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.

Explore prompts

9,991 prompts

Product Marketing - Graphic Cut-Paper Editorial Portrait — output

Product Marketing - Graphic Cut-Paper Editorial Portrait

ZayanGPT Image 2
Waist-up editorial portrait of {argument name="character" default="a stylish person"} in a calm three-quarter pose, with {argument name="hair style" default="a short bob"}, wearing {argument name="clothing" default="a linen blazer"}, oversized geometric sunglasses, bold circular earrings, layered necklaces, and holding [OBJECT] near the shoulder. Stylized [ANIMAL] beside the figure, constructed from the same flat cut-paper shapes and simplified graphic anatomy. Hand-cut paper collage with angular facial planes, minimal features, sharp silhouette edges, flat opaque color blocks, visible paper fibers, subtle screen-print grain, slight color misregistration, dry crayon-like marks, and no dimensional modeling. Controlled [COLOR] palette. Background made from [ELEMENTS], arranged as overlapping rectangles, rounded panels, striped inserts, hand-drawn grids, and small geometric accents on warm speckled off-white paper. Maintain a balanced modern editorial composition, strong negative space, crisp color separation, and tactile handmade print aesthetics.
Social Media Post - Photorealistic Close-up Portrait in Vintage Car — output

Social Media Post - Photorealistic Close-up Portrait in Vintage Car

MeemGPT Image 2
Photorealistic close-up over-the-shoulder portrait of the exact same {argument name="woman" default="young woman"} from the reference image. Preserve her facial identity, face shape, light blue-green eyes, thick natural eyebrows, nose, lips, skin tone, and distinctive facial features exactly as shown in the reference. Preserve her {argument name="hair color" default="dirty-blonde"} hair and overall appearance. She is sitting in the back seat of a {argument name="car style" default="vintage car"}, resting her arm on the leather upholstery and looking directly into the camera. Soft ambient light, rain-streaked window in the background, cinematic 85mm lens, shallow depth of field, realistic skin texture, high-end fashion photography. Generate only one image, single frame, no collage, no split-screen, no multiple panels.
YouTube Thumbnail - Cyberpunk Neon Dragon Awakening — output

YouTube Thumbnail - Cyberpunk Neon Dragon Awakening

Nagarjuna CreatesGPT Image 2
Create an ultra-cinematic 9:16 cyberpunk movie still titled “The Neon Dragon Awakens.” Nighttime in a vast futuristic metropolis during heavy rain. Towering glass skyscrapers disappear into the dark clouds, surrounded by glowing neon advertisements, holographic signs, flying vehicles, atmospheric fog and steam rising from the streets. In the foreground, show a {argument name="biker" default="lone female biker"} stopped on a {argument name="motorcycle" default="sleek futuristic black superbike"}. She is viewed mostly from behind, wearing a stylish black cyberpunk jacket and boots, staring upward toward an enormous curved digital billboard wrapped around a skyscraper. The billboard displays a {argument name="creature" default="gigantic holographic Chinese-style dragon"} made from brilliant crimson, magenta, electric blue and white energy. Capture the exact moment when something impossible begins happening: the dragon’s head and front claws are emerging beyond the flat surface of the billboard, as though the digital creature is becoming physically real. Parts of its body should still remain inside the screen, breaking apart into glowing pixels and holographic fragments where the digital world transitions into reality. The dragon looks directly toward the biker with intensely glowing eyes. Its enormous scale should make the biker and motorcycle look tiny by comparison. Rain falls through the neon light. Wet asphalt creates beautiful mirror reflections across the street. Steam drifts between buildings. Small futuristic vehicles and flying cars add depth and scale. Composition should feel like the opening frame of a high-budget cyberpunk science-fiction movie, with strong foreground, middle ground and deep city background specifically designed for image-to-video animation. Photorealistic cinematic lighting, dramatic volumetric atmosphere, realistic rain, extremely detailed dragon scales, holographic particle effects, realistic motorcycle materials, deep blacks, brilliant neon reflections, strong depth, subtle motion tension, anamorphic cinematic feel, epic scale, premium VFX quality, razor-sharp subject detail. The scene must instantly make the viewer wonder: “What happens when the dragon completely escapes?” No logos, no watermark, no captions, no readable brand names, no malformed motorcycle, no extra limbs, no duplicate dragon, no cartoon appearance. Vertical 9:16 composition, cinematic poster quality, visually spectacular and scroll-stopping.
Profile / Avatar - Realistic Woman Portrait with Wood Background — output

Profile / Avatar - Realistic Woman Portrait with Wood Background

Jahan ZaibGPT Image 2
Ultra-realistic close-up portrait of a {argument name="woman" default="beautiful young woman"} seated against a dark, richly textured wooden-paneled interior. She has {argument name="hair color" default="long, naturally wavy medium-brown hair"} with subtle highlights, parted slightly off-center and cascading over one shoulder. Her head is gently tilted toward the camera, creating an elegant, intimate composition. She has fair luminous skin with realistic natural texture, soft rosy cheeks, delicate facial features, expressive pale blue-green eyes with detailed irises and natural catchlights, softly defined brown eyebrows, long natural eyelashes, a small refined nose, and naturally full glossy pink lips. Her expression is calm, gentle, and slightly dreamy, looking directly into the camera. She is wearing an elegant {argument name="outfit" default="burgundy off-the-shoulder top"} that naturally reveals her shoulders and collarbones. Warm indoor lighting softly illuminates her face while preserving realistic shadows and depth. The dark wooden background creates a cozy, sophisticated atmosphere with subtle vertical paneling and rich brown tones. Photography: ultra-realistic smartphone portrait, close-up framing, slightly high camera angle, shallow depth of field, natural skin texture, realistic hair strands, soft warm lighting, subtle highlights, authentic facial proportions, cinematic depth, photorealistic, highly detailed, 8K quality, editorial beauty photography, natural color grading, no excessive retouching. Aspect ratio: 3:4 vertical.
Product Marketing - Sarah Nabila Cinematic Double Exposure — output

Product Marketing - Sarah Nabila Cinematic Double Exposure

Laraib Fatima‎GPT Image 2
Create a premium cinematic double-exposure portrait poster of the subject in a {argument name="background style" default="clean, soft beige studio environment"}, 4:5 aspect ratio. Use a sophisticated visual style combining Luxury Fashion Campaign, Apple Commercial, Premium Editorial Photography, and Hollywood Cinematic Poster aesthetics.

Feature a large, highly realistic side-profile portrait of the subject facing left, occupying approximately 70–75% of the frame height. The expression should be calm, confident, and elegant, with extremely sharp and detailed facial features, realistic skin texture, natural proportions, and refined editorial lighting. Behind the portrait, add strong horizontal motion-blur streaks moving toward the right, creating speed and dynamic energy while remaining clean, controlled, and premium.

In the foreground, include a full-body version of the exact same subject, approximately 30–35% of the overall frame height. Both versions must clearly be the same person with identical facial identity, facial features, skin tone, hairstyle, body shape, and overall visual characteristics. The double-exposure effect should feel like one seamless identity rather than two separate images.

The full-body subject wears a premium casual beige-toned outfit consisting of a relaxed-fit beige overshirt or jacket, neutral inner shirt, light-wash loose-fit jeans, modern casual sneakers, and transparent-frame modern glasses. Pose the subject naturally and confidently with both hands inside the trouser pockets, one leg naturally crossed in front of the other, and the body slightly leaning in a relaxed fashion-editorial posture. The head and eyes should be subtly directed toward the typography rather than looking directly at the camera.

Behind the full-body subject, integrate large futuristic typography reading exactly “{argument name="name" default="SARAH NABILA"}”. The typography should be bold, futuristic, modern, premium, slightly transparent, layered, and dimensional, with parts naturally hidden behind the subject to create convincing foreground-background integration. It must feel embedded into the composition rather than appearing as flat ordinary text.

Add minimal futuristic graphic direction around the composition: subtle geometric shapes, thin technical lines, translucent panels, fine grid details, minimal interface elements, futuristic markers, layered graphics, and subtle depth effects. Keep these elements elegant, restrained, and secondary to the subject.

Use premium soft studio lighting with gentle facial highlights, soft shadows, controlled contrast, natural skin texture, subtle cinematic glow, and a realistic soft shadow beneath the full-body subject. Lighting, color, and depth must remain consistent across both subject versions.

Maintain ultra-realistic facial details, realistic fabric and denim textures, sharp subject focus, cinematic depth, premium neutral color grading, sophisticated visual hierarchy, realistic anatomy, natural proportions, and professional high-end ad
Comic / Storyboard - Mid-Century Western Movie Trailer Cartoon — output

Comic / Storyboard - Mid-Century Western Movie Trailer Cartoon

ManuAGI 🤖 - ( ManuIn )GPT Image 2
Mid-century theatrical cartoon still promotional Hollywood movie trailer banner featuring a {argument name="male character" default="rugged cowboy with a short beard and steady gaze"}, wearing a classic western shirt, vest and cowboy hat, and a {argument name="female character" default="bold frontier woman with long chestnut hair and a determined smile"}, wearing a practical blouse and riding skirt, seated on a wooden porch railing outside a dusty saloon. Stage them in a lighthearted, spirited, good-humored interaction, with both characters fully visible, relaxed, and clearly reacting to each other with playful tension. Design the figures with exaggerated early-1950s animation caricature: clean black contour lines, sharply simplified anatomy, elegant angular silhouettes, expressive eyebrows, stylized facial shapes, graceful hand gestures, and cheerful readable expressions. Render the entire image in a unified traditional cel-animation aesthetic, with the background following the same stylized visual language as the characters, using flat opaque colors, minimal hard-edged shading, simplified furniture and décor, subtle hand-painted texture, controlled perspective, and crisp theatrical staging. Use a {argument name="color palette" default="dusty western palette of warm sand, deep brown, soft turquoise, and cream"} and maintain a witty, charming, visually snappy mood.
Product Marketing - 90s Retro Diner Fashion Editorial — output

Product Marketing - 90s Retro Diner Fashion Editorial

EeshaGPT Image 2
Create a photorealistic cinematic vintage editorial fashion photograph of a {argument name="subject" default="young adult woman with long messy black hair and wispy bangs"}, sitting inside a {argument name="setting" default="dark nostalgic retro American diner"}. She holds a cream-colored vintage corded telephone, with the curly cable naturally falling through the frame. She wears a fitted cream graphic baby tee with a red vintage car print, a {argument name="clothing style" default="burgundy ruffled mini skirt"}, white lace thigh-high socks and retro red-and-white sneakers. Calm dreamy expression, subtle eye contact, effortless 90s fashion editorial attitude. Dark wooden cabinets, vintage patterned tiles, vinyl records, old magazines, Coca-Cola memorabilia, popcorn and retro snacks fill the background. Warm tungsten lighting, deep shadows, subtle flash, realistic skin texture, 35mm analog film grain, muted brown tones, cinematic contrast, authentic vintage atmosphere. Add distressed off-white magazine typography around the image: “NOISE PRAYER”, “QUIET SIGNAL”, “SOFT STATIC”, “THE SIGNAL IS SOFT BUT IT STAYS.” Include scratched ink texture, dust, film imperfections, small typewriter text, arrows and minimal graphic markings. Vertical magazine-cover composition, highly detailed, photorealistic, nostalgic, mysterious, artistic, underground 90s editorial aesthetic, natural anatomy, realistic hands, no watermark.
YouTube Thumbnail - The Last Photo of Humanity — output

YouTube Thumbnail - The Last Photo of Humanity

Compound Learning - Tech | ScienceGPT Image 2
{
  "title": "The Last Photo of Humanity",
  "image_description": "A lone photographer stands on a rooftop taking the final photograph of Earth as gigantic evacuation ships leave the planet.",
  "subject": {
    "character": "{argument name="character" default="Photographer"}",
    "emotion": "{argument name="emotion" default="Acceptance, sadness"}"
  },
  "setting": {
    "location": "{argument name="location" default="Megacity Rooftop"}",
    "time": "Sunset"
  },
  "story_element": {
    "text": "LAST FLIGHT DEPARTING"
  },
  "cinematography": {
    "shot_type": "Wide Shot",
    "lens": "85mm Anamorphic"
  },
  "mood": ["Emotional", "Epic", "Cinematic"],
  "quality": "Hollywood Blockbuster, 8K"
}
Social Media Post - Parisian Night Seine Portrait — output

Social Media Post - Parisian Night Seine Portrait

TaarukGPT Image 2
A cinematic nighttime portrait of a {argument name="subject" default="beautiful young woman"} sitting alone beside the {argument name="location" default="Seine in Paris"}, with the {argument name="landmark" default="Eiffel Tower"} glowing softly in the distant background. She sits casually on a stone riverside ledge, body turned slightly away from the camera while looking back over her shoulder with a calm, confident, subtly melancholic expression. Long, naturally tousled dark brown hair flowing gently in the cool night breeze.

She wears an oversized dark chocolate-brown/black sweater or coat, relaxed cream-colored wide-leg trousers, and simple black leather flats. Natural minimal makeup, realistic skin texture, soft lips, expressive eyes, effortless Parisian style.

The Seine reflects warm golden city lights in long shimmering streaks. Background architecture and streetlights are heavily defocused into beautiful warm amber bokeh, while the deep navy-blue night sky creates strong contrast. The Eiffel Tower should remain recognizable but softly blurred and atmospheric, positioned behind her without dominating the frame.

Shot on 35mm analog film, candid fashion photography, low-light photography, subtle direct flash mixed with ambient city light, warm highlights, deep blue shadows, gentle film grain, soft halation, slight lens imperfections, natural exposure, realistic hair movement, authentic skin texture, nostalgic 1990s/2000s film aesthetic, intimate Paris-at-night mood, understated luxury, editorial street photography.

Composition: vertical 4:5 portrait, medium-full body framing, subject slightly off-center, generous negative space above, shallow depth of field, foreground light leaks and subtle haze, realistic proportions, photorealistic, cinematic, dreamy but natural, no excessive retouching, no artificial-looking skin.
Social Media Post - Indoor Fan Event Candid Portrait — output

Social Media Post - Indoor Fan Event Candid Portrait

AqsaGPT Image 2
A candid vertical portrait of a {argument name="subject" default="cheerful young woman"} at a {argument name="location" default="busy indoor fan event or shopping mall"}, smiling brightly at the camera while forming a small heart gesture with her hands. She has long dark brown hair with soft bangs and a small white hair clip, wearing a {argument name="outfit" default="black cropped jacket with fluffy white cuffs, a white inner top, and a high-waisted black pleated skirt"}. A large crowd of fans surrounds her in the background, many holding phones and cameras, with event booths and bright mall lighting creating a lively atmosphere. A blurred hand reaches into the foreground, adding authentic candid perspective. Bright indoor lighting, colorful ambient glow, shallow depth of field, realistic skin and hair texture, natural expression, slight smartphone-camera softness, energetic fan-meeting atmosphere, photorealistic, high detail, vertical composition.
Product Marketing - New York Street Coffee Portrait — output

Product Marketing - New York Street Coffee Portrait

mini singhGPT Image 2
Create an ultra-realistic close-up cinematic portrait of a {argument name="subject" default="stylish Asian woman"} on a modern {argument name="city" default="New York City"} street during the afternoon, holding a {argument name="beverage" default="simple elegant ceramic coffee mug"} with no logo, no branding, and no recognizable coffee-shop design.

Frame her from approximately waist/chest-up, with her face and coffee mug clearly visible. She has natural Asian facial features, realistic skin texture, detailed individual hair strands, subtle makeup, and a relaxed confident expression. She is casually holding the plain ceramic mug near her face/chest, with natural fingers and realistic hand anatomy. A small amount of authentic steam rises from the coffee.

The New York street background must remain sharp and highly detailed, rather than heavily blurred: modern glass buildings, contemporary storefronts, clean sidewalks, traffic lights, street trees, cars, pedestrians, café terraces, reflections in windows, and realistic urban activity. Maintain enough depth separation to keep the woman as the primary subject while allowing the entire city environment to remain clearly recognizable.

Lighting: beautiful natural afternoon sunlight, soft directional illumination on her face, realistic shadows, subtle reflections from surrounding glass architecture, physically accurate exposure.

Camera: close-up lifestyle street photography, 50mm lens, eye-level viewpoint, high-resolution full-frame camera, realistic depth of field but moderate background separation—not excessive bokeh.

Style: photorealistic, premium fashion-editorial street photography, cinematic realism, natural skin pores, realistic hair, authentic clothing textures, sharp environmental details, realistic colors, sophisticated modern urban atmosphere.

Important: plain unbranded ceramic mug only. No Starbucks-style branding, no logos, no text, no recognizable corporate designs, no watermarks.

Negative prompt: cartoon, CGI look, plastic skin, over-smoothed face, distorted hands, extra fingers, deformed mug, blurry background, excessive bokeh, warped buildings, duplicate people, unnatural anatomy, logos, text, watermark.
Game Asset - Anime Realistic Ninja Duo Portrait — output

Game Asset - Anime Realistic Ninja Duo Portrait

Zarnab AiGPT Image 2
A highly detailed anime-realistic cinematic portrait of {argument name="characters" default="two ninja-inspired characters"} standing back-to-back in a dynamic action pose. A blond, blue-eyed male character with spiky hair, a black forehead protector with a leaf symbol, three whisker-like marks on each cheek, and black-and-orange tactical clothing performs a hand sign. Beside him stands a beautiful young woman with long, wavy dark brown hair, soft facial features, brown eyes, and a confident expression, wearing a {argument name="outfit" default="black tactical ninja-style outfit with orange accents"}, utility straps, and a matching leaf-symbol shoulder patch, with her arms crossed. A katana is visible behind them. Clean white background with dramatic {argument name="accents" default="orange and yellow diagonal brush-stroke accents"}, sharp details, realistic skin texture, cinematic lighting, high contrast, polished anime-meets-photorealistic style, ultra-detailed clothing textures, dynamic composition, professional character poster aesthetic, 8K quality, crisp focus.
Comic / Storyboard - Handcrafted 3D Paper-Craft Travel Diorama — output

Comic / Storyboard - Handcrafted 3D Paper-Craft Travel Diorama

simeon-sanaiGPT Image 2
Create a premium handcrafted 3D paper-craft travel diorama centered around a little girl and her beloved doll on a magical journey.

adorable young girl doll character sitting on the upper edge of the diorama with her favorite small doll companion beside her. She wears a charming vintage travel outfit — a soft knitted cardigan, pleated skirt, little boots, cute hat, and a tiny backpack. She holds a miniature travel journal or map, while her doll is dressed in a matching outfit and carries a tiny suitcase.

The main scene inside the dimensional frame should represent {argument name="destination" default="Paris"} as a magical miniature world. Include its most recognizable architecture and landscapes, but reinterpret everything as handcrafted toys and paper sculptures: tiny buildings, colorful streets, flowers, trees, bridges, cafés, lanterns, local decorations, and a small pathway leading into the scene.

Add charming storytelling details:

The girl’s doll sitting beside her as her travel companion
Tiny suitcase covered with travel stickers
Miniature teddy bear peeking from the backpack
A tiny camera hanging around the girl’s neck
Small postcards and stamps scattered around the frame
A miniature paper airplane flying through the scene
A tiny map with a dotted route
Handcrafted flowers and plants around the foreground

Use a soft pastel vintage palette of dusty pink, warm cream, terracotta, muted teal, sage green, peach, and warm brown.

The entire artwork should feel like a luxury handcrafted children’s storybook mixed with a vintage travel scrapbook, using layered cardstock, paper quilling, embossed paper, miniature clay details, fabric textures, stitched leather accents, and delicate hand-painted surfaces.

Make the girl and her doll especially charming and expressive, with a cute collectible-doll aesthetic, oversized curious eyes, soft handcrafted facial details, and a warm adventurous personality.

Add a large raised plaque at the bottom reading:

{argument name="destination" default="Paris"}
{argument name="country" default="France"}

Surround the composition with subtle travel elements such as a compass, postage stamps, luggage tags, leaves, postcards, and a dotted travel route.

Soft warm studio lighting, realistic miniature shadows, tactile paper fibers, shallow depth of field, premium product photography, highly detailed handcrafted textures, whimsical cinematic atmosphere, elegant composition, cozy nostalgic feeling, museum-quality miniature diorama, 8K.

Avoid: photorealistic humans, plastic-looking 3D characters, excessive text, clutter, harsh colors, modern objects, generic fantasy scenery.
Social Media Post - Ancient Chinese Study Portrait — output

Social Media Post - Ancient Chinese Study Portrait

李岳GPT Image 2
9:16 vertical version, high-precision ancient Chinese fantasy boudoir makeup portrait, realistic refined character poster style. Oriental classical boudoir atmosphere, the image is gentle, delicate, noble, and soft. The subject is a young adult Oriental female, visual age about 20–28, with a soft oval face and bright almond eyes. The overall temperament is delicate and elegant. The makeup is {argument name="makeup style" default="peach water-light makeup"}, refined and high-end. Hair is long, straight, and black, partially draped and partially tied, decorated with pearl and gold ornaments. The attire is a {argument name="clothing color scheme" default="lotus pink pearl gold system"}, featuring light gauze outer robes and embroidered inner layers with clear details. The character sits at a desk in a half-length close-up, holding a scroll in one hand, looking down in quiet thought. The scene is {argument name="setting" default="begonia window / desk scroll / flower shadows on paper"}. The background shows wooden window frames, ink, brushes, and blurred begonia branches. The light is soft window light, warm white and natural, creating clear and bright facial features with gentle highlights on the silk and embroidery. Overall presentation: ancient fantasy boudoir beauty reading a scroll by the window.
Profile / Avatar - Hijab Fashion Editorial Portrait — output

Profile / Avatar - Hijab Fashion Editorial Portrait

Jahan ZaibGPT Image 2
Ultra-realistic vertical close-up portrait of a {argument name="subject" default="beautiful young woman"} wearing a {argument name="hijab style" default="soft pastel striped hijab"} and a flowing {argument name="outfit style" default="orange-and-white striped traditional outfit"}. She is positioned upright and naturally facing the camera, with her head straight and shoulders aligned, creating a clean, balanced portrait composition. She has fair luminous skin with realistic natural texture, softly flushed rosy cheeks, delicate facial features, long dark eyelashes, naturally shaped eyebrows, striking light hazel-green eyes, and glossy soft-pink lips. She looks directly into the camera with a calm, gentle, slightly dreamy expression. Her hijab is loosely and naturally wrapped around her head, featuring beautiful pastel mint green, powder blue, cream, and soft beige tones, with realistic fabric folds and fine textile texture. Her outfit features warm orange, peach, cream, and white vertical stripes, coordinated beautifully with the hijab. She is standing or sitting upright beside a simple muted gray interior wall. Warm natural sunlight enters from a nearby window, illuminating one side of her face and creating realistic highlights on her forehead, cheeks, nose, and lips. Soft architectural shadows fall naturally across the wall behind her, creating an artistic sunlit atmosphere. Straight camera orientation, upright composition, natural eye-level smartphone photography, face centered in frame, realistic perspective, authentic skin texture, subtle natural imperfections, soft sunlight, gentle shadows, cinematic realism, editorial Instagram aesthetic, photorealistic, ultra-detailed, 8K quality, vertical 3:4 aspect ratio.
E-commerce Main Image - Realistic Teacher in Math Classroom — output

E-commerce Main Image - Realistic Teacher in Math Classroom

AIVideoHub 🕊️GPT Image 2
Adjust the frame to a vertical 9:16 aspect ratio. Maintain the exact clothing style, color, fabric texture, stitching, and layering details of the light-blue denim cross-strap vest and off-white layered skirt from the reference image without changing the core design. The image should have a realistic, natural, high-definition, and soft photographic texture, featuring a young woman around {argument name="age" default="25 years old"}, approximately {argument name="height" default="160cm"} tall, with cool fair skin and long brown curly hair, wearing the same outfit and transparent heeled sandals. Remove all handheld items and bags. She wears a red work badge around her neck and is lifting her hand to explain, with a natural expression looking toward the front. The figure is complete and prominent. The background is a fresh and trendy classroom, with a black chalkboard on the left filled with math formulas, functions, and derivatives, and an electronic whiteboard on the right showing math problems with red annotations. A light wood lectern sits in the right corner with books and tablets. The overall tone is classroom white and chalkboard black with soft indoor light. The clothing is the focal point, creating a purchase-worthy look with no AI artifacts.
Infographic / Edu Visual - Lipstick Recommendation and Analysis Infographic — output

Infographic / Edu Visual - Lipstick Recommendation and Analysis Infographic

Derek Wen|德里克文GPT Image 2
You are a professional makeup consultant, image analyst, and infographic designer.

Please generate a "Lipstick Recommendation Report Infographic" based on the selfie uploaded by the user and the specified lipstick brand.

Objective:
Recommend 3-5 suitable lipstick shades based on the person's overall temperament, skin tone tendency, makeup suitability, and lip characteristics, and present them in a clear, professional way that matches the brand's identity.

Brand:
{argument name="brand name" default="Dior / YSL / Armani / Chanel / Tom Ford"}

The visual content includes the following structures:

1. Top-left area: User selfie and basic analysis
- Display the user's selfie avatar
- Extract skin tone tendency, overall temperament, and suitable color directions
- Summarize with short Chinese labels, such as: cool-toned, soft, commuting, powerful, etc.

2. Middle main area: Lipstick recommendation matrix
- Recommend 3-5 suitable lipstick shades
- Show the lip swatching effect for each shade
- Keep the same person, same angle, and same lighting, only changing the lip color
- Each shade is accompanied by a Chinese name or number
- Mark the color impression, such as: gentle bean paste, commuting nude red, temperament rose, brightening red-brown, date berry, etc.

3. Right or bottom area: Usage scenario suggestions
- Match suitable scenarios for each recommended shade
- For example: commuting, dating, shopping, banquet, photography, daily bare-faced look

4. Bottom summary area: Conclusion and suggestions
- Give summaries such as "most recommended color," "most versatile color," "best complexion-enhancing color"
- Write a short Chinese purchase or selection suggestion

Brand visual style should automatically match:
- Dior: Elegant French gray-white + silver accents
- YSL: High-contrast black-gold, sexy and strong
- Armani: Low-saturation gray tones, high-end and restrained
- Chanel: Minimalist black and white, rational and stylish
- Tom Ford: Dark luxury, cinematic feel
- Visual language can be extended automatically according to the brand

Visual Requirements:
- The overall look should resemble a high-end beauty consultant report or brand swatching analysis chart
- Chinese text must be clear and accurate
- Clean layout, complete information, suitable for social media sharing
- Keep the character identity consistent, only comparing lip color differences
- High-end style, avoid looking like common e-commerce screenshots

Note:
This is a visual recommendation based on image and temperament; do not make medical judgments or absolute conclusions.
Social Media Post - Jiangnan Night Hanfu Cinematic Photography — output

Social Media Post - Jiangnan Night Hanfu Cinematic Photography

AI设计钟师傅GPT Image 2
Theme: A carved wooden corridor overlooking the water on the second floor of a Jiangnan song tower under a moonlit night. A clearly adult woman leans against the carved railing, turning her head to look at the camera after hearing a soft call. Like a cinematic shot, a natural and beautiful Ming Dynasty Jiangnan photoshoot. Subject: Facial identity strictly follows the attached reference image: consistently matching facial features, proportions, skin tone, and overall identity; hairstyle, hair accessories, and expressions follow the current era, scene, and activity, without copying the reference's hairstyle or neutral expression. Body Anchors: She has a petite Korean fashion model figure, about 163cm tall, elegant feminine proportions, naturally charming yet realistic hourglass silhouette. She has naturally full and well-proportioned breasts with realistic volume, soft lower fullness, authentic weight, natural gravity, and believable soft tissue. Her body features narrow ribs, a slim and toned waist, soft rounded hips, full upper thighs, firm feminine limbs, and realistic anatomy. Each piece of clothing fits her body naturally with believable fabric tension, realistic folds, subtle compression, and authentic garment physics. Hairstyle, makeup, and expression are determined by the theme. Character/Expression: Makeup: Apricot pink milk tea amber makeup—gradient apricot pink milk tea eyeshadow, slight rose brown at the eye corners, low-saturation peach blush spreading from under eyes to the center of the face; Expression: Lost in thought by the window, features: eyes not fully focused, lips relaxed, face calm; Hairstyle and accessories: Classical half-up half-down style with jade ornaments, long black hair partially tied up, bun positioned at middle-low height, long hair falling naturally, a few stray hairs framing the face. Clothing/Pose: Clothing: Classical long dress with a cinnabar red to ivory white gradient, complete opaque inner layer with a low-shoulder neckline, wide draping water sleeves, sheer outer gauze, restrained gold thread embroidery, and era-appropriate back ribbons, clear but not overly tight waistband, paired with gilded flower branch hairpins, pearl tassel earrings, and thin gold bracelets; Pose: Leaning against the carved railing, turning back to look at the camera after hearing a soft call, environmental contact points providing slight support, weight mainly on one leg or the seating surface, the other limb naturally relaxed; Material Physics: Silk, gauze, thin silk, crepe, or cotton/linen retain their respective textures, metal ornaments only provide local reflections without altering the physics of the main fabric. Background/Lighting: Second-floor carved corridor of a Jiangnan song tower by the water at night. The environment includes only carved wooden railings, vermillion gauze curtains, gilded palace lanterns, a guqin (ancient zither), celadon wine sets, a sandalwood censer, and a screen. Dancers and musicians downstairs are soft, out-of-focus environmental layers. Outside the corridor, the moonlit sky and light-colored gauze curtains form a wide, soft main light, continuously illuminating the entire face. The face receives only one primary flash direction, with highlights rolling off continuously, avoiding random discrete spots or local bleaching. Composition/Lens: 70mm two-thirds body environmental portrait, lens height near the railing level, the figure's turning line and wide sleeves forming a diagonal, depth of the tower and the performance below softly blurred; 9:16 vertical aspect ratio, the figure located slightly left of center and occupying about 60%-72% of the frame, leaving negative space in the direction of sight or movement. Texture/Style: Portable CCD direct flash: 2000s portable CCD digital camera, 28–35mm equivalent close-range wide-angle, on-camera flash illuminating the subject, background one stop lower, limited dynamic range with minor highlight clipping, slight digital sharpening, cool/warm color cast, realistic shadow noise, and upload compression. Skin shows realistic pores and fine facial hair, natural skin tone transitions, clear hair details, believable fabric textures, and subtle digital noise with natural high dynamic range. A small handwritten signature 'Zhong' is naturally added in the bottom right corner. Negative: Avoid random facial spots, local bleaching, oily shine, point light sources, multi-colored light fragmenting facial features; avoid extra fingers, missing fingers, extra arms, deformed gestures; avoid underage look, baby face, plastic skin, oily highlights, excessive blurring, doll-like skin texture; avoid gibberish text, real brand logos, or watermarks that distract from the subject.
Comic / Storyboard - Oriental Papercut Art of Sacred Temple Bridge — output

Comic / Storyboard - Oriental Papercut Art of Sacred Temple Bridge

李岳GPT Image 2
9:16 vertical version, modern oriental female dreamscape 3D papercut art, modern oriental papercut art, layered paper cut illustration, dimensional paper sculpture, intricate paper carving, paper diorama, layered shadow box, epic oriental papercraft fantasy, poetic female dreamscape, contemporary oriental art poster. The theme of the work is 'She crosses a suspended sky bridge towards the center of the temple.' The core narrative of the scene is: a young oriental woman alone embarks on a long paper-art sky bridge floating above a sea of clouds, with a giant glowing paper-sculpture temple at the end of the bridge. She moves forward step by step, finally deciding to enter the center that only appeared in her dreams. The entire scene emphasizes a pilgrimage-like sense of progression, a vast high-altitude world, and the epic momentum of a paper-art mythological scene. The main character is an adult oriental woman with a visual age of about 25, bright, brave, quiet, and firm, with a sense of solemnity when facing the unknown temple. The character has a soft oval face, clear almond eyes, and gazes intently at the distant temple with a calm and determined expression. The character is not the main large-scale close-up of the scene but an emotional anchor in a huge world, and the proportions must be significantly small. Character hairstyle and headwear: long black hair naturally loose, the ends of the hair blown by the wind into slender flowing paper ribbons, wearing light gold leaves and small star-shaped hair accessories. The headwear is exquisite and light, not complex or tall. The long hair and silk drape extend behind her in the high-altitude wind, forming clear and elegant flowing lines. Character clothing: a layered paper-art long skirt in moon white and cyan-green, the hem unfolded in layers of leaves and cloud patterns, the silk drape slender and light, partially with light gold hollowed patterns. The clothing must have a multi-layered paper structure, fine hollowed edges, paper fibers, slight creases, real paper thickness, and a high-degree of handmade cutting feel. The hem and drape extend in the wind on the bridge, but do not block the perspective direction of the bridge. The dream carrier is: a suspended paper-art sky bridge. Dream imagery includes: sky bridge, cloud sea, temple, flying birds, distant mountains, glowing cloud layers. All bridges, temples, clouds, mountains, birds, and characters must be unified in a high-quality 3D paper sculpture language; realistic characters with paper-cut backgrounds or ordinary CG architecture are not allowed. The overall paper-cut structure adopts: a surrounding dreamscape style. Composition and camera requirements: the camera is located on the bridge surface, using a low-angle or eye-level shot, high-angle top-down shots cannot be used. The line of sight extends along the bridge surface toward the distant temple, forming a strong single-point perspective and epic depth. The sky bridge extends from the foreground at the bottom of the screen to the far center, leading directly to the temple. The bridge width is moderate but visually extremely long, with exquisite hollowed railings, suspension chains, carvings, and paper-art components on both sides. The character is located in a small position in the middle-lower part of the bridge, facing away from or semi-facing away from the camera, walking towards the distant temple. The character must be significantly smaller than the bridge and the temple to highlight the oppressive sense of the scene and the scale of the bridge. The main subject of the scene is an extremely long and narrow suspended paper-art sky bridge. The bridge body floats above an infinite sea of clouds, and the bridge surface is composed of silver-white, moon-white, and light-gold details, with rich oriental hollowed patterns, paper-sculpted railings, layered structures, and translucent edges. The bridge is not an ordinary small bridge but like a sacred bridge leading to the center of a divine realm, with exaggerated length and strong depth, making the viewer feel the distance and the sense of high-altitude danger. In the distance is a huge, multi-layered glowing paper-sculpted temple. The volume of the temple is much larger than the person and even much larger than the bridge entrance porch, possessing a clear sense of oppression and divine scale. The temple is composed of multiple halls, arches, towers, corridors, and a central glowing entrance, with a complex and exquisite structure, layered and situated between the sea of clouds and the mountains. There is a glowing doorway or main hall entrance at the center of the temple, becoming the final visual focus. The temple should be like the ultimate center in a dream, not a common courtyard building. On both sides of the bridge are a huge sea of clouds and high-altitude white space. The sea of clouds is composed of a large number of paper layers of different thicknesses, forming surging layers and a massive sense of volume. Distant paper-art mountains rise from the clouds, the peaks are cyan and misty blue, with fine gold-line hollowed decorations. A few birds may fly by in the high sky to enhance the sense of scale and airspace, but do not stack too many. The overall color scheme is: moon white, cyan-green, silver white as primary colors, with a small amount of light gold accents. Moon white is used for the bridge body, bright parts of the temple, outer layers of character clothing, and highlights of the sea of clouds; cyan-green is used for distant mountains, inner layers of clothing, and partial decorations; silver white is used for temple highlights, bridge surface highlights, and the sky atmosphere; light gold is only used for railing chains, hollowed patterns, clothing outlines, and partial highlights. The overall look must be bright, transparent, and clear, not gray, not darkened, not overall blueish, and not yellowish. Light and paper texture: bright daylight with a blend of cold and warm tones at high altitude illuminates the sky bridge and the temple, the edges of the bridge surface are slightly translucent, the shadow layers of the temple paper are clear, and the paper fibers and layered structures are exquisite and obvious. The distant temple entrance emits a soft but strong light, extending toward the foreground along the bridge. The bridge railings, character's shoulders, hair strands, and skirt edges have soft rim lighting. The paper surface must have clearly visible fiber textures, manual cutting marks, slight creases, layered shadows, and translucent edges, overall looking like a high-quality museum-grade paper sculpture art installation. The atmosphere of the image is: epic, solemn, sacred, vast, quiet, and firm. The focus is not on exaggerated character postures, but on creating a strong sense of pilgrimage and oppression through the extremely long sky bridge, giant temple, massive sea of clouds, and high-altitude space. The scene must look like a paper-art mythological epic scene, not an ordinary dreamscape.
Social Media Post - Reaching Hand in Neon Night Cityscape — output

Social Media Post - Reaching Hand in Neon Night Cityscape

Prompt アトリエ|AI画像プロンプトGPT Image 2
Subject:
Hand reaching towards the neon lights

Primary Subject:
A vertical wide-angle photo of a single woman in the lower right corner, leaning forward and reaching her right hand out significantly toward the camera beside a {argument name="location" default="downtown pedestrian bridge"}. She is wearing {argument name="clothing color" default="pink"} ruffled clothes, in a pose with one leg raised behind her, against a night road with cars and glowing signs.

Character/Expression:
The upper body and head lean heavily to the left of the frame, with {argument name="eye color" default="brown"} eyes looking up toward the camera, and glossy pink lips lightly closed in a serious yet soft expression. A small oval face with a rounded chin, large almond-shaped eyes, thin parallel eyebrows, and a small, well-shaped nose. Eyeliner extending from the outer corners of the eyes with pink lower eyelids and bright glossy skin. Long light-brown hair with thin bangs and large waves flowing over the left shoulder.

Clothing/Pose:
A short camisole top with a light pink floral pattern, thin shoulder straps, lace trim, and a ribbon tie at the chest. A pink belt and a short pleated skirt layered with sheer plaid fabric, lace, and ruffles. White high socks and white/pink platform sneakers. A pink shoulder bag with a small stuffed animal charm. She is holding a black handrail with her left hand, standing on her left leg with her right knee bent back and shoe raised to the lower left, extending her right arm toward the camera at the upper right of the frame.

Background/Lighting:
A large night street with cars lined up from the left to the center background, colorful vertical signs and window lights on both sides, and a single man standing in the right middle ground. In addition to the diffused light from streetlamps and signs, a soft white light source on the camera side brightly illuminates the face and torso. The background consists of blue dusk and warm-colored bokeh.

Composition/Camera:
3:4 vertical orientation, a wide-angle portrait with a strong high-angle view looking down at the subject. The person occupies a large portion from the bottom right to the center, with the extended right hand appearing extremely large in the upper right foreground, while the head and torso recede and appear smaller. The entire figure from head to the raised shoe is within the frame, with focus on the face and a slight blur on the hand and night scenery.

Texture/Style:
A photorealistic live-action photo with a flash feel. High-definition rendering of lace, transparent ruffles, metal charms, skin, road surface, and neon reflections, with a strong contrast between pink and the blue night.

Negative:
Do not make the foreground right hand small; do not lower the right leg raised behind.
Social Media Post - Girl in Yukata with Platinum Fireworks — output

Social Media Post - Girl in Yukata with Platinum Fireworks

春永睦月 Harunaga MutsukiGPT Image 2
{argument name="location" default="shrine stone steps"} with a {argument name="subject" default="girl in a yukata"} x {argument name="fireworks type" default="platinum fireworks"}
Infographic / Edu Visual - Photography Tutorial and Camera Setup Infographic — output

Infographic / Edu Visual - Photography Tutorial and Camera Setup Infographic

Loriel.AIGPT Image 2
Using [{argument name="reference image" default="Image 1 Reference"}] as the sole visual basis, generate a vertical 3:4 {argument name="teaching topic" default="street photography knowledge analysis chart"} (educational infographic poster). Goal: Use clear and interesting diagrams to explain "subject position, camera position, lens/distance, camera height, shooting angle, and composition points" for the purpose of teaching others how to recreate the shot. Overall style: Clean and high-end photography tutorial infographic + light scrapbook-style annotations; light off-white paper texture or light gray background; mainly black, white, and gray; automatically extract 1–2 colors from Image 1 as accents; sharp lines, high information density but not cluttered, unified alignment, and strong readability.

Mandatory Rules:
- Must preserve the following from Image 1: subject pose, relative position between subject and environment, main background structural lines, lighting direction, and spatial logic.
- Do not change the pose or the scene; only provide an "analytical diagrammatic presentation."
- Faces are not the focus: they can be lightly blurred/simplified, no realistic beautification, no emphasis on facial features.
- Full Chinese; no English, no brand names, no watermarks, no UI interface elements.

Fixed Layout (remains the same every time, does not change with Image 1):
1) Main Visual Area (upper half or large image on the left): Place the "Reference Scene Display" (lightly stylized/illustrated based on Image 1, but with recognizable scene and posture), overlaid with: rule-of-thirds grid, subject outline box, leading line prompts, vertical/horizontal line correction prompts; use numbered dots + hand-drawn arrows to mark key points (subject landing point, negative space direction, leg extension direction, background leading line source).
2) Diagram Area (two side-by-side images on the right or bottom half):
- Top View: Use minimalist icons to draw wall/street/building boundaries (abstracted from Image 1), subject position (person icon), camera position (camera icon); must show shooting direction arrows, distance between subject and camera (dashed line + numerical range), recommended position points A/B (two alternative positions); camera orientation must match Image 1 (front/side/oblique, etc.).
- Side View: Draw ground line, subject height示意, camera height示意, tilt angle sector; must show camera height range from ground (reasonably inferred from Image 1), lens tilt angle range (reasonably inferred from Image 1); low angle/eye level/high angle must be correct.
3) Parameter Card Area (three fixed rounded-corner cards at the bottom):
- Card 1: Lens and Distance (give recommended equivalent focal length range + shooting distance range).
- Card 2: Camera Height and Angle (give camera height range + tilt angle range).
- Card 3: Pose and Body Points (summarize key points of the pose in Image 1 using short sentences).
4) Error Demonstration Area (fixed at the bottom right): 3 red-cross error prompts (automatically generated based on the most relevant issues in Image 1, short sentences), for example: don't use ultra-wide angle too close to the face, don't crop toes/fingers, don't use a camera position that's too high resulting in distorted proportions (adjust automatically based on Image 1's actual situation).

Automatic Inference Requirements (to make it usable for any replacement of Image 1):
- Automatically infer and write into the diagrams based on Image 1: camera orientation, camera height, shooting distance interval, equivalent focal length interval, subject landing point and cropping strategy, background leading line source.
- All numerical values should be expressed as "ranges" (credible and reproducible), do not provide a single fixed number.

Output Requirements:
High definition, sharp lines, natural shadows, unified icons, neat layout, readable information; no garbled text, no logos, no watermarks, no excessive decoration.

Negative Constraints:
No watermarks, no logos, no English, no garbled text, no overly realistic faces, no exaggerated cartoon proportions, no limb deformities/extra fingers, no cluttered layouts, no low resolution, no heavy filters, no changes to the subject pose or scene relationship of Image 1.
Comic / Storyboard - Three-View Character Reference Sheet Layout — output

Comic / Storyboard - Three-View Character Reference Sheet Layout

h64gGPT Image 2
A {argument name="aspect ratio" default="2:1 horizontal"} image. Divide the whole into left and right, with the left being 25% of the total width and the right being 75%. The right side is a 3:2 area using the full height, containing a three-view diagram on a {argument name="background color" default="gray background"} arranged side-by-side in the order of front, side, and back. The three-view diagrams should all be {argument name="standing poses" default="standing poses"} where the full body is visible. However, in all three cuts, the top should be cut slightly below the jaw, showing only from the jaw down. Everything above the neck is completely out of frame, and the face, head, and hair are not shown at all. The left side is divided into two parts, top and bottom, with two squares of the same size. Both are close-ups of faces on a gray background. The top shows a serious expression facing the camera, and the bottom shows a face looking away. The three-view diagram on the right is configured for full-body costume verification.
E-commerce Main Image - Pistachio Crochet Cardigan and Plaid Mini Dress — output

E-commerce Main Image - Pistachio Crochet Cardigan and Plaid Mini Dress

MoodLock|AI画像の惜しいを直すGPT Image 2
Wardrobe: Outerwear / layers: One solid pistachio short-sleeve crochet cardigan built from fine softly matte yarn. Upper-hip length with a close straight body, lightly shaped waist, and two independent front panels. A deep rounded V opening continues into narrow scalloped front bands. Two short set-in sleeves have compact fitted upper sections, softly expanded lower edges, and narrow scalloped cuffs. The body and sleeves use a consistent openwork construction of slim vertical chain ladders alternating with dense shell-like crochet columns, preserving small irregular apertures and a clearly fibrous looped surface. A narrow scalloped crochet border completes the neckline, both front edges, cuffs, and lower hem. Five evenly spaced pistachio four-hole buttons run down one front band, with aligned crochet buttonholes on the opposite band; all five buttons remain released. Keep the open cells distinct, the shell columns vertically coherent, the front panels balanced, the buttons flat and evenly aligned, and the soft yarn texture clean rather than fuzzy or melted together. Dress / all-in-one: One olive-green, smoky-charcoal, muted-lavender, beige, and black spaghetti-strap mini dress made from lightweight fine-gauge semi-sheer mesh with soft fluid drape. Across the complete plaid shell, an all-over oblique multiscale check places broad smoky-charcoal bands, narrower muted-lavender bands, and fine beige lines over an olive ground, creating a regular field of unequal rectangular cells with stable band order and crisp intersections. The dress is close through the shaped bust and waist, then widens immediately below the fitted waist into a full upper-thigh-length skater skirt with rounded fluid flare and unpleated volume. The front upper edge forms a deep sweetheart V from two shaped bust panels, while the rear upper edge follows a low soft curve. Shaped front, side, and rear bodice panels continue below the curved underbust line, and the fitted torso releases into the full bias-cut skirt with evenly distributed soft folds. Two very narrow constant-width straps join the upper front corners to corresponding rear anchors. Black scalloped floral lace traces the complete bust edge and rear upper edge; a broader black scalloped lace band follows the curved underbust seam, with a compact flat black ribbon knot at the center front. A narrow black mesh binding finishes the full undulating hem. Elastic recovery in the lace bands and pliant bias mesh forms a clean pull-on closure with a continuous fitted upper circuit. The rear lace edge and underbust band continue uninterrupted between the paired strap anchors, and the checked skirt retains its full flare across the rear. Preserve the fine mesh grain, slight translucency through single layers, denser tone at overlaps, delicate lace openwork, crisp scallops, slim seam allowances, stable check-band widths, and thin flexible edge depth throughout. Footwear: One matching pair of solid dark brown platform Mary Jane shoes built from smooth low-luster structured upper material with shallow natural creasing, clean rounded edge returns, and dense molded dark brown rubber at the base. Each shoe has a broad rounded-square overall front envelope and a low substantial platform profile. The low upper opening has a shallow curved rear arc and continues forward into two narrow transverse unfilled instep slots. A broad rounded-square closed toe box and low side quarters form the upper, while a one-piece platform sole follows the full perimeter, projects slightly beyond the toe and sides, and combines a softly rounded sidewall with a nearly level lower profile and a low integrated heel. One wide flat crosswise instep strap spans between the two open slots and anchors directly into both side quarters. The anatomical mirror counterparts use identical toe width, opening geometry, strap position, upper-panel seams, platform depth, and edge finish. Keep the toe boxes broad but not bulbous, the strap planes flat, the instep slots sharply bounded, the upper surfaces smooth, and the sole sidewalls dense and cleanly molded. Belt: Styling: - Belt placement: Place the complete belt as one flat diagonal closed circuit on the outermost surface of Mini dress, with the wearer-left upper-hip side distinctly lower than the wearer-right side. Maintain the same wearer-left-downward diagonal across the front and back; do not mirror it to image-left or twist the band. Preserve any separately selected buckle or knot position and tail treatment, and do not invent unregistered hardware. One pistachio crochet cord belt built from a long slender round braided cord and a dimensional yarn rosette. The flexible cord forms one complete adjustable circuit and retains a consistently narrow circular section. A large rosette is constructed from three concentric tiers of tightly crocheted scalloped petals around a compact spiral center. Two narrow unequal free tails end in clean bound yarn terminals, with the longer tail substantially exceeding the rosette diameter. Beside the rosette, the cord and tails are secured into a compact single-loop knot. Keep the cord smooth and untwisted, the knot compact, the petal tiers clearly separated, the spiral center legible, and the yarn color and stitch scale consistent across every component. Necklace: One fine silver-tone oval-link pendant necklace with a compact single-loop envelope; the pendant is distinctly broader than the chain and its drop remains short compared with the complete chain circuit. Small polished black bead stations punctuate the fine link path. The central pendant is a solid polished black heart with two rounded upper lobes and one clean lower point, framed by a narrow silver-tone rim and joined to the chain by a compact polished bail. Keep the links fine and individually resolved, the bead stations spherical, the heart face smooth and opaque, the rim uniform, and the metal joins precise with controlled reflections. Earrings: One matching pair of small pale warm-gold-tone round stud earrings, each constructed with one compact domed front face carrying subtle fine textured relief, one concealed straight post, and one matching friction clutch. Keep both earrings identical in diameter, section thickness, mounting depth, color, finish, and fastening construction. Complete the rear surfaces, post anchoring, clutches, hidden joins, and polished edges as one coherent matching pair with no chain, drop, pearl, colored enamel, readable branding, or additional component. Preserve precise bilateral matching, clean circular geometry, secure post construction, consistent relief depth, uniform plated finish, and restrained material-correct highlights. Bracelet: Styling: - Bracelet placement: VIEW-CONDITIONAL HARD SIDE MAP — choose one case by facing direction. FRONT OR NEAR-FRONT: IMAGE-RIGHT wrist = TARGET and IMAGE-LEFT wrist = NON-TARGET. BACK OR NEAR-BACK: IMAGE-LEFT wrist = TARGET and IMAGE-RIGHT wrist = NON-TARGET. PROFILE, CROSSED ARMS, OR AMBIGUOUS IMAGE SIDE: trace the subject's left arm from the left shoulder to its wrist; do not choose by screen side. TARGET is always the subject's anatomical left wrist; NON-TARGET is the anatomical right wrist. Render one complete instance of the registered bracelet item described directly below around TARGET only; keep NON-TARGET free of this bracelet and do not duplicate it. Preserve the registered design and count. Keep other separately selected wrist items unchanged. One delicate gold-tone chain bracelet with a fine flexible closed circuit and a sparse sequence of small translucent oval beads separated by exposed chain spans. The bead sequence alternates emerald green, pale rose, and deep plum accents, each bead secured by tiny gold wire loops and remaining distinctly la
Browse by model, style or topic

Find your next direction

ASTORIE CANVAS

Take the idea further.

Bring your prompts, references and results together in one creative space.

Open your canvas ↗