Prompts
Featured
Models
Submit
Blog

AhaPrompt

AI Prompts for Images, Video & Audio — Every Model, One Library

Explore

All Prompts
Featured Prompts
Image Prompts
Video Prompts
Audio Prompts
AI Models
Submit a Prompt
Blog

Languages

English
中文
日本語
한국어

Copyright © 2026 AhaPrompt All rights reserved.

Privacy Policy Terms of Service

HomeAI Prompt LibraryAI Image PromptsCozy Bedroom Winking Selfie Portrait

Cozy Bedroom Winking Selfie Portrait — AI image prompt — GPT Image 2.5 — Fashion, Realistic, Portrait - 1

Cozy Bedroom Winking Selfie Portrait — AI image prompt — GPT Image 2.5 — Fashion, Realistic, Portrait - 2

Cozy Bedroom Winking Selfie Portrait

GPT Image 2.5OpenAIimage

Ultra-realistic low-angle selfie of a beautiful East Asian girl with long dark brown hair and wispy bangs, glossy soft pink lips, natural makeup, delicate silver earrings, and a cute winking smile. Wearing an oversized fluffy white cardigan over a white top with shorts, sitting casually on a chair in a cozy bedroom with a laptop, cute room decor, and warm desk lighting. Candid smartphone selfie aesthetic, slightly blurry soft-focus effect, dreamy warm lighting, realistic skin texture, K-pop girl vibe, natural facial features, 9:16 vertical composition.

Details

Type: AI Image Prompts
Aspect Ratio: 3:4
Updated: Oct 13, 2026

Category

Fashion Realistic Portrait

How to use this prompt

1Copy the full prompt with the copy button above.
2Open GPT Image 2.5 by OpenAI, or any image generator with a similar style range.
3Paste the prompt, then swap the subject and style keywords to match your idea.
4Match the example's settings (3:4 · Fashion · Realistic · Portrait), then iterate — small wording changes shift the output a lot.

Frequently asked questions

Which AI model generated this image?

This image was generated with GPT Image 2.5 by OpenAI. The prompt on this page is the exact text used to create it.

What settings does this prompt use?

The example was generated with GPT Image 2.5 using: 3:4 · Fashion · Realistic · Portrait. Reusing these settings gives the closest match.

How do I get similar results?

Copy the prompt as-is first, then replace only the subject while keeping the style, lighting, and composition keywords. Generate a few variations — outputs differ between runs.

Can I modify this prompt?

Yes. Prompts work best as starting points — adjust descriptors, aspect ratio, or style tags to make the output your own.

More GPT Image 2.5 prompts

Create an ultra-realistic vertical 2×4 photobooth contact-sheet collage of the same adorable young c — AI image prompt — GPT Image 2.5

Create an ultra-realistic vertical 2×4 photobooth contact-sheet collage of the same adorable young couple across all 8 frames. They should look like genuine real people photographed together, never AI-generated: natural facial asymmetry, realistic pores and skin texture, tiny imperfections, individual hair strands, authentic eyes, believable hands and anatomy. Character continuity: cute young woman with long soft dark-brown hair, warm expressive eyes, subtle natural makeup, oversized cream knit sweater. Cute young man with messy naturally curly dark-brown hair, warm expressive eyes, dark charcoal hoodie/jacket over a simple white T-shirt. Keep their faces, hairstyles, age, proportions and clothing perfectly consistent in every frame. Make every frame feel like a different spontaneous moment rather than repeated poses: 1. She rests her cheek on her hand while he looks at her with a tiny smile. 2. Both lean extremely close to the camera, laughing naturally, slightly imperfect framing. 3. She kisses his cheek while gently squishing his face; his eyes close with a genuine smile. 4. Both hide half their faces inside their oversized sleeves, only their eyes visible. 5. They wear matching dark vintage baseball caps; she makes a playful pout while he looks toward her. 6. A genuine mid-laugh shot where she covers her smile and he laughs beside her. 7. She makes a small heart with both hands in the foreground while he rests his cheek against her head. 8. Final emotional frame: he kisses her forehead while she closes her eyes and hugs him tightly. Shot like a real late-night photobooth session on Kodak Portra 400, direct on-camera flash, slightly warm neutral white balance, soft shadow behind them, realistic flash falloff, subtle highlight bloom, fine 35mm grain, mild lens softness, tiny exposure inconsistencies and imperfect candid framing. No beauty filter, plastic skin, excessive sharpening, CGI or AI aesthetic. Arrange all eight photographs inside distressed black analog contact-sheet borders on a matte black scrapbook background. Add tiny orange film-edge markings, subtle scratches and dust. Around the photographs, add sparse handwritten white-ink doodles and small imperfect hearts with phrases such as “Better Together ♡”, “My Happy Place”, “Same People, Different Moments”, “Still You ♡” and “More Silly Moments Please.” Keep typography secondary to the photographs and authentically handwritten rather than digitally perfect. At the bottom, handwritten: “A thousand little moments with you ♡” with a small handwritten date. The overall result should feel like a real couple accidentally created the perfect roll of film, intimate, youthful, nostalgic, cute and highly shareable—not a polished commercial photoshoot. Premium editorial composition, believable analog photography, extremely detailed faces, clean tonal separation, excellent contrast and natural cinematic color grading, 8K-quality realism, 9:16 vertical, absolutely no obvious AI artifacts.

A cinematic high-fashion editorial photograph captured on location — an intimate waist-up hero compo — AI image prompt — GPT Image 2.5

A cinematic high-fashion editorial photograph captured on location — an intimate waist-up hero composition of an East Asian woman in a luxury marble bathroom suite, the camera positioned at eye level in a three-quarter rear framing capturing her striking over-the-shoulder gaze and the reflective vanity mirror in an M2 luxury interior editorial register. The woman has a sleek, glossy jet-black blunt bob haircut that grazes her shoulders with clean-cut ends, complemented by soft, airy wispy fringe framing her brow. Her fair, porcelain-toned skin displays natural fine pore texture, delicate shoulder blades, and subtle subsurface scattering under warm vanity lighting. Her defined almond eyes look back over her right shoulder directly toward the camera with a poised, captivating expression, paired with a sculpted profile, soft blush, and naturally glossy rose lips. She wears an architectural backless black silk halter evening piece: completely open across the spine, secured by delicate geometric crisscross black satin micro-straps intersecting at a miniature black floral buckle fastener at the mid-back and tying low around the waist, paired with matching draped black bottoms. She leans slightly forward over the vanity counter with one arm extended for support, her torso gracefully twisted to showcase both the intricate back strap design and her elegant silhouette. The setting is an opulent contemporary hotel bathroom vanity area — in front of her sits a polished black marble countertop with an undermount white porcelain sink and modern chrome swan-neck faucets, with the large vanity mirror reflecting a soft frontal view of her draped silhouette and the surrounding suite. In the softly blurred background, a freestanding white oval soaking tub and polished white-and-gray veined marble walls complete the high-end architectural interior. The scene is illuminated by soft, flattering luxury hospitality vanity lighting — diffused warm-white glow radiating from surrounding mirror sconces and recessed ceiling fixtures, evenly enveloping her shoulders, neck, and back with creamy, gentle illumination without harsh cast shadows. Crisp, subtle specular highlights glint off the polished chrome bathroom fixtures, the wet sink basin, and the sleek surface of her black satin straps, enhancing the tactile luxury of the space. Captured with a wide-latitude digital cinema look on a fast 50mm portrait prime lens at T2.0, delivering razor-sharp optical detail across her facial profile, eyeliner, individual hair strands, and the satin strap intersections, while the vanity mirror reflection and bathroom background melt into soft, organic circular bokeh. Refined high-end interior color grade balancing cool marble veins with warm, radiant skin tones and deep, uncrushed blacks in the fabric, finished with fine, organic 35mm theatrical film grain across the frame. Real photographic frame captured on a real cinema camera, real prime lens, real silk satin fabric, real marble countertop, real East Asian human subject, real luxury bathroom environment — no CGI, no rendered look, no digital cleanliness, no plastic surfaces, no AI smoothness, no skin smoothing, no glow, no halation bloom that reads as artificial, no glossy highlights.

Create a refined, high-end PHOTO + MINIMAL WATERCOLOR VIGNETTE artwork based entirely on the uploade — AI image prompt — GPT Image 2.5

Create a refined, high-end PHOTO + MINIMAL WATERCOLOR VIGNETTE artwork based entirely on the uploaded photograph. Use the photograph as the only visual reference and preserve the exact subject, composition, environment, clothing, objects, lighting, colors, and mood. FORMAT: Vertical 3:4 editorial composition. TOP SECTION — ORIGINAL PHOTOGRAPH: Place the original photograph in the upper 55–60% of the canvas. Keep it photorealistic and naturally detailed. Do not alter the identity, pose, proportions, objects, architecture, scenery, or important visual details. Give it a subtle premium editorial photography finish with natural cinematic light and gentle tonal balance. BOTTOM SECTION — HAND-PAINTED INTERPRETATION: Transform the same exact scene into a delicate minimal watercolor and fine-ink illustration. Recreate the main subject, pose, perspective, key objects, and recognizable background elements from the photograph. Use loose watercolor washes, subtle pencil/ink outlines, imperfect hand-painted edges, soft paper texture, and restrained pastel tones. Keep the illustration airy, elegant, and slightly imperfect rather than digitally polished. The illustration should feel like a fashion/lifestyle magazine sketchbook page, with plenty of clean negative space and a warm off-white textured paper background. Do not introduce new subjects or details. TYPOGRAPHY: Add a short elegant handwritten brush-script phrase underneath or integrated naturally into the illustrated section, similar to a premium lifestyle editorial poster. Underneath it, add a tiny minimalist lowercase serif/sans-serif subtitle. Typography should be subtle, sophisticated, thin, and balanced with the artwork. AESTHETIC: Scandinavian editorial design, quiet luxury, nostalgic travel journal, soft watercolor, delicate ink drawing, handmade paper texture, muted natural palette, sophisticated minimalism, emotional storytelling, premium art-book layout. IMPORTANT: The photograph and illustration must clearly represent the same exact moment and scene. No collage of unrelated images, no dramatic redesign, no excessive watercolor, no cartoon appearance, no heavy outlines, no saturated colors, no clutter. Output: photorealistic upper section + matching delicate watercolor illustration below, seamless premium editorial composition, vertical 3:4, high detail. For different photos, just change the text phrase Examples: •Good Days — a kinder me •Better Together — same window, same silence •Little Moments — worth remembering •Slow Days — nothing to rush •Somewhere Quiet — just for a while •Golden Hours — softly remembered

Ultra-realistic expensive lifestyle shot. A girl is in the frame. Her hair is very long, straight to — AI image prompt — GPT Image 2.5

Ultra-realistic expensive lifestyle shot. A girl is in the frame. Her hair is very long, straight to the waist, evenly parted, with several strands falling on her face. Smooth skin tone. 100% facial similarity. She is wearing an oversized grey turtleneck sweater with long sleeves, a black denim skirt with raw/frayed edges, and a black belt from a recognizable brand. Part of the sweater is tucked into the skirt. She wears black nylon tights and tight-fitting high black boots. Her nails are short and milky. She has small round gold earrings. She holds a black Dior bag in her hand and wears a long, voluminous grey coat. The image looks stylish and harmonious. She stands on a city street with wet paving stones, building facades, fallen leaves, and puddles. A tree is visible next to her, with yellow-leafed branches hanging over her. She looks to the side with a soft closed smile. Shot on iPhone 17 Pro Max. The background is not blurred. Clouds are visible. High skin detail. Soft, dimmed lighting. Live photo, no retouching on the face. Raw look.

Transform every visible person in the uploaded image into a realistic LEGO-style minifigure while pr — AI image prompt — GPT Image 2.5

Transform every visible person in the uploaded image into a realistic LEGO-style minifigure while preserving the original environment, background, composition, lighting, and relationships. Create exactly one separate minifigure for every visible person. Preserve each person’s recognizable identity, expression, hairstyle, hair color, skin tone, proportions, pose, position, clothing, accessories, and held objects. FORMAT LOCK Vertical 3:4 composition. Show every minifigure fully from head to toe without cropping. Preserve the original group arrangement and perspective. Extend the environment naturally only when needed for the 3:4 frame. STYLE TRANSFER Convert only the people into authentic LEGO-style minifigures. Use realistic molded plastic, cylindrical heads, block-shaped torsos, standard arms and hands, short legs, printed facial features, detailed printed clothing, and molded plastic hairpieces matching each person’s hairstyle. Keep the figures seamlessly integrated into the original photograph. DETAIL & COLOR Accurately reproduce each person’s original clothing colors, patterns, layers, sleeves, collars, pants, skirts, shoes, jewelry, glasses, hats, bags and other visible accessories as LEGO prints or molded elements. Preserve original skin tones and facial expressions. Realistic plastic reflections, subtle seams, fine printed details and natural contact shadows. COMPOSITION LOCK Keep the original location, architecture, scenery, furniture, objects, colors, textures, perspective, depth, weather, atmosphere and time of day unchanged. Do not redesign or simplify the background. Preserve all existing objects in their original positions. Objects held or worn by people may be converted into LEGO-style accessories while maintaining their original appearance and color. STYLE Photorealistic LEGO-style minifigure transformation, premium 3D toy photography, realistic molded plastic, subtle glossy finish, physically accurate reflections, natural lighting, cinematic detail, seamless integration with the original scene. NEGATIVE PROMPT No changed background, studio backdrop, LEGO environment, added bricks, removed objects, extra people, missing people, duplicates, merged figures, generic characters, altered outfits, invented accessories, identity loss, wrong hairstyles, cropped bodies, missing limbs, oversized heads, realistic human bodies, real hair, real fabric, anime, cartoon exaggeration, CGI-looking environment, floating figures, excessive reflections, harsh shadows, blur, low resolution, text, logos, watermark.

Create a sophisticated 3:4 vertical editorial art poster using the uploaded image as the primary vis — AI image prompt — GPT Image 2.5

Create a sophisticated 3:4 vertical editorial art poster using the uploaded image as the primary visual reference. The composition must be divided into two perfectly balanced horizontal halves, with a precise 50/50 visual structure. UPPER 50% — ORIGINAL PHOTOGRAPH Place the reference photograph in the entire upper half. Keep it almost completely untouched. Preserve the exact: * facial identity and facial features * expression * hairstyle and hair length * skin tone and natural skin texture * body proportions * pose and posture * clothing and accessories * objects and environment * composition and perspective * lighting direction * colors and tonal relationships * photographic details and natural texture The photograph should still look like a real, authentic editorial photograph, with only subtle premium color grading and extremely restrained tonal refinement. Do not reinterpret, redraw, beautify, or stylize the photograph. LOWER 50% — HANDMADE ARTISTIC MEMORY Transform the main visual idea and recognizable elements of the photograph into a tiny, centered handmade-paper artwork. The artwork should occupy only approximately 10–20% of the entire lower half, leaving a large amount of intentional negative space around it. It should look as though an independent contemporary artist created a small visual memory of the photograph by hand. Use: * warm off-white handmade paper * subtle natural paper fibers * delicate imperfect ink-like outlines * simple flat acrylic-inspired shapes * organic, slightly uneven edges * restrained abstract simplification * visible handmade-print character * maximum 4 colors, carefully sampled from the original photograph * subtle variations in ink density * slightly imperfect registration and handmade imperfections Reduce the photograph into only its most recognizable visual elements. Do not reproduce every detail. The result should feel like a poetic visual memory rather than a literal miniature copy. The artwork must remain small, quiet, centered, and understated. TYPOGRAPHY Optional: add extremely minimal editorial typography only if it naturally enhances the composition. If typography is included, use: * very small scale * elegant contemporary editorial type * restrained spacing * subtle placement * no large headline * no commercial branding * no distracting text Typography must remain secondary to both the photograph and the miniature artwork. OVERALL ART DIRECTION The final composition should feel like a limited-edition independent contemporary art-book cover where the original photograph and its handmade artistic memory coexist within one carefully designed page. Visual references: contemporary art book, gallery editorial, quiet luxury, independent art publication, handmade print, refined minimalism, poetic negative space, museum catalog design, sophisticated editorial composition. The transition between the two halves should feel intentional and beautifully balanced, with a generous breathing space around the miniature artwork. IMPORTANT Do not make the lower artwork: * cartoonish * childish * watercolor * colored-pencil * 3D * glossy * photorealistic * overly digital * highly detailed * colorful * busy * commercial * decorative for its own sake Do not turn the entire image into an illustration. The upper half must remain a real photograph. The lower half must be a tiny handmade artistic interpretation. The contrast between photographic realism above and restrained handmade abstraction below is the central concept. Final format: 3:4 vertical, sophisticated contemporary editorial art poster, high-end print quality, precise 50/50 horizontal division.

Create an ultra-photorealistic vertical romantic photo-booth contact-sheet collage, 2 columns × 5 ro — AI image prompt — GPT Image 2.5

Create an ultra-photorealistic vertical romantic photo-booth contact-sheet collage, 2 columns × 5 rows, showing ONE continuous visual story involving the exact same young adult couple throughout. CORE VISUAL IDEA: The two columns are not ten unrelated photos. They represent two separate adjacent photo-booth spaces. The young woman begins entirely inside the LEFT column and the young man begins entirely inside the RIGHT column. As the rows move downward, the man gradually leaves his own frame and physically moves into the woman’s frame. His original RIGHT frame therefore becomes progressively emptier. This visual migration is the central concept and MUST remain logically consistent. CHARACTERS: A very cute young adult East Asian couple, approximately 20–23 years old, both clearly adults. GIRL: Naturally adorable Korean-looking young woman, soft youthful facial features, expressive dark-brown eyes, realistic fair skin with visible pores and subtle natural texture, slightly rosy cheeks, dark-brown hair in a loose messy bun with wispy strands around her face. Oversized black knitted sweater. Minimal natural makeup. Sweet, shy, playful personality. BOY: Cute Korean-looking young man, youthful but clearly adult, soft masculine facial features, warm dark eyes, naturally messy fluffy dark hair, realistic skin texture. Light-grey oversized hoodie over a simple white T-shirt. Gentle, slightly shy personality. STRICT IDENTITY LOCK: The SAME woman and SAME man must appear in every row. Identical faces, hairstyle, clothing, skin tone and proportions throughout. No face drift, no hairstyle changes, no outfit changes. STORYBOARD: ROW 1 — TWO STRANGERS LEFT: girl alone, chest-up portrait, casually looking toward the right edge as though she has noticed someone. RIGHT: boy completely visible and centered in his own frame, facing camera naturally. They are physically separated by the vertical black divider. Small handwritten text: LEFT: “just a girl… ♡” RIGHT: “just a guy…” ROW 2 — THEY NOTICE EACH OTHER LEFT: girl turns her eyes and face toward him with a tiny restrained smile. RIGHT: boy turns toward the girl, leaning slightly toward the LEFT boundary for the first time. He is still mostly inside his own frame. Text: LEFT: “who noticed something” RIGHT: “…and looked twice ♡” ROW 3 — CROSSING THE LINE This is the important transition. The boy has moved substantially LEFT and is now entering the girl’s frame across the central divider. The couple are close together, looking directly at each other and smiling naturally. His RIGHT frame must now contain noticeably more empty background because he has physically moved away from it. Do NOT duplicate him. Text: LEFT: “then we smiled ♡” RIGHT empty area: “and suddenly it made sense” ROW 4 — HE HAS LEFT HIS FRAME The boy is now almost COMPLETELY inside the LEFT frame with the girl. They share one soft, natural kiss, photographed candidly rather than dramatically. Only a tiny portion of his shoulder/body may intersect the central border. The RIGHT frame is approximately 85–90% EMPTY — just clean studio background. This empty frame is intentional and visually important. Text: LEFT: “same weird thoughts ♡” RIGHT empty frame: “different chaos ♡” ROW 5 — FINAL PAYOFF The boy has now COMPLETELY abandoned his original right-hand frame. Both characters are entirely together inside the LEFT frame. Instead of another kiss, create an irresistibly cute candid moment: he hugs her tightly from behind while giving her a small forehead/temple kiss; she scrunches her cheeks slightly, closes her eyes and smiles naturally. Their body language should feel spontaneous, warm and genuinely affectionate. RIGHT frame must be COMPLETELY EMPTY except for: “more stories ♡” Text in left: “same people…” IMPORTANT: Never place a second copy of either character in the right frame after the man moves left. Never repeat the kissing image across both columns. The empty space tells the story. DESIGN: Minimal premium analog contact-sheet aesthetic inspired by an old 35mm film proof sheet, but make the composition completely original. Warm off-white / soft beige seamless studio background. Deep black film borders. Thin slightly imperfect frame separators. Tiny amber film-number markings and subtle sprocket details along outer edges. Very subtle authentic analog grain, dust and microscopic scratches. Small pieces of aged masking tape. A few torn-paper notes. Tiny hand-drawn hearts. Small dried flowers near one bottom corner. Only a handful of decorations — never clutter the photographs. Margin notes: “Good people, good times ♡” “You + Me Always ♡” “Collect moments, not things ♡” BOTTOM HERO MESSAGE: Place a torn warm-ivory paper strip across the lower border with handwritten text: “you + me = a better kind of chaos ♡” PHOTOGRAPHY: 100% believable real-human photography. Premium editorial photo-booth portraits shot on a full-frame camera with approximately 50–85mm portrait-lens character. Soft warm studio key light, subtle fill, realistic shadow falloff. Natural skin pores, peach fuzz, individual hair strands, realistic knitted fabric and hoodie texture. Slightly imperfect candid expressions. Warm cinematic color grade with creamy highlights, rich blacks and subtle analog grain. Faces remain sharp while retaining natural photographic softness. The first row should feel slightly awkward and separated. Every subsequent row becomes visually warmer and physically closer. The final row should provide the strongest emotional payoff. NO CGI. NO illustration. NO anime. NO plastic skin. NO excessive beauty retouching. NO duplicated people. NO extra fingers or limbs. NO random additional characters. NO identity changes. NO duplicated poses. NO repeated kiss. NO decorative overload. NO characters appearing inside intentionally empty right-side frames. FINAL FEEL: A photograph someone would instantly stop scrolling to understand — first they notice two sep

2x2 grird, do this for 4 fashion movement of various decades, 16:9 class EditorialPoster: def __ — AI image prompt — GPT Image 2.5

2x2 grird, do this for 4 fashion movement of various decades, 16:9 class EditorialPoster: def __init__(self, topic): self.topic = topic self.resolution = self.resolve_auto_fields(topic) def resolve_auto_fields(self, topic): # Module 2: Copy & Facts self.title = generate_title(topic, max_words=5) self.tagline = generate_tagline(topic, min_words=3, max_words=8) self.labels = extract_key_points(topic, count=6-12, relationship="components") # principles/stages/types # Module 3: The Surreal Character Engine self.mechanism = infer_verb(topic) # e.g., "filtering", "branching", "accumulating" self.base_form = select_organism(self.mechanism) # human, animal, or object # CRITICAL: Transformation must be structural, not just accessories self.transformation = invent_structural_alteration(self.base_form, self.mechanism) self.pose = select_pose(topic, attitude="intriguing_uncanny") # Module 5: Geometry & Palette self.geometry = select_geometric_family(topic) # rays, arcs, ribbons, grids self.palette = derive_accent_colors(topic, count=2-6, mood="flat_matte_weathered") def verify_character_logic(self): # The "Thumbnail & Concept" Check assert is_structural(self.transformation), "Module 3: Must be anatomy/proportion, not accessories." assert fits_sentence(self.transformation, self.mechanism), "Module 3: Logic check failed." assert visible_at_thumbnail(self.transformation), "Module 3: Must read at small scale." assert not is_generic_cute_scary(self.pose), "Module 3: Avoid default emotional tropes." def render(self): self.verify_character_logic() # Module 1 & 6: Style Kernel canvas = Canvas(aspect="1:1", bg="warm_ivory", texture="subtle_analog_grain") # Hero: Grayscale, sculptural shading, stippling/halftone hero = render_grayscale_sculptural(self.base_form, self.transformation, self.pose, shading="fine_stippling", texture="tactile_print") # Module 4: Adaptive Layout layout = adaptive_composition( hero=hero, title=self.title, # Oversized, black, condensed, uppercase labels=self.labels, # Compact, high contrast geometry=self.geometry, # Connects hero to info palette=self.palette # Flat, matte accents ) return canvas.compose(layout, typography="extreme_contrast_hierarchy") EditorialPoster($ TOPIC).render()

Browse all GPT Image 2.5 prompts Explore AI Image Prompts