyebrows, deep expressive dark-brown eyes, a straight sculpted nose, prominent cheekbones, a sharp masculine jawline, and subtle natural stubble. He wears an {argument name="outfit" default="impeccably tailored classic black suit with a crisp black shirt"}, creating an elegant, mysterious, sophisticated presence. The grand staircase is crafted from polished white marble with luxurious black-and-gold detailing, surrounded by towering classical columns, ornate carved balustrades, dramatic arches, and magnificent palace architecture. Soft warm golden light streams through enormous windows, creating cinematic highlights and subtle shadows across his face and suit. He stands with relaxed confidence, one hand resting naturally on the marble railing, looking slightly away from the camera with a calm, powerful expression. Luxury fashion editorial aesthetic, European aristocratic palace atmosphere, timeless elegance, photorealistic skin texture, realistic fabric details, natural proportions, shallow depth of field, cinematic lighting, sophisticated composition, 85mm portrait lens, ultra-detailed, high dynamic range, subtle film grain, 8K quality, vertical composition.
使用此提示词 ↗
按模型、风格或主题浏览

寻找下一个方向

ASTORIE CANVAS

让灵感,继续生长。

在同一个创作空间,连接提示词、参考素材和生成结果。

打开创作画布 ↗