GPT Image 2 prompts

The photo was taken inside a car at night; the frame reveals only {argument name="subject detail" default="a woman's hand and an iPhone"}, while the young woman's face is visible solely on the phone screen. The camera is positioned on the passenger side, framed to capture the windshield and the phone, which is being held in one hand directly in front of the person. The hand holds a black, latest-model iPhone Pro in a horizontal orientation; the screen displays the iPhone's front-facing camera interface, complete with visible shutter buttons, focus frames, and UI elements. A close-up of the young woman's face inside the car interior is visible on the phone screen: her lips are slightly parted as she touches her lower lip with a slender black object resembling a lip liner pencil. The woman on the screen is wearing {argument name="clothing color" default="black"} clothing, and the light from the phone softly illuminates her face. The hand holding the phone features long fingers and a short, square-shaped French manicure. The rest of the frame is dark; the car's interior is a premium black finish, with parts of the window and dashboard visible. Outside the window lies a night street—warm, blurred city lights, dark silhouettes of trees, and faint light reflections on the glass. The shot is heavily darkened, evoking a "cinematic night" aesthetic and a "rich lifestyle" mood. (9:16 aspect ratio). Shot on an iPhone at night without flash; realistic photo style with slight motion blur and high-contrast shadows. No filters; do not completely blur the background. The hair appears voluminous.

Ultra-realistic, high-quality portrait of the {argument name="subject" default="attached woman"} standing confidently against a large artistic mural featuring an oversized painted portrait of her face. 

She leans casually against the textured wall with a confident, thoughtful expression, one hand resting in her pocket. The background is a dramatic mixed-media collage filled with scattered candid photographs of her from different angles and moments, creating a cinematic storytelling effect. A massive hand-painted portrait of her face dominates the wall behind her, rendered in warm earthy tones, expressive brushstrokes, and urban street-art textures.

Dynamic composition, floating photo prints in the foreground, artistic depth, moody warm lighting, cinematic shadows, rich contrast, highly detailed textures, fashion editorial photography, luxury magazine aesthetic, urban contemporary art gallery vibe, shallow depth of field, ultra-sharp focus, masterpiece quality, 8K resolution, photorealistic, no text, no watermark, no logo, no signature.

**Shot Type:** Wide Cinematic Medium-Full Shot
**Subject & Expression:** {argument name="subject" default="A realistic portrait featuring the exact man from the uploaded reference face"}. He maintains a calm, almost predatory confidence.
**Setting & Atmosphere:** {argument name="setting" default="A rain-slicked, abandoned underground parking garage at night"}. The air is heavy with humidity, visible mist, and dust motes catching the light.
**Action & Details:** He is leaning casually against the wet, graffiti-covered concrete pillar. He is smoking a thick cigar; orange light glows as he inhales, throwing shadows across his face. In one hand, he holds a highly customized, suppressed AR-15 rifle (tactical viral gun idea: integrated laser/light combo and a unique 'worn bronze' Cerakote finish) pointing safely downwards.
**Attire:** A charcoal grey, water-resistant tactical jacket (sleeves slightly rolled) over a black t-shirt, dark ripped jeans, and mud-stained tactical boots. The tactical belt holds several magazines.
**Lighting & Color:** High-contrast, gritty neo-noir lighting. The primary light is a single, warm, yellow tungsten lamp buzzing overhead, creating harsh 'butterfly shadows' on his face and sharp highlights on the wet gun metal and asphalt. This is dramatically contrasted by a deep, cool violet neon sign reflecting off puddles on the ground and casting a sharp edge-light on his shoulder and hair.
**Technical:** Shot on a Panavision anamorphic lens (70mm) with noticeable horizontal lens flare and heavy cinematic grain. Shallow depth of field (shallow DoF), rendering the sprawling garage background in a beautifully blurred, moody bokeh. Gritty film color grade, 2:3 aspect ratio.

Create an ultra-realistic 4:5 portrait based on the uploaded reference photo. Preserve the person's identity exactly, including facial structure, proportions, expression, hairstyle, skin tone, and natural imperfections. Do not reshape the face, beautify it, add artificial filters, or stylize the result.

Show {argument name="subject" default="a young woman with sun-kissed skin and a fit, athletic build"} in a messy kitchen, laughing naturally with her mouth open. Add a playful smear of white flour on her nose and cheek. Keep the bright green eyes, short-to-medium slightly messy hair, and the exact camera-facing angle from the reference.

She is wearing {argument name="clothing" default="a plain black t-shirt fitted like the reference pose with tiny pajama shorts"}, no accessories, and bare feet. Her hands are lightly dusted with flour. One hand holds the phone for a mirror selfie, and the other rests near her face, matching the reference hand placement.

Pose her leaning over a kitchen island counter with elbows on the surface. Capture the scene as an eye-level mirror selfie reflected in a kitchen cabinet or window, using the same perspective as the reference photo. The kitchen should feel casually messy, with a bowl of dough, scattered flour, cracked eggshells, and bright overhead kitchen lighting.

The final image should feel playful, domestic, candid, and highly realistic, with sharp detail in natural skin texture, flour dust, messy surfaces, and real indoor light. The goal is a believable mirror selfie portrait of her laughing in the kitchen, perfectly matching the reference photo's identity, pose, expression, and overall realism.

A street snapshot full of life. The subject is an {argument name="ethnicity" default="East Asian girl"} in her {argument name="age" default="early 20s"}, with a fresh and sweet temperament like the girl next door. She has shoulder-length dark brown hair tied casually in a loose low bun or ponytail, with thin airy bangs, giving an unintentional sense of intimacy and first love. Face close-up: She is turning her head sideways, showing an extremely brilliant, unguarded smile to the camera, her eyes curved like crescents, and her gaze clear and bright. Her makeup is elegant and natural, featuring glossy pink lip glaze that makes her lips look full and crystalline. Her skin texture is fair and translucent, showing a 'glass skin' glow under the light, especially with obvious highlights on her left cheek and the bridge of her nose. She wears a light-colored floral sleeveless halter top, revealing rounded shoulders and slender collarbones in a relaxed pose. The background is set on a city street at dusk, such as a {argument name="location" default="hutong entrance in Beijing"} or a neighborhood full of life. Behind her is a scene of crossing the street, with a blue bus and people on electric bikes in the far left distance, and a boy in a mask riding a blue and white shared bike closer by; these dynamic elements add a sense of story. On the right is the rear of a dark blue car, and further away are green roadside trees and Chinese-style eaves. The background has some depth of field, in a slight state of motion blur and out-of-focus, highlighting the foreground figure. The mood is the laziness and coziness of a summer evening, mixed with millennial retro nostalgia and the freshness of Japanese photography. This is a chance travel snapshot or life record, capturing an unexpected beautiful moment full of relaxation and real breath. Photography and quality focus: This photo should strictly imitate the direct output of an early 2000s consumer-grade CCD digital camera (e.g., Canon IXUS or Sony Cyber-shot). Relatively low resolution, slight compression and blurriness, absolutely not a modern HD refined masterpiece. Details, especially the background and hair edges, lack sharpness, retaining the rough noise and grain unique to old sensors. The light source is dappled light at dusk, overall even and soft. Light comes from her front left, forming obvious highlights on her left cheek, nose, and forehead, with partial slight overexposure, which creates the tender skin texture and the halo effect characteristic of CCDs. She has bright catchlights in her eyes. Overall color saturation is low but warm-toned, with a hint of pink and yellow; the sky is whitened due to overexposure, forming a retro film filter look with low contrast and soft shadows. Emphasize that this is a non-meticulously composed snapshot, retaining the imperfections and authenticity of the image. The composition is a vertical half-length portrait. The camera level is roughly equal to her line of sight, with a slightly low-angle perspective. The character is placed center-right, with her turned-back posture forming a beautiful dynamic leading line. The streets, vehicles, and pedestrians in the background serve as environmental elements, enriching the image layers and creating a strong sense of spatial depth and presence. Aspect ratio '3:4'

Cute puffy sticker sheet, vertical layout, featuring {argument name="character poses" default="characters in multiple poses and expressions, including full body, bust-up, sitting, winking, smiling, and holding a heart"} in a rich variety of compositions.

Place many accessories that match the character's world, such as {argument name="accessories" default="hearts, stars, ribbons, candy, gems, stuffed animals, flowers, drinks, bags, sweets, and mascots"}.

Transparent puffy resin finish, epoxy resin stickers, thick 3D feel, die-cut stickers, transparent glossy edges, strong reflective highlights, sparkling glitter, and a transparent, glossy texture.

Cute miscellaneous goods product design, collection stickers, sticker set, stationery design, unified arrangement, easy-to-read information organization, character as the main focus.

{argument name="color theme" default="Pastel colors"}, cute atmosphere, shimmering highlights, transparency, soft colors, high-end sticker product photo style.

The background is a simple design that functions as a sticker sheet, no unnecessary background elements, and a composition where the character and stickers stand out.

Use the provided image as the character's baseline reference.

Depict "{argument name="prank scenario" default="the moment a popular variety show's wake-up prank was a huge success"}" featuring the character from the reference image as the protagonist.

This is not a poster.
This is not a key visual.
This is a screenshot of an actual wake-up prank video broadcast on a TV program.

The character must be immediately post-wake-up.
Naturally express surprise, confusion, sleepiness, embarrassment, and a reaction of not yet grasping the situation from being suddenly woken up.
Describe bed hair, messy blankets, a collapsed posture, and a room with a lived-in feel.
Do not fix the sleepwear or sleeping position.
Naturally infer from the reference character's personality, profession, worldview, usual clothes, and lifestyle.
Make the appearance feel like a glimpse into that character's private life.

On the desk, shelves, around the bed, and bedside, place personal items that would be a bit embarrassing for others to see.
Naturally infer these from the reference character's personality, profession, hobbies, worldview, and lifestyle.
Do not limit these to general otaku goods.
Embarrassing personal items are elements to express the character's unique individuality; do not repeatedly place only figure shelves or anime goods.
Include elements that make viewers think, "So they had that kind of hobby," or "So that was their private life."
Do not fix the entire room as an otaku room.
Naturally infer the room itself from the reference character's lifestyle.

Add TV show-style production to the screen.
Display "{argument name="caption content" default="Wake-up Prank Big Success"}" in large telop text.
Incorporate TV-like decorations, telops, sound-effect-style text, wipes, subtitles, program logos, and a screen composition that shows it is being filmed.
Include a prank reporter.
If there is one reference image: Generate an original TV reporter suited to the worldview.
If there are multiple reference images: Use the first image as the prank target and the second image as the prank reporter.
The reporter should hold a microphone and be commentating excitedly or pointing the mic toward the target.
Production elements suggesting the presence of TV staff or a filming crew may be added.
Emphasize a comical and fun atmosphere for expressions.
Describe it as a scene from a TV show that looks like it's really being broadcast.
Prioritize making the situation understandable at a glance on SNS.
{argument name="style" default="High-quality anime illustration"}.
Natural character expression.
Abundant depiction of small items.
Information-rich TV show production.
Fun and laughable atmosphere of a prank show.
Focus on depictions where viewers can glimpse an unexpected side or private life of the character that makes them chuckle.

A real SNS-style smartphone photo of a hotel guest room at late night, with only warm-colored bedside lamps quietly lit. A {argument name="person" default="Korean woman in her late 20s"}, long dark brown hair, slightly messy bangs, and a natural, tired, sleepy expression. An unbalanced sleeping pose with the head facing the floor as if falling off the edge of the bed, the upper body sinking softly into the mattress, and legs extending from the bed into the air. A {argument name="outfit" default="champagne-colored long satin dress"}, natural deep V neckline, soft fabric drape, lightweight satin folds, and elegant modern cinematic elegance. White sheets are messy, pillows are collapsed, and on the nightstand are plastic bottles, a smartphone charging cable, used lip balm, and a small bag. {argument name="lighting" default="Mixed lighting of direct smartphone flash and warm lamps"}, slight overexposure on sheets, natural smartphone HDR, slight motion blur, and a compressed SNS image feel. The composition is slightly tilted, creating a candid atmosphere as if a friend had accidentally taken it late at night. Not a glamour photoshoot, but a sense of daily life having fallen asleep from travel fatigue. Realistic Korean facial features, photorealistic skin texture, natural body proportions, soft cinematic shadows, elegant flowing dress extending downward, subtle visibility without explicit focus, cozy hotel ambience, messy realistic bedding, casual luxury aesthetic, authentic late-night traveler mood.

Please generate an intense Korean high-fashion street portrait in a 3:4 vertical aspect ratio.

The subject is a young streetwear model looking directly into the camera on a rainy Seoul night street. Avoid making them look like a specific celebrity or idol; instead, emphasize a natural face, pores, fine skin texture, slight pigmentation differences, and wet hair details.

The outfit consists of {argument name="outfit" default="an oversized silver and gray techwear jacket, black layered pants, and glossy waterproof fabric"}. Raindrops and reflections from cold lights should be visible on the clothing surface.

The scene is a city street like {argument name="location" default="Seongsu-dong, Seoul"} after the rain. Include glass storefronts, wet asphalt, reflecting puddles, chrome railings, cold white signage light, and pale blue neon reflections. Do not include legible text or brand logos.

The composition is a high-angle shot looking down. The camera is about 55 degrees above the subject, who is clearly fixed in the center. Surroundings like people, umbrellas, and scooters should be blurred with a diagonal motion blur, as if captured with a slow shutter.

The lens gives the feel of 35mm fashion editorial photography. The face is in sharp focus, while the background is blurred by shallow depth of field and motion. Let glass panels and reflective surfaces frame the subject's face.

The lighting features {argument name="lighting" default="cold white street lamps, silver rim light from glass shops, and blue reflections from the wet ground"}. The overall atmosphere should be halfway between a Korean fashion magazine cover and viral AI street photography—dramatic, luxurious, and realistic.

Do not include text, watermarks, brand logos, celebrity faces, idol-lookalike faces, anime style, distorted faces, extra fingers, plastic-like skin, or complex backgrounds.

Use the uploaded robot image as a complete reference source. Maintain the head shape, large glowing compound eyes, dark blue and gold color scheme, and retro-futuristic design while deforming it into a 1970s Japanese soft vinyl (sofubi) toy. The theme is 'a used sofubi released in {argument name="year" default="1978"} that has been played with by children for decades.' On the left side of the screen is the original box. It is heavily sun-bleached, with crushed corners and tears repaired with cellophane tape. The printing is rubbed and fading, with price tags and remnants of stickers applied by children. There is also deformation and dirt from moisture. Not a leftover from a Showa-era toy store, but an atmosphere of having been actually stored at home for decades. On the right side of the screen is the robot sofubi figure. The head and shoulders are covered in small dents from being dropped on the floor many times. The paint on the nose and horns is peeling, exposing the base sofubi material color. There are fine scratches on the compound eye parts. Countless scratches on the arms and legs from play. The soles of the feet are worn and rounded. The dark blue vinyl has partially faded from years of sunlight. The gold paint is more than half peeled off, with the coating cracking. Accumulation of grime and dust around the joints. Overall decrease in gloss due to aging. No new glossy feel. Faint traces of a name written by a child with an oil-based pen. Rubbed marks from trying to erase graffiti. Small cracks repaired with glue. Realistic sense of life from a Showa-era child playing seriously. On a wooden study desk. The desk has fine scratches and pencil marks. The background is a blurred scene reminiscent of a Showa-era child's room. Warm incandescent light bulb lighting. Evening atmosphere. A photorealistic product photo as if taken of an actual used sofubi found by a toy collector. Film-style graininess. Minute dust. High definition. Vintage toy magazine feature page quality. extremely worn vintage sofubi, heavily played with by children, chipped paint, scratches, dents, faded colors, repaired cracks, dust accumulation, realistic aging, authentic Japanese vintage toy photography, photorealistic, collectible toy documentation no mint condition, no factory new appearance, no modern collectible figure, no premium statue, no pristine surface, no clean packaging, no modern toy store display

A {argument name="person" default="man"} laughing happily while holding a bottle of {argument name="drink" default="whiskey"}

Dark, high-contrast noir-style portrait of {argument name="subject" default="SUBJECT"}, drawn entirely with bold black ink lines and deliberate splatter. Deep shadows dominate the frame, with bright highlights carved out through empty white space. A subtle paper grain shows through. The mood is brooding, cinematic, and intense, like the most gripping panel in a graphic novel.

9:16 vertical format, editorial portrait style, one subject only. Black mist effect applied lightly, soft atmospheric haze, gentle glow around highlights, tones muted and desaturated. Indoor space kept minimal and clean, background plain with subtle surface texture. {argument name="subject" default="Young Korean woman"}, very little makeup, natural skin visible. Clothes: {argument name="clothing" default="ribbed knit fitted top or thin camisole under a loose open shirt, high-waist shorts or skirt"}; fabric drapes close to the body naturally, soft, not revealing. Hair casual and slightly messy with natural body. Pose: {argument name="pose" default="sitting on the floor, one leg folded up, the other stretched out loosely"}; torso leans slightly, shoulders at different heights, head tilted to one side. Subject placed slightly off-center in frame, open negative space visible. Expression: relaxed and calm, eyes looking softly away, lips at rest. Light: gentle side lighting, shadows falling off gradually. Overall mood: quiet, understated, naturally sensual through relaxed body language rather than styling. Texture: fine grain, slight softness, photorealistic quality.

Draw {argument name="character" default="the character in the image"} in a free and stripped colored sketch style. On a bright white background, freely distribute full-body drawings, face close-ups, small scribbles, full-body sketches and chibi/deformed versions, so that the page conveys the character's humor and personality. Don't do it like an organized character sheet, but like a sketchbook full of information drawn at will by an illustrator and then stacked. The written make it in {argument name="language" default="Urdu"}

A scroll-stopping product advertisement photo for summer. Subject: {argument name="drink type" default="carbonated drink"} in a {argument name="packaging" default="500ml PET bottle"}, branded {argument name="brand name" default="Natsukan SODA (Summer Citrus Soda)"}. Style: high-CTA 2025 beverage campaign — vibrant citrus freshness, clean composition, bold visual energy designed to make you want to grab one. Portrait format, 3:4 ratio.

Studio editorial photograph of a {argument name="vessel type" default="premium skincare vessel (bottle, jar, or tube)"} in {argument name="material" default="glass or ceramic"}, with a colored accent detail. Set on a {argument name="surface" default="natural stone or marble slab"} resting on a round mirror, all on a soft neutral surface. Scattered droplets of serum or oil catch the light around the mirror and slab. Sprigs of lavender, eucalyptus, or rose petals drape naturally across both surfaces. Warm sunlight from the upper left casts gentle leaf shadows evoking filtered daylight. Aesthetic is minimalist and luxurious, with golden hour tones highlighting natural textures. Style: 3D realism, luxury product photography, shallow depth of field. Format: 1:1, ultra-detailed.

Semi-realistic anime-inspired portrait of a stylish young Korean woman with a {argument name="hairstyle" default="short glossy black bob tucked behind one ear"}, delicate round-frame glasses, and a gentle confident expression. She wears an oversized {argument name="outfit" default="pastel lilac blouse with rolled sleeves paired with a flowing ivory A-line midi skirt"}. Full-body composition, standing casually with relaxed posture. Behind her is an artistic collage of hand-drawn monochrome character studies, loose pencil sketches, manga panels, playful doodles, stars, hearts, swirls, and handwritten notes scattered organically across the backdrop. Contemporary anime fashion illustration with mixed ink-and-pencil textures, clean linework, subtle cel shading, bright white background, magazine-cover aesthetic, highly detailed, ultra-sharp, vibrant yet elegant, 8K masterpiece.

Harajuku girl, wearing a {argument name="dress color" default="purple and matching color"} dress, {argument name="hairstyle" default="exaggerated hairstyle"}.

Luxury athleisure fashion campaign featuring a stunning young East Asian female model in a {argument name="outfit" default="sleek oversized performance windbreaker layered over a fitted technical crop top, pleated athletic skort, ribbed thigh-high sports socks, and designer running sneakers"}. Standing confidently inside a {argument name="location" default="modern training facility corridor with illuminated metallic storage units"} and subtle architectural details. Clean monochromatic teal and silver color palette, contemporary sports-luxury aesthetic, high-end magazine editorial, dynamic yet elegant pose, premium commercial fashion photography, realistic fabric textures, sophisticated studio lighting, soft cinematic shadows, shallow depth of field, minimalist composition, elite brand advertising, ultra-sharp focus, photorealistic, 8K, Vogue-inspired sports couture campaign, luxury athletic lifestyle imagery.

[{argument name="brand" default="BRAND NAME"}]. You are a Creative Director and Still Life Photographer for a high-fashion hypebeast magazine.

YOUR TASK:
Design a premium "Showroom Still Life" image to announce a limited merch drop for [{argument name="brand" default="BRAND NAME"}].

STEP 1: BRAND ANALYSIS
Study [{argument name="brand" default="BRAND NAME"}]: identify its industry and signature physical product (e.g., "Spalding" = basketballs, "McDonald's" = burger packaging, "Visa" = metal cards).
Choose the Color Palette:
- Background: a deep, rich, textured tone from the brand's secondary colors (Teal, Navy, Burgundy, or Slate Grey).
- Merch: a warm or neutral accent tone (Camel, Orange, or Cream) that pops against the backdrop.
- Apparel Piece: select something that fits the brand's energy (Varsity Letterman Jacket, Heavyweight Hoodie, Canvas Tote, or Wool Scarf).

STEP 2: SET DESIGN
Main Prop: a clean, modern White Powder-Coated Metal Rack or shelving unit.
Layout:
- The apparel piece hangs casually from the rack or a hanger, showing off its texture.
- On the rack shelves, stack several units of the brand's core product (e.g., basketballs, cans, boxes).
- Backdrop: hand-painted canvas in the chosen deep background color, with visible brushstrokes for that studio aesthetic.

STEP 3: BRANDING DETAILS
Apparel: feature premium physical branding via Chenille Patches, Embroidered Logos, or Screen Print on the sleeve or back. It should look like a genuinely expensive garment.
Products: ensure the [{argument name="brand" default="BRAND NAME"}] logo is clearly visible on all stacked items.

STEP 4: PHOTOGRAPHY
Lighting: soft, directional side window light with realistic soft shadows and rich texture highlights.
Focal length: 50mm or 85mm. Sharp focus on the merch, gentle background falloff.

STEP 5: GRAPHIC OVERLAY
Left-aligned composition:
- Large, clean white [{argument name="brand" default="BRAND NAME"}] logo placed in the negative space on the left.
- Beneath the logo, small white text with the brand's official tagline.

Create a cinematic 16:9 environment and crowd scene featuring {argument name="character name" default="Jiel"}, a young thief, as the clear focal character within a dense, bustling street market.

STYLE: {argument name="style" default="Rough sketch"}

Create an ultra-realistic vertical portrait photograph of an elegant adult woman in a refined indoor bathroom or spa-like interior, framed from the upper chest to just above the head. She has {argument name="hair color" default="dark brown"} wavy hair pulled back loosely into a low ponytail with natural flyaways, one ear visible, warm tan skin, and a slim neck with realistic collarbones, subtle skin sheen, pores, small moles, and natural texture. Her face is intentionally covered by one large opaque square censor block centered over the face, using a smooth warm brown-to-taupe vertical gradient that hides all facial features while leaving the hairline, ear, neck, and shoulders visible. She wears a {argument name="garment color" default="champagne ivory"} silky V-neck robe or blouse with soft satin highlights and relaxed shoulders. Use warm natural sunlight from the left, gentle shadows across the neck and fabric, shallow depth of field, and a high-end editorial fashion photography look. Background: softly blurred marble wall panels, muted beige-gray tones, a vertical brass or gold trim line on the right, a faint hanging lamp at the upper right, and blurred white flowers on the left. Composition should feel candid and photorealistic, with realistic skin texture and natural body features, no text, no watermark, no extra people, no exaggerated beauty retouching. Use {argument name="aspect ratio" default="3:4 vertical"} framing and {argument name="lighting mood" default="warm late-afternoon sunlight"}.

Create a bright Japanese YouTube thumbnail in a high-energy variety-show style about the urban legend that the blue Lawson sign is actually a milk can. Use a 16:9 horizontal canvas, glossy anime/Vtuber thumbnail design, warm blurred convenience-store or city-light background, heavy white outlines, sparkles, radial speed lines, halftone dots, comic splashes, and strong drop shadows. On the right side, place one anime-style young woman presenter from chest up: short brown bob haircut with side-swept bangs, large black glasses, closed smiling eyes with blush, fair skin, wearing a black blazer over a deep V-neck white blouse and a delicate gold necklace; her hand is partly raised near the bottom as if explaining. On the left and center, add huge stacked Japanese headline typography with thick white and dark outlines: 「青い看板の」 in bright blue at the top, and 「正体」 in oversized yellow below, angled slightly for impact. Add a red rounded label at the top left reading 「#えもーにんぐ No.2114」 with small star decorations. Add a small illustrated silver milk can near the center-right of the headline, labeled “MILK” with a blue cow icon, with blue motion marks around it. Add a pink comic burst near the lower center reading 「実は 牛乳缶!?」 with 「牛乳缶!?」 very large in hot pink. Add a rounded white badge at the top right with an orange sun icon and text 「6/3 ローソンの日」 in orange and blue. Add the channel logo-like text 「癒色えも」 at the bottom left in pale blue. Include exactly 6 main text elements: top-left episode label, blue headline, yellow headline, pink burst claim, top-right date badge, bottom-left channel name. Make the image colorful, cute, glossy, and attention-grabbing, with no photorealism, no extra characters, no watermark, and keep all Japanese text crisp and readable. Allow the headline to be customized as {argument name="main headline" default="青い看板の 正体"}, the episode label as {argument name="episode label" default="#えもーにんぐ No.2114"}, the claim burst as {argument name="claim text" default="実は 牛乳缶!?"}, the date badge as {argument name="date badge text" default="6/3 ローソンの日"}, and the presenter style as {argument name="presenter style" default="anime young woman with short brown bob hair, black glasses, black blazer, white blouse, gold necklace"}.

Create a high-impact Japanese YouTube thumbnail about AI image generation improvement. Canvas: 16:9 horizontal thumbnail, photorealistic with bold creator-thumbnail typography. Scene: a warm, softly blurred cafe interior with pendant lights and bokeh in the background, wooden table foreground. On the right side, show 1 young Japanese woman in a white lace blouse, hair in a loose elegant updo, seated and facing slightly left; her face is covered by a flat rectangular beige blur/mosaic block to anonymize her. She holds 1 white stylus in her right hand, pointing toward a large tablet on the left. On the left side, show 1 large black-framed tablet standing upright; on its screen are exactly 2 side-by-side portrait images of the same woman in a white blouse, each with a beige rectangular blur over the face. The left portrait looks like a simpler original image on a light plain background, and the right portrait looks enhanced, with more realistic cafe lighting and detail. Between the 2 tablet portraits, place 1 glowing cyan vertical divider with 1 bright white-blue chevron arrow pointing from left to right, indicating before-to-after enhancement. Text: place a small energetic Japanese headline at the top left reading {argument name="top headline text" default="無料でこのクオリティ"}, with the first word in red/pink and the remaining characters in white, thick black outline, slightly tilted, with decorative diagonal slash marks on both sides. Place the main headline across the bottom in huge bold lettering reading {argument name="main headline text" default="GPT Image 2.0神進化"}; make “GPT Image 2.0” bright yellow with black outline and subtle shadow, and make “神進化” white with black outline. Keep exactly 2 visible text blocks: the top headline and the bottom headline. Overall style: glossy, professional Japanese tech tutorial thumbnail, strong contrast, warm cinematic lighting, shallow depth of field, clean composition, no logos or watermarks, no extra text. Customization: the woman should appear as {argument name="subject description" default="a young Japanese woman with dark hair in a loose updo wearing a white lace blouse"}, the setting should be {argument name="background setting" default="a cozy modern cafe with warm pendant lights"}, and the topic should visually imply {argument name="topic" default="GPT Image 2.0 photo enhancement"}.