Photography image prompts.

Using REFERENCE_0 as the character base, generate a 3x3 grid collage containing exactly 9 distinct images. The aesthetic should mimic amateur smartphone photography (candid snapshots) rather than polished digital art. Layout & Content: - Create 9 separate panels arranged in a square grid. - Locations: Mix of bedroom (messy background), classroom (desks/chalkboard), and outdoor park (swings/sky). - Outfits: Change the character's clothing to casual streetwear (hoodies, t-shirts, caps) or winter wear (scarves). Do not strictly keep the uniform. - Poses/Actions: Include specific scenarios such as holding a black cat, taking a mirror selfie with a phone covering part of the face, eating a strawberry tart, sitting on a swing, lying down on a desk, and close-ups with fingers partially blocking the lens. Style Constraints: - Apply realistic lighting effects like sun glare, indoor shadows, and slight motion blur to enhance the 'snapshot' feel. - Keep the character's facial features (eyes, hair color/style) consistent with REFERENCE_0 but rendered in a more realistic/anime-hybrid style typical of AI photo generation.

Create a high-fashion urban streetwear photo of {argument name="model description" default="a confident young woman with a short black bob haircut and medium tan skin"} standing in a gritty concrete tunnel at night. Use an extreme low-angle, ground-level perspective with a wide-angle lens so one sneaker sole dominates the foreground as she steps toward the camera, creating dramatic foreshortening. She wears exactly 4 visible outfit pieces: an oversized black hoodie with a large white abstract square logo on the chest, distressed charcoal-gray baggy cargo pants with multiple flap pockets and metal D-rings, black-and-white skate sneakers with thick white soles, and black hoodie drawstrings. Her pose is assertive and relaxed, one hand in her pants pocket, chin slightly raised, looking directly down at the camera with a calm serious expression. The setting is a wet underpass with rough stained concrete ceiling and walls, graffiti on the right wall in black and orange, warm wall lights glowing along the tunnel, distant city lights at the far end, and rain-slick pavement reflecting amber light. Emphasize premium fashion editorial realism, crisp clothing texture, worn denim details, rubber waffle sole pattern, shallow depth of field, moody cinematic lighting, realistic skin, high contrast, vertical composition, no text overlay, no watermark. Customize the hoodie logo as {argument name="hoodie logo" default="a bold white rounded square mark with a black center"}, the pants as {argument name="pants style" default="distressed charcoal-gray baggy cargo pants"}, the location as {argument name="location" default="a graffiti-covered concrete underpass at night"}, and the lighting mood as {argument name="lighting mood" default="warm amber streetlights reflected on wet pavement"}.

Using the provided reference image as the character base, generate a 3x3 grid collage in a 9:16 aspect ratio. The goal is to create a collection of 'failed' or amateur-style camera roll photos featuring this character throughout an entire day. Each panel should depict a candid, unpolished moment (e.g., eating, looking at a phone, walking on pavement) with realistic lighting and casual poses. Do not include any text overlays.

Goal: Create a vertical smartphone screenshot of an iOS photo gallery grid displaying a collection of surreal images. Canvas: A mobile interface with a white top bar containing a blue back arrow and three dots, and a bottom toolbar with four icons (Photos, Heart, Info, Trash). Layout: A dense 4-column by 5-row grid of square thumbnails. The subject in every thumbnail is the same character: a muscular male body with a large, textured granite boulder replacing the head. Sections: 1. Top Row: The boulder-head man lying in bed, brushing teeth in a mirror, flexing muscles at a window, and holding a black mug. 2. Second Row: Walking away on a city street with a backpack, shopping in a grocery aisle, checking out at a register, and drinking an iced coffee. 3. Third Row: Waiting for a train, eating ramen with chopsticks, taking a shirtless mirror selfie, and sitting on a park bench. 4. Fourth Row: Shopping for produce, petting a tabby cat, walking down a sunset alleyway, and standing in rain puddles. 5. Fifth Row: Eating dinner, sleeping in bed, walking through blurry night lights, and showering under water spray. Visual style: Photorealistic, cinematic lighting, high definition, slightly humorous but serious tone. The boulder texture must be consistent across all frames. Constraints: Ensure the grid layout is perfectly aligned with thin white gutters between images.

A hyper-realistic, vertical close-up shot of a young Asian man with messy black hair and rectangular glasses, wearing a black t-shirt. He is holding a smartphone up to the camera with an expression of shock and awe, his mouth slightly open. The screen of the phone displays a stunning 'augmented reality' scene where two miniature anime-style girls are standing on a wooden deck inside a lush tropical jungle. The girls have long dark hair, wear black jackets over white tops and skirts, and look like they are interacting with their environment. Green ferns and plants from the phone's screen appear to be growing out of the device, blending into the real world. In the blurred background, there is a computer monitor displaying colorful anime wallpapers.

Late 1990s disposable-camera flash photograph of the woman from the reference sheet, same face and hair, sitting at a small outdoor trattoria table on a harbor at blue hour. Harsh direct on-camera flash lights her face and bare shoulders while the background falls into deep navy dusk with warm string lights and moored fishing boats. She wears a black slip dress and a thin gold chain, hair slightly wind-messy, mid-laugh, one hand holding a glass of lemonade, a half-eaten plate of pasta on a red checkered tablecloth in front of her. Slight overexposure on skin, hard flash shadow behind her head, soft focus, heavy grain, faded magenta-green color shift, an orange digital date stamp reading "08 14 '98" in the lower right corner. Palette 45% deep dusk navy, 35% flash-lit warm skin and white, 20% tablecloth red.She laughs and tilts her head back, then looks straight at the lens and raises her glass toward camera. String lights sway in the harbor breeze and boat masts rock behind her. Camera: handheld and close, with slightly clumsy framing, like a friend filming across the table. Hard flash-like light on her face against the dark dusk background. Sound: laughter, cutlery, soft harbor water, a distant accordion.

{argument name="subject" default="old man"} {argument name="style" default="camera roll style photo"}

A split-screen comparison image demonstrating AI image editing capabilities. The left side shows a woman in a dark charcoal blazer holding a silver cylindrical product container against a white geometric background. The right side shows the identical scene with only one change: her blazer is now bright lime green, while all other elements remain exactly the same. At the top center, bold black text reads "CHANGE ONE THING. KEEP THE REST." Four circular detail insets at the bottom show close-ups of textures: brushed metal surface, skin texture near eye, dark fabric weave, and green fabric weave. Professional studio lighting, clean minimalist aesthetic.

A lone {argument name="warrior type" default="Japanese female warrior"} in a weathered {argument name="clothing color" default="off-white"}

A breathtaking, hyper-realistic portrait of a young Asian woman in profile, looking back over her shoulder. She is dressed in an exquisite kimono featuring a double-exposure design that blends the fabric with a serene landscape painting of a five-story pagoda, misty mountains, and autumn trees. Her hair is elegantly styled in a loose updo adorned with vibrant red maple leaves. The scene is set against a warm beige background dominated by a large, detailed full moon on the right, across which a flock of wild geese flies in formation. Swirling ink-wash effects and gold leaf accents mix with falling maple leaves to create a dynamic, ethereal atmosphere. A traditional red seal stamp is visible in the upper right corner.

Transform any input travel photo into a standalone 3:4 vertical comparison poster. The top half fully preserves the original real travel photo, maintaining location, architecture or landscape, composition, perspective, subject count, pose and environmental relationships, with only slight publication color grading; use a thin, clean white horizontal divider line in the middle. The bottom half rebuilds the same scene as a realistic shootable physical brick miniature 3D model, using plastic bricks with one-by-one stud bumps, connection seams, and clear part edges, accurately preserving the main outlines, spatial hierarchy, and iconic elements of the original photo, but actively shrinking subjects, simplifying backgrounds, and reorganizing into a complete small tourist scene model. The model must have the real structure of physical bricks: stud bumps, splicing seams, wall thickness, steps, baseplates, roofs or terrain undulations, transparent window parts, miniature vegetation, and contact shadows. The model scale is relatively small, leaving whitespace around the desktop, using slight tilt-shift macro photography depth of field. Brick colors are extracted from the original photo, not fixed to island blue; buildings, streets, bridges, mountain villages, cities, natural landforms, or character scenes are all applicable. The bottom half can only use elements truly visible in the original photo, do not arbitrarily add waves, palm trees, boats, landmarks, or people. Must form a clear 'Real Photo - Physical Brick Model' top-bottom contrast relationship. Do not make it pixel art, voxel rendering, mosaic, block filter, low-poly CGI, smooth clay, paper craft, felt, oil painting, watercolor, flat illustration, or ordinary cartoon; do not apply a brick texture to the entire photo. No text, titles, subtitles, original/AI image corner marks, logos, watermarks, decorative borders, no stitching multiple photos.

A cinematic, photorealistic portrait of a young East Asian woman with long, dark brown hair styled in loose waves. She is wearing a tight-fitting black mini dress with spaghetti straps and tall black leather high-heeled boots. She leans casually against the front fender of a glossy red sports car (resembling a modern coupe) inside a dimly lit underground parking garage. The concrete floor is wet, reflecting the overhead fluorescent lights and the red taillights of cars in the background. The lighting is moody and dramatic, typical of a K-pop music video aesthetic, with cool tones contrasting against the warm red of the car.

A {argument name="subject" default="ballet dancer"} photographed from an extreme low-angle ground-level view, camera positioned near the floor and tilted upward, standing alone in an off-white studio void, confident pose, dominant elongated silhouette, stylised proportions, sleek fashion styling, reflective textures, bold accessories, soft studio light, single beauty-dish flash casting crisp shadows, subtle Kodak Portra-inspired grain, candid editorial energy, minimalist composition, sharp detail, premium studio photography

A man standing with his {argument name="left leg position" default="LEFT foot forward"} and {argument name="right leg position" default="RIGHT foot back"}.

Use the {argument name="character reference" default="uploaded character reference image"} as the strict identity and outfit reference. Preserve the reference character’s: face identity, facial proportions, eye shape, nose, lips, skin tone, hairstyle, hair color, visible hair accessories, overall recognizable vibe, outfit and styling shown in the reference image. Do not hardcode any specific character traits that are not present in the uploaded reference. All identity, hairstyle, accessories, and clothing details must be inferred directly from the uploaded reference image. Create a high-quality mixed-style vertical portrait showing: 1. a realistic full-body version of the uploaded character/person 2. a black hand-drawn doodle-shadow version of the same character/person on the wall beside them. Core concept: The real person and their doodle-shadow are doing a {argument name="pose" default="playful mischievous pose"} together. The real person performs a cute realistic version of the pose, while the doodle-shadow performs a much more exaggerated, chaotic, cartoonish version of the same pose idea. The mood should feel cute, playful, mischievous, stylish, funny, and social-media-friendly. Real person: Must remain realistic and photogenic, wear the same outfit style and key visible details from the uploaded reference image. Expression should be {argument name="expression" default="cute, slightly confused, mildly embarrassed, playful"}, as if thinking: “Why am I doing this with my shadow?” Doodle-shadow: Must be a black hand-drawn sketch version of the same person, drawn directly on the wall. Black sketch line-art only. Should resemble the person through hairstyle silhouette, accessories, outfit silhouette, and pose structure. Add manga-like motion lines, hearts, stars, sparkles, and comic marks around the doodle if helpful. Create a different mischievous pose each time. Possible pose directions: playful idol pose, silly dance pose, leaning sideways with one arm curved overhead.

Style: An Instagram story-style photo of {argument name="character" default="Albedo"} cosplay; Content: {argument name="action" default="squatting on the ground facing the camera, making exaggerated rebellious gestures with both hands, rolling eyes, with an arrogant and disdainful expression"}

Create a highly realistic vertical portrait photo of {argument name="character name" default="a beautiful Japanese woman in her 20s"} at a summer evening fireworks festival in Japan. She is shown from the waist up in a three-quarter back-facing pose, turning her head over her shoulder to smile warmly at the camera, with natural expressive eyes, soft skin texture, and an approachable candid expression. She wears a pale cream-pink yukata with purple and lavender floral patterns, a large beige obi bow tied at the back, and small pink and cream chrysanthemum hair ornaments tucked into a low updo with loose bangs and face-framing strands. Her right hand holds a small floral drawstring kinchaku pouch with thin red cords. The setting is a crowded Japanese matsuri street at dusk, lined with glowing food stalls and red-and-white festival banners, warm paper lanterns, and many festivalgoers in colorful yukata walking away in the background. Above her, the blue twilight sky is filled with large bright fireworks bursts in pink, purple, white, and gold, slightly blurred by depth of field but still dramatic and luminous. Use a close 3/4 portrait composition, subject centered slightly right, shallow depth of field, realistic lens perspective, warm lantern light on her face and yukata, cool blue ambient evening light in the sky, cinematic color grading, crisp detail on the woman and soft bokeh background. Emphasize photorealism, natural human proportions, realistic fabric folds, authentic Japanese summer festival atmosphere, and a joyful romantic mood. Avoid extra text, logos, watermarks, distorted hands, plastic skin, over-smoothed face, or anime styling.

A realistic indoor portrait photo of a young East Asian woman seated on a light beige fabric sofa in a softly lit modern living room, framed from the chest up in a casual selfie-like composition. She has long, straight {argument name="hair color" default="dark brown"} hair with a side part, smooth natural skin, and a slim build. Her face is fully covered by a large square mosaic blur censor block centered over the head, obscuring all facial features while leaving the hairline, ears, jawline edge, and neck partially visible. She wears a simple {argument name="top color" default="white"} ribbed long-sleeve knit top with a round neckline and exactly 3 small front buttons visible. Her posture is relaxed, slightly leaning toward the camera, with one arm implied to be extended to take the photo. The background shows 1 bright window at the far left with sheer daylight, 1 beige curtain, and the neutral sofa wrapping behind her. Soft natural daylight from the left, muted warm-gray walls, minimal home interior, shallow depth of field, clean realistic photography, understated candid atmosphere, no text, no accessories, no dramatic styling.

A formal Japanese-style passport or ID photo of a young adult woman, chest-up and centered, facing straight toward the camera with a neutral professional expression, on a clean light gray studio background. She has straight dark brown to near-black hair, smooth and glossy, parted slightly off-center near the top, with the hair falling evenly past the shoulders on both sides. Her ears are partially visible, with no noticeable accessories. She wears a tailored black business blazer over a plain white crew-neck blouse, creating a conservative job-application or official-document look. The lighting is soft, even, and frontal with minimal shadows, high sharpness, natural skin tones, and a realistic photographic finish. Composition is symmetrical and tightly cropped like an ID photo, showing the top of the head, shoulders, neckline, and upper chest. No smile, no dramatic styling, no props, no text, no border, no background details.

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

Create a hyper-realistic HD portrait of a {argument name="subject" default="confident young professional businesswoman"}, {argument name="outfit" default="elegant modern black blazer over a white blouse"}, standing in a {argument name="setting" default="premium futuristic office with glass walls"}, subtle AI technology screens and a city skyline in the background. Natural makeup, polished hairstyle, confident expression, professional corporate appearance, cinematic soft lighting, realistic skin texture, shallow depth of field, luxury business atmosphere, sophisticated blue-and-white tones, ultra-detailed, photorealistic, 8K quality, sharp focus, premium LinkedIn and AI startup branding aesthetic, vertical 4:5 composition, no text, no watermark.

Create a photorealistic vertical street-fashion photo of an {argument name="model age" default="adult young woman in her early 20s"} walking through the interior lobby of a modern cinema complex in Shinjuku at night. Use a low-angle, full-body perspective from near the glossy black floor, with the subject centered and slightly towering in the frame, one foot stepping forward naturally. She wears a Japanese school-uniform-inspired outfit: navy button cardigan over a white shirt, striped bow tie, very short dark pleated skirt, navy knee-high socks, and black glossy loafers. She carries a black shoulder bag on her right shoulder with a small beige teddy bear charm hanging from it, and holds a smartphone loosely in her left hand. Her long straight dark hair falls over her shoulders; her face is softly anonymized/blurred with no distinct facial features. The setting is a sleek movie theater corridor with reflective polished flooring, cool blue ambient lighting, escalators and a few distant pedestrians in the background. On the left wall, include large illuminated movie posters and a black cinema sign reading “109 CINEMAS PREMIUM SHINJUKU”; one poster prominently shows the date “4.25” in pink. Use realistic lens distortion and depth of field, crisp clothing and accessory details, natural walking posture, cinematic indoor lighting, reflections on the floor, and no watermark.

Goal: Create a realistic vertical smartphone social-media video screenshot of an after-school classroom scene, styled like a Japanese short-video app post. Canvas: 9:16 vertical image, 675×1125 style composition, natural daylight, realistic phone-camera look, slight wide-angle perspective, high detail, no illustration style. Main scene: In a Japanese high school classroom after school, show exactly 2 foreground teenage girls in summer uniforms. The central girl is fully visible from head to mid-thigh, looking directly at the camera with a shy smile, holding a beige smartphone with small cute stickers partly covering her mouth. She has straight {argument name="hair color" default="dark brown"} shoulder-length hair with thin bangs, soft natural makeup, and large expressive eyes. Her left hand holds the strap of a navy shoulder bag. The second girl stands cropped on the right edge, visible from half of her face down to her skirt, smiling gently toward the camera. Uniform and accessories: Both girls wear crisp white short-sleeve button-up shirts, navy-and-green plaid pleated skirts, and navy striped ribbon bow ties. The central girl carries a glossy navy school bag covered with exactly 8 visible plush keychains and charms: 1 large cream teddy bear, 1 smaller white teddy bear, 1 cream bear with pink bow, 1 fluffy white animal charm, 1 lavender plush charm, 1 pink plush charm, 1 small beige tag charm, and 1 metal chain charm. Background: A busy classroom with wooden desks and chairs, chalkboard on the back right, tall windows on the left with bright daylight. Include exactly 6 background students in white shirts: 2 seated at desks near the left foreground with backs/side views, 1 standing or leaning near the windows, 2 seated near the middle-back, and 1 seated near the chalkboard. Keep them softly out of focus compared with the foreground girls. App overlay layout: Add a short-video app interface overlay on top of the photo. Right-side vertical action bar with exactly 5 stacked elements: 1 circular profile thumbnail with a pink plus badge, 1 white heart icon with count “3.2万”, 1 white speech-bubble icon with count “162”, 1 white share arrow icon with count “392”, and 1 small circular spinning-record thumbnail at the bottom. Bottom-left caption area contains the username and post text in white Japanese text: “@{argument name="username" default="yui._.daily"} ・ 3時間前”, then “{argument name="caption text" default="放課後の教室ってなんか特別だよね🧸"}”, then “{argument name="hashtags" default="#jk #放課後 #クラスメイト #日常"}”, then a music line with a musical note icon: “オリジナル楽曲 - yui._.daily”. Bottom black comment bar contains placeholder text “すてきなコメントを書く...” plus exactly 2 icons on the right: an @ symbol and a smiley face. Visual style: Photorealistic Japanese teen lifestyle snapshot, warm natural lighting, clean skin texture, realistic fabric folds, accurate hands and fingers, believable classroom depth, subtle social-media compression, candid but polished. Constraints: Preserve the exact counts of foreground girls, background students, plush charms, and overlay elements. Keep the image wholesome and non-explicit. Do not add extra people in the foreground, do not add watermarks, and avoid distorted text or broken hands.

A highly realistic casual smartphone selfie taken indoors at a McDonald's restaurant in Asia, framed as a chest-up portrait of a young man seated at a table. The camera is held slightly above table height at arm’s length, creating a natural front-facing selfie perspective with one forearm extending toward the lens. The subject wears a black T-shirt with a small white Tesla logo on the left chest, has short straight black hair, thin dark eyeglass frames partly visible, and rests one hand lightly against his chin in a relaxed pose. His face is fully obscured by a large solid rectangular blur block in the center, preserving privacy while leaving the hair, ears, jawline edges, and glasses arms visible. In the lower left foreground sits 1 white McDonald's paper drink cup with a lid and a white straw, cropped by the frame. The background shows the restaurant counter area with warm ambient lighting, 1 large red wall panel on the left featuring the yellow McDonald's arches and the white slogan “i’m lovin’ it” with Chinese text below, 4 illuminated digital menu boards across the top displaying burgers, fries, combo meals, prices, and Chinese text, plus 2 people in the background near the counter, one facing away with a backpack and another partially visible behind the register. Use natural color balance, slight indoor grain, realistic reflections, shallow to moderate depth of field, and the candid look of an unstaged social media snapshot.

A candid, highly realistic smartphone photo inside a busy Sam’s Club warehouse store in China. Center the composition on a young East Asian man from mid-torso up, standing upright and facing the camera, with his face obscured by a rectangular blur block for privacy. He wears a plain black short-sleeve T-shirt with a small white Tesla logo on the left chest and holds a large clear plastic bag of red apples in his left hand, tied at the top with a blue band. The apple bag has a white label reading “envy” with small Chinese text beneath it. Behind him is a bright retail interior with tall industrial ceilings, warehouse shelving, shoppers, shopping carts, and stacked produce displays. Prominently show the blue diamond Sam’s Club wall sign at upper left with the text “Sam’s CLUB” and “山姆会员商店,” and a large blue wall banner behind him reading “更好的生活尽在山姆” and “Life is Better in the Club.” On the upper right, hang a tall white vertical banner that reads “优质优价” and “Great Products Great Prices,” with blue and green geometric accents. Include many background customers, slightly out of focus, to create an authentic crowded shopping atmosphere. Lighting should be bright, even retail overhead lighting; colors natural; perspective eye level; documentary snapshot aesthetic; sharp foreground subject with mildly softened background; portrait orientation.

Using this product as inspiration, design a set of {argument name="style" default="cool-style"} women's clothing

Using REFERENCE_0, restore the old damaged family photo into a clean, high-resolution modern scan. Remove the heavy scratches, stains, fading, tears, and surface damage while preserving the original composition, pose, framing, and background curtain. Reconstruct realistic natural skin tones, sharpen details, and colorize the image with believable warm indoor tones. Keep the woman holding the baby in the same position, restore the black sleeveless dress, the baby's light outfit, the reddish-brown hair, and the subtle necklace. Maintain the same portrait crop and photographic realism, as if the original print was professionally repaired and remastered in 4K.

Edit the image while keeping the original photo completely unchanged — including the person, face, body, pose, lighting, and gym background. Add multiple small, cute chibi-style “mini versions” of her around the image. Each mini character should have a big head, expressive facial features, and match her hairstyle and outfit. Depict each mini version doing different gym-related activities: one cheering with arms raised one running in running shoes one drinking from a shaker bottle one wearing sporty running glasses one climbing near her leg Enhance the image with playful, hand-drawn doodles and handwritten notes in white and pink ink, in a scrapbook style. Include elements like arrows, stars, hearts, sparkles, and sketchy lines. Add cute, handwritten gym-themed motivational phrases: “lift strong” “stronger every rep” “no pain no gain” “sweat now, shine later” “progress over perfection” “train hard, stay soft” The overall vibe should feel fun, energetic, and feminine.