by OpenAI

GPT Image 2 Prompts

OpenAI's reasoning image model — it plans the layout, thinks through your instructions, and checks its own work before drawing.

image

GPT Image 2

Using my uploaded photo, turn me into an intense Nightmare On Elm Street-inspired version of myself. Keep my face and features recognizable. Dress me in a Freddy Krueger-inspired outfit with Freddy Krueger accessories, scars, wounds and burn detals, and an creepy dreamwalker vibe. Put me in a basment/boiler room-style setting with rusted creepy, dank, dark scenery. Make it realistic, creepy AF, and high quality. 8k resolution, 2:3 format, octane render.

Details

GPT Image 2

Please create a separate, independently designed premium poster from each uploaded photo. Do not combine multiple photos into one composition; output one individual poster for each photo. Use a vertical 3:4 composition, with the upper and lower sections strictly divided 1:1, each occupying exactly 50% of the total height. Upper Half: Preserve the original photograph, maintaining the subject’s identity, structure, pose, realistic texture, natural lighting, and original color atmosphere. Apply only subtle, sophisticated color grading to give it the visual quality of an art magazine, independent publication, or exhibition image. To adapt the image to the 3:4 format, the surrounding background may be naturally extended, but do not stretch, distort, or alter the subject. Lower Half: Extract the most recognizable subject, silhouette, structure, pose, and narrative relationship from the photograph and reconstruct it in the style of Mid-century vernacular graphic illustration + schematic line drawing + two-color spot printing. Do not completely trace or replicate the photograph. Instead, use diagrammatic abstraction to compress complex objects into a small number of clear geometric shapes, functional contours, and essential structural elements. The result should resemble an illustration from an old instruction manual, advertising card, technical label, or vernacular print: immediately recognizable, yet more direct, humorous, and symbolic than the realistic object itself. Emphasize economy of line: if a structure can be explained with a single line, do not use unnecessary strokes. Use direct black pen outlines, rectangles, circles, diamonds, straight lines, and simple planes to describe the objects. People, animals, and objects may have slightly exaggerated proportions, while machines, buildings, and complex structures should be simplified into clear boxes, openings, panels, and silhouette relationships. Use a flat, schematic diagrammatic perspective rather than realistic lighting or strictly accurate spatial depth. The visual language should exist somewhere between illustration and technical diagram, maintaining this distinctive character throughout the composition. Reorganize the composition according to the most important narrative relationship in the original image. Maintain one clear primary subject, while using a small number of supporting objects, guide lines, directional relationships, or structural symbols to reinforce the story. Pay close attention to visual hierarchy, geometric order, scale contrast, positive and negative space, and intentional whitespace. The image may feel slightly naïve, awkward, or handmade in a vernacular way, but it must never feel cluttered. Every visual element should appear to exist for the purpose of “explaining what is happening”, rather than simply serving as decoration.

Details

GPT Image 2

Use the uploaded food photograph as the primary reference and transform it into a vertical 3:4 editorial art poster while preserving the main food, its appearance, composition, colors, textures, and recognizable details. Keep the upper half photorealistic, styled like a premium lifestyle/food magazine photograph: natural warm light, soft realistic shadows, elegant composition, authentic food textures, subtle film grain, vintage photography atmosphere, and a sophisticated cozy aesthetic. In the lower half, seamlessly transform the main food or a visually important element from the photograph into a whimsical hand-drawn scene or surreal miniature world related to the food. Extend, reshape, or reinterpret the food naturally as part of the illustration. Add one or two tiny human figures interacting with it in a charming, imaginative way. Use delicate imperfect ink linework, minimal vintage sketch style, subtle botanical/details, warm ivory paper texture, and plenty of negative space. Create a smooth, creative transition between the realistic photograph and the illustration so they feel like one continuous artwork rather than two separate images. The illustrated scene should tell a simple visual story based on the food and its characteristics. Add a short, witty handwritten caption that relates specifically to the food and the illustrated concept. Use small, understated handwritten typography that feels naturally drawn onto the paper. Overall style: premium editorial food photography + whimsical conceptual illustration + vintage storybook aesthetic + minimalist art direction + warm nostalgic mood. Composition: vertical 3:4, balanced negative space, realistic upper section, illustrated lower section, seamless transition, refined visual hierarchy. Avoid: changing the identity of the food, excessive decoration, clutter, large typography, borders, frames, logos, watermarks, harsh dividing lines, cartoonish 3D graphics, overly saturated colors, or an artificial AI-generated appearance.

Details

${ "prompt_type": "reference_template_identity_replacement", "CORE_RULE": "Use the supplied imag — AI image prompt — GPT Image 2$

GPT Image 2

{ "prompt_type": "reference_template_identity_replacement", "CORE_RULE": "Use the supplied image as a locked photographic template. Preserve the photograph as closely as possible, but replace the woman's facial identity with a completely different fictional adult woman.", "PRESERVE": [ "exact pose and body position", "head angle and gaze direction", "camera angle, height, perspective and framing", "subject scale and crop", "background and environment", "lighting and shadows", "hairstyle, hair length and placement", "ALL clothing exactly as shown in the reference", "ALL accessories and jewelry exactly as shown in the reference", "glasses, if present", "clothing colors, materials, patterns, fit and silhouette", "jewelry type, placement and appearance", "overall smartphone photography aesthetic" ], "IDENTITY_CHANGE": { "instruction": "Create a completely different fictional adult woman. Do not preserve the reference woman's recognizable identity or facial structure.", "change": [ "face shape", "eyes and eye spacing", "eyebrows", "nose", "cheekbones", "jawline", "chin", "lips", "overall facial proportions" ], "rule": "The new woman must clearly look like a different person while keeping the same photograph composition." }, "CLOTHING_AND_ACCESSORIES": { "instruction": "Do not invent, redesign or recolor the wardrobe. Automatically copy the clothing and accessories visible in the supplied reference image.", "preserve": [ "top or shirt", "bottoms", "dress or outerwear if present", "shoes if visible", "glasses if present", "necklaces", "earrings", "rings", "bracelets", "watches", "all other visible accessories" ], "important": "Whatever the woman is wearing or carrying in the reference must remain visually consistent in the generated image." }, "PHOTOGRAPHY": { "style": "authentic candid smartphone photograph", "realism": "extreme photorealism", "skin": "natural pores and realistic imperfections", "processing": "natural smartphone HDR", "retouching": "minimal and believable" }, "CLEANUP": [ "remove text", "remove watermarks", "remove logos", "remove captions", "remove UI elements", "remove screen borders", "remove black strips or borders" ], "NEGATIVE_PROMPT": [ "same woman", "same face", "facial duplicate", "recognizable identity", "different pose", "different camera angle", "different framing", "different background", "different clothing", "different accessories", "invented jewelry", "invented clothing", "changed clothing color", "missing accessories", "missing glasses", "CGI", "3D render", "plastic skin", "airbrushed skin", "anime", "illustration", "extra limbs", "deformed hands", "warped anatomy", "text", "watermark", "logo", "UI" ], "FINAL_COMMAND": "Treat the supplied image as a locked photographic template, not an identity reference. Keep the exact pose, camera, composition, environment, lighting, hairstyle, clothing and every visible accessory from the reference. Replace only the woman's facial identity with a completely different fictional adult woman. The result must look like a genuine photograph of a different person wearing the exact same outfit and accessories in the exact same scene." }

Details

GPT Image 2

Automotive concept poster, white background, top banner with Ferrari prancing horse logo and 'FERRARI F90 CONCEPT' in bold red/black text, Italian flag + 'ITALY' subtitle. Front 3/4 shot of a sleek red hypercar with aggressive front splitter and matte black wheels. Spec icon row: Engine (3.0L V6 Hybrid), Power (1,200 HP), Torque (900 Nm @ 6,000 rpm), 0-100 km/h (2.1s), Top Speed (360 km/h / 224 mph), Drivetrain (AWD, 8-Speed DCT). Below, rear 3/4 shot showing large rear diffuser and quad taillights. Bottom tagline: 'CRAFTED FOR PURE SPEED.

Details

GPT Image 2

Create a premium cinematic Adidas sports advertising image featuring a futuristic black Adidas performance sneaker as the hero product, suspended slightly above a dark reflective surface in a dramatic studio environment. The sneaker should look powerful, aerodynamic, and meticulously engineered, with realistic mesh, engineered knit, rubber outsole, subtle stitching, fine material textures, and the iconic Adidas three-stripe design clearly visible. Keep the product design authentic and commercially polished. Use dramatic directional lighting from above and behind, creating sharp rim highlights along the silhouette while revealing the intricate texture of the shoe. Add subtle atmospheric mist, tiny floating particles, and controlled motion-inspired light trails around the sneaker to suggest speed and energy without distracting from the product. The background transitions from deep charcoal to black with a subtle architectural texture inspired by a modern urban sports arena. The composition should feel minimal, bold, premium, and technologically advanced. Place the Adidas logo naturally and tastefully within the composition, with clean brand visibility and generous negative space. No unnecessary text. Camera: low-angle three-quarter product photography, 85mm lens, shallow depth of field, ultra-detailed macro-level textures, crisp focus on the sneaker, realistic reflections, cinematic contrast, professional commercial photography. Visual style: premium global sports campaign, futuristic athletic aesthetic, luxury product photography, dramatic editorial lighting, photorealistic materials, high dynamic range, sophisticated composition. Color palette: black, graphite, subtle metallic silver, with restrained white highlights. Aspect ratio: 3:4 vertical. Ultra-photorealistic, 4K detail, realistic materials, physically accurate lighting, premium advertising quality, clean composition, no distortion, no extra shoes, no malformed logos, no duplicate objects, no watermark.

Details

GPT Image 2

Create a highly realistic full-body fashion portrait of a young woman sitting elegantly on wide marble stairs inside a luxurious, sunlit modern building. She has long, straight dark-brown hair with soft bangs, natural facial features, a gentle expression, and realistic skin texture. She is wearing a rust-orange utility jacket draped over her shoulders, a cream ribbed knit sweater, a dark navy buttoned vest, high-waisted wide-leg navy trousers, and elegant rust-orange pointed-toe high heels. A matching structured rust-orange handbag rests beside her. She sits naturally with one hand supporting her face and the other resting beside her, relaxed editorial pose. Large floor-to-ceiling windows in the background reveal a softly blurred city and distant mountains. Warm golden sunlight streams through the windows, creating beautiful natural highlights and soft shadows across the marble architecture. Photorealistic fashion photography, luxury editorial aesthetic, natural skin texture, realistic fabric details, soft warm sunlight, shallow depth of field, cinematic composition, high detail, realistic proportions, subtle film grain, 9:16 vertical composition, no text, no watermark, no CGI or artificial

Details

GPT Image 2

A high-resolution, full-body paper-sculpture relief illustration of an elegant East Asian woman, viewed from a three-quarter back profile turned to the right. Her dark hair is styled in an intricate updo with a green paper-cut accent bun. She is centered in a minimal composition. She wears an elaborate, dimensionally layered off-the-shoulder paper gown in rich magenta, constructed with dense, complex paper quilling and accordion pleats that swirl and flow, fanning out into a textured train at her feet. Directly behind her head and back, a massive, stylized fuchsia paper-cut lotus flower radiating with thin black line-work and a green-capped center creates a large background canopy. Sprigs of delicate pink paper-cut cherry blossoms on thin green stems are in the foreground near her side. The background is a clean, neutral cream-colored surface with soft directional lighting casting precise, delicate shadows behind every sculpted element, creating depth. --ar 1:1

Details

GPT Image 2

Shot on 35mm film, editorial fashion campaign, crisp natural daylight with hard directional sun, true-to-life skin texture with visible freckles and pores, oversized 1980s power tailoring, high colour saturation, clean sharp focus, subtle film grain, candid unposed energy, commercial beauty photography Tight upper-body portrait of a young woman with freckled skin and glossy lips, chin tilted up, gazing past the camera. She wears an oversized charcoal pinstripe blazer over a crisp pale blue shirt with a black and white striped tie, one hand pulling at the tie knot. Slim gold rectangular glasses, long dark hair lifted across her face by wind, sunlight raking across the top of her head. A dark glass office facade sits out of focus behind her.

Details

GPT Image 2

From the image provided, generate a new hyper-realistic image in the foreground portraying a man with short to medium brown hair and fair skin, maintaining his real facial features without alteration. He is sitting on the sidewalk wearing a yellow raincoat with the hood up, leaving his face visible. He wears dark blue wide-leg jeans and slightly dirty white sneakers. In his right hand, he holds a red balloon, and with his left arm, he friendly hugs the clown Pennywise, who appears beside him. The background, slightly blurred, shows an American-style house with a front garden. The environment is humid, with light rain and wet asphalt, illuminated by bluish and cold tones that create a dark, melancholic mood. The lighting is natural and soft, with subtle reflections in puddles and realistic sparkles on the balloon. The image conveys a cinematic atmosphere of gentle tension and mystery, like a movie scene. Style: ultra-realistic quality 8K, Halloween photo style with an artistic touch. Don't change the face. (Use the attached image)

Details

GPT Image 2

A photorealistic vertical full-body portrait of the same girl from the black-shirt reference image. Keep her exact facial features, green-hazel eyes, fair skin tone, natural makeup, and dark brown hair in a loose bun. Place her in the same elegant outdoor terrace garden setting with white flowering plants and a vintage lantern. She is wearing a fitted cream camisole with thin straps, high-waisted loose sage-green trousers, and a small cream shoulder bag. Add the same delicate silver floral pendant necklace and natural, minimal styling. Her body pose, hand placement, outfit proportions, and overall composition should match the original reference image. Use warm golden-hour sunlight with soft highlights on her face and hair, creating a natural cinematic glow. Keep the background with a stone railing, distant lake, mountains, greenery, and soft sunset sky. Ultra-realistic photography, natural skin texture, realistic fabric details, sharp focus, soft depth of field, 9:16 vertical composition.

Details

GPT Image 2

ULTRA-REALISTIC NATURAL SMARTPHONE PHOTOGRAPH, vertical 3:4, spontaneous candid travel portrait of a young East Asian woman standing on a quiet stone walkway beside a misty mountain stream in a lush Japanese-inspired garden. She has long, softly wavy deep-black hair falling naturally over her shoulders and down her back, with a slightly off-center part and a few loose strands gently framing her face. Her facial features are delicate and youthful, with naturally textured skin, subtle realistic pores, minimal makeup, soft pink lips, and a relaxed thoughtful expression as she looks slightly past the camera. She is wearing a cream-colored lightweight knit cardigan over a simple muted sage-green camisole, paired with a flowing dark charcoal pleated midi skirt. A small vintage tan leather crossbody bag rests naturally against her hip, with a tiny red fabric keychain attached to the strap. Her body is angled slightly toward the stream while one foot is naturally positioned a little ahead of the other, as if she has just paused during a quiet morning walk. One hand gently holds the strap of her bag while the other lightly touches a strand of hair near her cheek. The pose feels spontaneous, relaxed, and completely unposed rather than like a fashion shoot. In the background, a clear shallow mountain stream flows over smooth dark stones, surrounded by moss-covered rocks, bamboo, ferns, flowering shrubs, and tall green trees. A small traditional wooden footbridge crosses the stream in the distance, partially hidden by soft vegetation. A couple of tiny distant pedestrians are naturally present on the pathway, adding subtle scale without distracting from the subject. The atmosphere is cool and slightly misty after a light morning rain. The sky is mostly covered with pale gray clouds, creating soft diffused natural daylight with gentle shadows and realistic muted green tones. Small droplets of moisture are visible on nearby leaves, while the wet stones subtly reflect the ambient light. RAW smartphone photography aesthetic, extremely realistic human skin texture, visible natural pores and tiny facial details, individual hair strands, anatomically accurate hands and fingers, realistic fabric weave and clothing folds, authentic leather texture, physically accurate reflections, natural ambient lighting, subtle smartphone computational photography characteristics, slight lens softness, realistic depth of field, mild background compression, tiny natural imperfections, no beauty filter, no artificial skin smoothing, no exaggerated bokeh, no CGI appearance, no plastic texture, no excessive sharpening, realistic body proportions, authentic candid travel photography, natural color grading, vertical 3:4 composition.

Details

GPT Image 2

Prompt 1 — Field Canopy Create a vertical 4:5 editorial travel-journal poster using the uploaded photograph as the exact visual reference. Show a wide open lush green field with large white star-shaped tensile canopy tents, smaller white shelters in the background, scattered wooden outdoor tables and chairs, distant tree-covered hills, and a bright blue sky with soft clouds. Preserve the architecture, proportions, perspective, tent placement, landscape, and overall composition of the photograph. Below the photograph, create a hand-drawn illustrated interpretation of the exact same scene in a playful modern sketchbook style. Use bold black ink outlines, flat bright blue sky, fresh green grass, white canopy structures, simple green trees, tiny yellow flowers, and minimal hand-drawn details. Make it feel like a cheerful outdoor-design magazine page. Add handwritten editorial typography on the illustrated section: FIELD CANOPY and smaller notes: open air green lawn white shelter noon light Add 01 with a simple underline. Keep generous blue and green negative space, textured paper feel, imperfect hand-drawn strokes, clean editorial layout, charming travel-journal aesthetic, sophisticated but playful. Prompt 2 — City Camp Create a vertical 4:5 editorial travel-journal poster using the uploaded photograph as the exact visual reference. Show a nighttime lakeside urban camping scene with a glowing modern dome canopy tent, a white triangular camping tent, warm string lights, camping chairs and a small table, green grass beside calm water, and a modern city skyline illuminated in the background. Preserve the original composition, perspective, tent positions, skyline arrangement, reflections, and nighttime atmosphere. Below the photograph, transform the same scene into a bold hand-drawn editorial illustration. Use thick black ink outlines, a vivid cobalt-blue night sky, deep navy skyscrapers with glowing yellow windows, bright green trees and grass, blue water, a warm yellow/orange illuminated dome tent, white triangular tent, camping chairs, tables, and delicate string lights. Add large playful handwritten typography: CITY CAMP and smaller handwritten notes: lakeside night glow urban view after dusk Add 03 with a simple underline. Use a clean magazine-style composition with generous blue negative space, subtle paper texture, imperfect hand-drawn strokes, playful illustrations, warm lighting, and a nostalgic outdoor-travel-journal aesthetic.

Details

GPT Image 2

A premium nostalgic editorial photo-and-sketch artbook page featuring a young East Asian woman at an airport terminal, arranged in a clean vertical 3:4 composition. The upper section shows an ultra-realistic candid photograph of the woman standing beside a large airport window, wearing a fitted white sleeveless top with a black puffer jacket casually slipping off her shoulders. She has long dark-brown hair falling naturally over one shoulder and holds a dark green Korean passport gently with both hands near her waist. Her pose is relaxed and natural, with her head turned to the side as she gazes thoughtfully toward the airport runway. Behind her, realistic airport architecture, glass windows, the runway, painted ground lines, and a boarding gate create an authentic travel atmosphere. Soft natural daylight enters through the window, with subtle film grain, realistic skin texture, authentic colors, shallow depth of field, and an intimate candid photography feeling. The lower section transforms the exact same woman, clothing, pose, airport environment, and composition into a detailed loose black-and-white hand-drawn ink illustration on warm cream-colored textured paper. Use expressive imperfect lines, delicate cross-hatching, subtle sketch shading, realistic anatomy, and a handmade Japanese-inspired visual diary aesthetic. Add elegant minimalist editorial typography in the surrounding cream negative space: a small “No. 24.” title, subtle Japanese handwritten-style text, a short poetic caption reading “Sometimes, I just stand in the light and let time be quiet.”, and tiny documentary-style notes such as time, date, location, and weather. Include understated words like “note.”, “observed.”, and “thought.” around the layout. Warm off-white paper texture, slightly imperfect ink printing, sophisticated contemporary photography journal design, nostalgic analog mood, generous negative space, cohesive transition between realistic photograph and sketch illustration, emotionally warm, highly detailed, premium artbook aesthetic, no watermark, no logos, vertical 3:4 aspect ratio.

Details

GPT Image 2

Create an ultra-realistic cinematic portrait of a young South Asian woman seated gracefully on the stone steps of a historic traditional South Asian palace. She is wearing an elegant dusty-rose pink traditional outfit with delicate gold floral embroidery, a flowing sheer dupatta draped naturally over her shoulders and cascading beside her, and matching embroidered trousers. She wears intricate traditional gold jhumka earrings, multiple pink and gold bangles, and subtle mehndi designs on her hands. She has long, naturally wavy dark-brown hair flowing softly around her shoulders. Her pose is graceful and relaxed, with both hands gently resting near her face. She looks slightly to the side with a soft, serene expression and subtle smile. Natural facial features, realistic skin texture, visible pores, delicate fine details, no excessive makeup or artificial beauty retouching. The background features ancient carved stone architecture, weathered steps, ornate pillars, and a beautiful arched doorway with warm sunlight glowing through it. Soft golden-hour lighting illuminates her face and outfit, creating a warm dreamy atmosphere with gentle shadows and cinematic depth. Shallow depth of field, realistic fabric texture, detailed embroidery, natural hair strands, photorealistic skin, professional fashion photography, 85mm lens, soft bokeh, cinematic color grading, high dynamic range, ultra-detailed, 8K, realistic photography, vertical composition, 9:16 aspect ratio.

Details

GPT Image 2

Create a two-panel travel poster inspired by the reference images. Top panel: a breathtaking photorealistic autumn landscape featuring a modern yellow sightseeing train traveling across a long elevated railway bridge over a perfectly calm lake. Surround the scene with dense golden-yellow autumn trees, vivid blue sky, soft white clouds, warm sunlight, and a crystal-clear reflection of the entire train, bridge, and foliage in the water. Highly detailed, vibrant colors, cinematic travel photography, realistic lighting, sharp focus. Bottom panel: transform the same scene into an elegant minimalist travel illustration. Show the yellow train crossing the elevated bridge, drawn with clean navy-blue hand-drawn linework and warm golden-yellow accents. Add a large golden sun/circle behind the train, stylized autumn leaves and branches framing the corners, subtle decorative stars and fine horizontal lines, and an off-white cream background. Preserve the recognizable train shape and composition from the photograph while giving it a refined editorial poster aesthetic. Style: premium travel magazine, sophisticated tourism poster, clean composition, harmonious color palette, highly detailed, balanced negative space, realistic-to-illustration transformation, vertical 4:5 layout, no text, no logos, no watermark.

Details

GPT Image 2

Transform the uploaded photograph into a minimalist, premium handmade editorial paper illustration. Use the photo strictly as reference and preserve the subject’s recognizable identity, facial features, hairstyle, facial hair, skin tone, body proportions, clothing, pose, expression, hands, umbrella and key recognizable details. Generate ONLY the illustration on a clean paper background. FORMAT LOCK Vertical 3:4 canvas. Small centered subject occupying approximately 15–25% of the canvas. Generous warm negative space. Do not crop important parts of the subject. STYLE TRANSFER Reinterpret the photograph as a sophisticated handmade watercolor, acrylic, colored-pencil and ink illustration. Preserve recognition while simplifying the image into a refined contemporary editorial artwork. Avoid photorealism and polished digital-vector aesthetics. DETAIL & COLOR Delicate imperfect ink outlines, loose watercolor washes, restrained acrylic shapes, dry-brush marks, rough pigment edges, subtle colored-pencil texture and natural paint imperfections. Warm ivory handmade paper with visible grain and fibers. Use a restrained palette of deep navy blue, muted dark green, natural skin tones and warm brown/ochre, with subtle blue and green environmental shapes. COMPOSITION LOCK Keep the subject small, centered and fully readable. Preserve the wavy dark hair, facial features and gentle smile, light facial hair, navy sweater, pale shirt collar, green umbrella, umbrella shaft, curved wooden handle, hand and ring. Simplify the environment aggressively into only a few loose painted shapes. Maintain a calm gallery-like composition with abundant clean negative space. STYLE Quiet, poetic, minimal, refined, warm, contemporary handmade editorial illustration. Premium art-book aesthetic, tactile paper surface, organic edges, subtle pigment variation and authentic traditional craftsmanship. NEGATIVE PROMPT No photograph, photorealism, split-screen, collage, top-and-bottom layout, second panel, photographic half, detailed background, oversized subject, large illustration, digital vector art, glossy CGI, 3D, anime, cartoon exaggeration, excessive detail, chaotic colors, typography, text, letters, words, numbers, logos, symbols, watermark or signature

Details

GPT Image 2

Create a hyper-realistic full-body low-angle outdoor adventure portrait of the same young adult female character from the reference image, preserving her vivid violet-purple chin-length bob with straight bangs, fair porcelain skin, natural freckles across her nose and cheeks, hazel/light-brown eyes, delicate facial features, glossy lips, and slim physique. She is walking across a textured sand dune while bending forward, one hand reaching down toward the sand and her head looking downward. She wears a beige and olive-green technical outdoor jacket over a neutral inner top, beige high-waisted outdoor shorts, tall tan-and-olive hiking boots with socks, a brown fabric beanie, black chest harness straps, and a small carabiner clip. The background features beautiful desert sand dunes with detailed ripples, distant green trees, and a clear sky. Use warm natural daylight with soft shadows and a cinematic outdoor adventure atmosphere. Emphasize realistic sand texture, fabric details, hiking boots, individual hair strands, natural skin and freckles, cinematic depth of field, photorealistic quality, ultra-detailed 8K, premium outdoor editorial photography.

Details

GPT Image 2

Using my uploaded photo, turn me into a fun Die Hard-inspired version of myself. Keep my face and features recognizable. Dress me in a barefoot John McClane-inspied outfit with Die Hard accessories, scar, wound and bruises detals, and an urgent/rugged off duty police officer vibe. Put me in a glass skyscraper-style setting with offices under construction scenery with pieces of broken glass covering the floor. Make it realistic, intense, and high quality. 8k resolution, 16:9 format, octane render.

Details

GPT Image 2

Transform every visible person in the uploaded image into realistic LEGO-style minifigure toys while preserving each person’s recognizable identity, hairstyle, outfit, colors, accessories, relative height, pose, and relationship to each other. FORMAT LOCK — NON-NEGOTIABLE Vertical 3:4 aspect ratio. Full-body product composition. All figures must be fully visible from head to toe. Do not generate square, landscape, widescreen, close-up, cropped, or half-body compositions. PERSON COUNT LOCK — NON-NEGOTIABLE Detect all visible people in the uploaded image. If there is 1 person, create 1 LEGO-style minifigure. If there are 2 people, create 2 LEGO-style minifigures. If there are 3 or more people, create the same number of LEGO-style minifigures. Do not remove, merge, ignore, duplicate, or replace any person. Every person visible in the reference image must appear as their own separate LEGO-style minifigure. REFERENCE LOCK — NON-NEGOTIABLE Use the uploaded image as the only reference for all subjects. Preserve each person’s recognizable facial identity as much as possible within the simplified LEGO minifigure style. Maintain each person’s hairstyle and hair color, adapted into molded LEGO-style plastic hairpieces. Preserve each person’s facial expression, clothing colors, clothing design, visible patterns, accessories, and styling. The final figures must clearly represent the same people translated into LEGO-style toy form. Do not create generic minifigures. Do not redesign outfits or invent new accessories. CLOTHING DETAIL LOCK Recreate each person’s outfit as accurately as possible in LEGO minifigure form. Preserve the exact clothing color palette, layering, garment type, collar shape, neckline, sleeves, jacket shape, pants or skirt style, shoes, visible patterns, seams, buttons, zippers, belts, logos, jewelry, bags, glasses, hats, and accessories. Translate real clothing into printed LEGO torso and leg graphics with clean toy-style linework. Outerwear should appear as molded or printed LEGO-style clothing details. Shoes should be simplified into LEGO foot/leg prints while keeping the original color and style. Do not replace outfits with generic LEGO clothing. Do not simplify clothing so much that the original styling is lost. GROUP COMPOSITION Keep the same number of people from the uploaded image. Preserve the relationship between subjects. Preserve relative height differences. Preserve basic pose direction and body language. If the reference shows a couple, create a matching LEGO-style couple. If the reference shows a group, create the full group as separate minifigures. Arrange the figures naturally together in a clean product-style composition. LEGO MINIFIGURE STRUCTURE Use authentic LEGO-style minifigure proportions for every figure. Cylindrical heads. Simplified printed facial features. Block-shaped torsos. Printed clothing details on each torso. Standard minifigure arms. Curved minifigure hands. Short minifigure legs. Custom molded plastic hairpieces matching each subject’s hairstyle. Classic yellow heads or realistic skin-tone heads depending on the uploaded subjects and chosen visual direction. MATERIAL & TEXTURE Render all figures as realistic molded plastic. Subtle glossy finish. Fine molded seams. Clean toy-surface reflections. Realistic plastic highlights. Printed face, torso, and leg details. Hairpieces should look like molded plastic, not real hair. Clothing should appear as printed LEGO-style graphics and molded toy details, not real fabric. COMPOSITION Full-body minifigures visible from head to toe. All figures centered in the frame. Entire group fully visible. No cropping. No close-up portrait framing. No props. No scenery. No extra elements. BACKGROUND Pure clean white background. Studio product photography setup. Minimal and premium. No environment, no table clutter, no unrelated objects. LIGHTING Soft diffused studio lighting. Subtle natural shadows beneath the figures. Crisp detail visibility. Balanced reflections across the plastic surfaces. Professional toy photography quality. OUTPUT STYLE Photorealistic LEGO-style minifigure toy render. High-quality 3D product visualization. Sharp focus. Clean white-background presentation. Premium collectible toy aesthetic. Highly detailed plastic texture. Professional studio lighting. The final image should look like realistic custom LEGO-style minifigures of every visible person from the uploaded image, photographed as a premium toy product.

Details

${ "aspect_ratio": "9:16", "style": "surreal colorful high-fashion editorial", "subject": { — AI image prompt — GPT Image 2$

GPT Image 2

{ "aspect_ratio": "9:16", "style": "surreal colorful high-fashion editorial", "subject": { "character": "beautiful young European blonde woman", "expression": "confident, playful", "accessories": "elegant sunglasses", "outfit": "bright orange cropped jacket, lime-green wide-leg trousers, cream sneakers" }, "action": "riding a cream vintage bicycle through a surreal fantasy garden", "pose": "dynamic three-quarter rear view, leaning naturally into the ride while turning her head toward the camera", "bicycle": "cream-colored vintage bicycle with a small minimal flower basket", "environment": { "setting": "open surreal garden", "flowers": "few enormous sculptural flowers placed far apart, oversized orange, yellow and turquoise petals", "ground": "pale mint pathway with generous empty space" }, "composition": { "camera": "dramatic low-angle hero shot", "framing": "full bicycle and full character visible", "foreground": "one giant flower subtly framing the edge", "negative_space": "strong, clean, uncluttered" }, "lighting": "warm golden daylight with cinematic shadows", "mood": "wild, playful, bizarre, luxurious, dreamlike", "visual_quality": "exaggerated scale, vibrant color harmony, crisp textures, unconventional fashion editorial energy, striking visual impact" }

Details

GPT Image 2

Create a hyper-realistic low-angle close-up fashion portrait of the same young adult female character from the reference image, preserving her vivid violet-purple chin-length bob with straight bangs, fair porcelain skin, natural freckles across her nose and cheeks, hazel/light-brown eyes, delicate facial features, glossy lips, and slim physique. She is crouching on outdoor concrete stairs with her knees bent wide apart, facing the camera confidently, hands relaxed between her knees. She wears a bright red oversized hooded windbreaker with the hood up, light-wash loose-fit blue denim jeans with rolled cuffs, vibrant red suede sneakers with thick white laces and white soles, and casual urban accessories. The background features a chain-link fence with softly blurred city buildings beneath an overcast sky. Use soft diffused natural daylight, realistic skin and hair, detailed denim and sneaker textures, cinematic depth of field, trendy urban streetwear editorial aesthetic, photorealistic, ultra-detailed, 8K.

Details

GPT Image 2

Photorealistic portrait of a beautiful young Asian woman in her early 20s, standing outdoors on a city street during warm golden hour. She has long, straight, dark brown to black hair flowing naturally over her shoulders, soft natural facial features, almond-shaped brown eyes, subtle eyeliner, natural eyebrows, a gentle confident smile, and smooth realistic skin. She is wearing a cozy oversized beige knitted off-shoulder sweater with long sleeves and fitted blue denim jeans. One hand is raised behind her head, lightly touching her hair, while the other arm rests naturally across her waist. A dark brown luxury-style handbag hangs from her arm. Warm sunlight illuminates her face and shoulders from the side, creating soft golden highlights and natural skin tones. The background is a blurred urban street with trees, cars, and buildings, strong shallow depth of field, creamy bokeh, cinematic atmosphere. Medium-full body portrait, slightly low eye-level perspective, natural relaxed pose, realistic anatomy, detailed hair strands, realistic knit sweater texture, detailed denim fabric, professional fashion photography, DSLR camera, 85mm portrait lens, f/1.8, soft background blur, golden hour lighting, cinematic color grading, ultra-detailed, photorealistic, high dynamic range, natural shadows, sharp focus on face, 8K quality, vertical composition, 3:4 aspect ratio.

Details

GPT Image 2

Hyper-realistic wildlife photograph. A young cheetah cub sitting in tall golden savannah grass at sunrise, enormous curious eyes looking directly at the camera, soft morning light glowing through its spotted fur. Soft warm golden light, shallow depth of field, gentle bokeh, innocent vulnerable energy. National Geographic grade, 4:5 vertical, 8k, no text.

Details

GPT Image 2

Premium luxury 3D miniature travel poster for [CITY_NAME], 3:4 vertical format. Create an original, sophisticated destination poster combining a raised architectural diorama, elegant vintage travel typography, realistic miniature details, and a beautiful cityscape viewed from a wide three-quarter angle. CITY IDENTITY Build the scene specifically around [CITY_NAME], featuring: One iconic landmark as the main focal point. The city's recognizable river, lake, coastline, or natural landscape where appropriate. Local architecture, bridges, streets, and waterfront areas. One or two authentic transportation elements such as boats, trains, or trams. Small pedestrians and subtle everyday city activity. The entire destination should look like a carefully crafted miniature city model sitting on a thick dark stone base. MAIN DIORAMA Create a highly detailed raised 3D cityscape with: miniature buildings iconic landmark bridges waterways boats or local transport trees and landscaped areas tiny streetlights small pedestrians warm architectural lighting realistic water reflections Use a wide elevated perspective so the city feels expansive while the stone base clearly shows the three-dimensional construction. SEASON & ATMOSPHERE Choose the season that best represents [CITY_NAME]. For winter destinations, use elegant snow-covered rooftops, snowy trees, cool blue water, and warm glowing windows. For warmer destinations, use lush green trees, golden-hour sunlight, warm architecture, and calm reflective water. Keep the atmosphere premium, peaceful, and visually clean. TYPOGRAPHY Place a small elegant tagline at the top, followed by: [CITY_NAME] in large sophisticated serif typography. Below: [COUNTRY] Add one short destination-inspired phrase. Include a small elegant brass or metallic plaque on the front of the stone base containing: [CITY_NAME] [COORDINATES] Typography should be crisp, luxurious, editorial, and correctly spelled. ART DIRECTION Luxury miniature architectural model, premium European travel poster, high-end tourism branding, realistic 3D diorama, elegant editorial design, detailed miniature city, refined architectural modeling, soft natural lighting, sophisticated postcard aesthetic. COLOR SYSTEM Use warm ivory and cream for the background, balanced with architectural neutrals, deep navy, soft blue, natural greens, muted gray, and subtle warm golden lighting. Keep the palette elegant, slightly desaturated, cohesive, and luxurious. MOOD Timeless, peaceful, luxurious, refined, romantic, sophisticated, and atmospheric. IMPORTANT QUALITY RULES Make the composition unique to [CITY_NAME]. Adapt the landmark, architecture, geography, transportation, season, viewpoint, and city layout specifically to the destination. The raised stone base must remain clearly visible and convincingly three-dimensional. Keep the city detailed but uncluttered. The landmark should be recognizable without overwhelming the entire composition. NEGATIVE PROMPT No generic city. No copied template. No random landmarks. No landmark collage. No flat illustration. No watercolor. No painterly brushwork. No messy composition. No excessive snow. No oversized people. No crowded streets. No distorted buildings. No malformed boats or vehicles. No floating architecture. No flat base. No weak 3D depth. No neon colors. No excessive gradients. No cluttered typography. No misspelled text. No watermark. No blurry details. No low-resolution architecture.

Details

GPT Image 2

Create an ultra-realistic cinematic travel fashion portrait of a beautiful young woman standing on Westminster Bridge in London during golden hour, with the iconic Big Ben clock tower and the Palace of Westminster in the background. She has long, thick, naturally wavy dark brown hair, parted slightly in the middle, with soft loose strands framing her face. She has delicate feminine facial features, natural glowing skin, expressive dark brown eyes, soft pink lips, and a gentle, charming smile. Her head is slightly tilted toward the camera, creating a natural and elegant pose. Outfit: She is wearing a stylish oversized dark brown leather jacket over a fitted black cropped top, paired with high-waisted light blue vintage-wash denim jeans. A small black crossbody shoulder bag hangs diagonally across her body. The outfit looks effortlessly chic, casual, and fashionable. Pose: Standing beside the green-painted iron railing of Westminster Bridge, her body slightly angled toward the camera. One arm rests naturally on the bridge railing, while the other hangs relaxed. Her head is tilted slightly, and she is looking directly into the camera with a soft, warm smile. Natural, confident travel photography pose. Background: A breathtaking view of the River Thames, the Palace of Westminster, and Big Ben clearly visible behind her. A white river boat is moving along the Thames. The bridge railing and London architectural details are visible on the right side. The background is slightly blurred but recognizable. Lighting: Magical golden-hour sunset lighting, warm orange and peach sky, soft sunlight illuminating her face and hair from behind, beautiful golden reflections on the River Thames, subtle lens flare, realistic shadows, and a dreamy romantic atmosphere. Photography style: Ultra-realistic professional travel photography, cinematic fashion editorial, natural beauty portrait, DSLR photography, 50mm lens, f/2.0 aperture, shallow depth of field, realistic skin texture, detailed hair strands, natural facial proportions, high dynamic range, warm cinematic color grading. Composition: Vertical 4:5 portrait, medium-full body shot, subject centered slightly to the right, Big Ben visible in the upper-right background, beautiful sunset sky filling the upper frame, realistic perspective, highly detailed, photorealistic, 8K quality. Negative prompt: Cartoon, anime, illustration, CGI, plastic skin, overly smooth face, distorted facial features, blurry eyes, extra fingers, deformed hands, unnatural hair, unrealistic body proportions, oversaturated colors, harsh shadows, low resolution, watermark, text.

Details

GPT Image 2

Transform the uploaded photo into a charming hand-drawn fashion illustration while preserving the original scene and composition. Keep the same people, number of people, pose, body positioning, facial expressions, clothing, accessories, hairstyles, objects, drinks, and overall framing from the reference photo. Do not add or remove important elements. Convert the realistic photograph into a minimal Japanese/Korean-inspired lifestyle sketch illustration, using loose but confident dark green ink linework with subtle hand-drawn imperfections. Simplify facial features while keeping each person’s recognizable hairstyle, glasses, headphones, clothing silhouette, and pose. Use a soft pastel pink background with the illustration drawn primarily in deep forest-green ink. Replace realistic textures, shadows, vehicles, buildings, pavement, and surroundings with simplified expressive linework and selective cross-hatching. Keep enough environmental details to make the original location and composition recognizable. Style: cute editorial illustration, Japanese stationery aesthetic, fashion sketch, casual slice-of-life manga drawing, imperfect pen strokes, clean negative space, minimal detailing, subtle vintage feel, handmade appearance. Color treatment: predominantly pastel pink background + dark green line art, with very minimal secondary tones if needed. No photorealism, no 3D rendering, no glossy digital painting. Important: preserve the original image’s composition, perspective, camera angle, poses, proportions, clothing, accessories, and key objects. The result should look like the exact photograph was redrawn by an illustrator, rather than redesigned into a different scene. Output: clean vertical illustration, aesthetically balanced, high-resolution, polished hand-drawn finish. Short version for image models: Turn this photo into a cute hand-drawn Japanese lifestyle/fashion sketch. Preserve the exact people, poses, expressions, clothing, hairstyles, accessories, drinks, composition, camera angle and important background elements. Redraw everything with loose imperfect dark forest-green ink linework on a soft pastel pink background, using minimal cross-hatching and simplified details. Charming editorial stationery aesthetic, casual manga-inspired illustration, handmade pen texture, clean negative space, elegant and whimsical. Do not change the composition or add/remove subjects; make it look like the original photo was directly illustrated by hand.

Details

GPT Image 2

Create a hyper-realistic full-body cinematic portrait of the same young adult female character from the reference image, preserving her signature appearance: vivid violet-purple chin-length straight bob haircut with soft bangs, fair porcelain skin, natural freckles across her nose and cheeks, hazel/light-brown almond-shaped eyes, small straight nose, delicate facial features, glossy natural lips, and slim physique. She is seated on a rustic wooden chair, one knee pulled up toward her chest while she holds and adjusts the shoelace of her raised foot. She leans slightly forward with her head tilted toward the camera and a calm relaxed expression. She wears an oversized loose olive-green short-sleeved T-shirt, light-blue denim jeans with rolled-up cuffs, dark canvas Converse-style sneakers with white soles, black round-framed glasses, and a small beige crossbody/waist bag. Set the scene outdoors among weathered stone and brick ruins, with an old stone archway framing the composition, dry plants and foliage in the foreground, and the wooden chair resting on earthy dirt ground. Fill the background with thick light-orange and peach-colored smoke creating a dreamy dramatic haze. Use soft moody natural lighting with warm pastel smoke tones, realistic shadows, cinematic depth of field, detailed skin and hair, authentic denim and fabric textures, atmospheric haze, photorealistic quality, ultra-detailed 8K, premium editorial photography, dreamy rustic aesthetic.

Details

GPT Image 2

Create one independent editorial-style poster for each uploaded photo. Do not make a collage. Process and output each photo separately. Use a strict 3:4 vertical composition, divided horizontally into two exactly equal sections, each occupying 50% of the canvas. TOP HALF — ORIGINAL PHOTOGRAPH Preserve the original photo. Keep the main subject unchanged while retaining its realistic texture, natural lighting, and original color atmosphere. Apply only subtle editorial-grade color correction to create the refined feel of an art magazine, independent publication, or exhibition photography. To fit the composition, you may gently extend the sky, ground, or surrounding environmental background, but do not stretch, distort, or alter the main subject. BOTTOM HALF — LAYERED PAPER CUT / PAPER ART REINTERPRETATION Reinterpret the most recognizable subject, silhouette, pose, and spatial relationships from the photo as a minimalist layered paper-cut / paper-art composition. Use one primary subject as the visual anchor. Do not mechanically reproduce every detail. Instead, reconstruct the key silhouette, proportions, and structure through folding, cutting, layering, and overlapping. Transform only a few supporting environmental elements into foreground, midground, and background paper layers. Use scale contrast, negative space, clean alignment, and front-to-back layering to make the subject immediately recognizable while maintaining a restrained editorial composition. COLOR & MATERIAL Extract the most distinctive and recognizable colors from the original photo, then reduce them into a limited and harmonious paper-art palette. Use warm ivory or light-colored paper as the base, supported by a small amount of stronger accent colors, darker structural tones, soft transitional layer colors, and very limited highlights. The material should resemble high-quality matte cardstock, with subtle visible paper fibers, clean cut edges, and soft contact shadows under natural diffused lighting. Emphasize the tactile quality of real handcrafted paper art. Avoid glossy plastic-like 3D effects, cheap craft-paper aesthetics, neon colors, and overly saturated or complex gradients. EDITORIAL TYPOGRAPHY SYSTEM Add a refined editorial typography system. Based on the identity, location, action, material, emotion, or symbolic meaning of the subject, create one short main title. Add 2–4 groups of smaller supporting text. These may include object names, location information, numbers, sequence markers, coordinate-like numbers, direction words, status words, material descriptions, classification labels, or a very short poetic phrase. Do not use any year or date. The main title should convey emotion and identity, while the smaller text should add rhythm, structure, and refinement. TYPOGRAPHY INTEGRATION Integrate the typography naturally into the composition so that it interacts with the paper-cut forms. Arrange text along paper-layer edges, subject contours, geometric axes, or areas of negative space. Use horizontal or vertical typesetting, rotated text, generous letter spacing, edge alignment, corner placement, cross-section layouts, embedded typography, or partially overlapped text. The main title may have a subtle paper-cut or folded-paper quality, while the supporting text should remain thin, modern, restrained, and precise. The final result should feel elegant, tactile, balanced, art-directed, and distinctly editorial.

Details

GPT Image 2

Create a hyper-realistic full-body luxury fashion editorial portrait of the same young adult female character from the reference image. Preserve her signature appearance exactly: vivid violet-purple chin-length blunt bob haircut with straight bangs, fair porcelain skin, natural freckles clearly visible across the nose and cheeks, soft delicate facial features, almond-shaped hazel/light-brown eyes, small straight nose, natural glossy lips, slim elegant physique, and youthful sophisticated appearance. Do not change her hairstyle or facial characteristics. She is standing confidently in a full-body fashion lookbook pose, facing the camera with a slight hip tilt. Her left hand rests naturally on her hip while her right arm extends downward holding a vintage worn skateboard upright by its nose. Her feet are slightly apart and her posture is relaxed but confident. She wears a bright yellow Brazil national football jersey-style T-shirt with green trim around the collar and sleeves, tucked naturally into tight black high-waisted biker shorts. She wears clean white crew socks and classic white Adidas Samba-style sneakers with black three-stripes and gum-colored soles. Add layered delicate gold neck chains with a small elegant pendant. Set the scene inside a stylish light lavender-purple studio with a nostalgic 1990s/Y2K skater and football-inspired collage aesthetic. Cover the background with carefully arranged newspaper cutouts featuring retro Nike-style graphics, a Thrasher magazine cover, skateboard imagery, comic-style flame stickers, yellow lightning bolt graphics, paper tape strips, handwritten to-do lists, small sun and smiley illustrations, retro soccer-player posters, vintage Brazil football imagery, and a classic 1990s computer window interface. Make the collage look like authentic physical paper, stickers, tape, and printed photographs attached to the wall. Use bright professional studio flash lighting with soft shadows, vibrant colors, subtle glow, realistic skin texture, detailed individual hair strands, natural fabric texture, realistic footwear and skateboard materials, and a slightly nostalgic editorial film aesthetic. Composition: vertical full-body fashion lookbook photography, subject centered, entire body visible from head to shoes, skateboard fully visible, balanced negative space, clean magazine-quality framing. Style: premium fashion editorial, 90s Y2K streetwear, skater culture, football nostalgia, retro magazine aesthetic, contemporary lookbook photography. Quality: ultra-realistic, photorealistic, highly detailed, 8K, HDR, realistic skin, realistic hair, crisp textures, cinematic depth of field, professional commercial photography, premium color grading.

Details

About GPT Image 2

GPT Image 2 is OpenAI's image generation model, and it works differently from most: instead of diving straight into pixels, it plans the layout, reasons about your instructions, and self-checks before it draws. That deliberate pipeline is why it handles briefs that would trip up faster models.

Its standout strength is complex multi-part instructions. Ask for a labeled diagram, an infographic with several panels, or a scene where three characters each do something specific, and GPT Image 2 keeps track of every requirement. Text rendering is another reliable strength — signs, labels, and headlines come out legible instead of garbled.

A model that actually reads your whole prompt rewards prompts worth reading. Vague briefs waste its reasoning; precise ones let it shine. The gallery below collects tested GPT Image 2 prompts with their real outputs, so you can start from a structure that already works.

How to write GPT Image 2 prompts

1Write the full brief, not a keyword pile. GPT Image 2 reasons over your instructions, so numbered requirements and complete sentences outperform comma-separated tags.
2Spell out every element and its relationship: "a three-panel comic; panel one shows…, panel two shows…". The model tracks multi-part structure — give it the structure to track.
3Put exact text in quotation marks: a sign reading "OPEN 24 HOURS", a mug printed with "World's Okayest Coder". Quoted strings render far more faithfully than paraphrased ones.
4Describe layout intent explicitly — foreground vs. background, left vs. right, what overlaps what. Because the model plans composition first, spatial language directly shapes the plan.
5State constraints as rules, not hopes: "no watermark, flat vector style, white background, exactly four icons". GPT Image 2 treats explicit rules as a checklist during its self-check.
6Iterate by editing the brief, not rerolling. When one element is wrong, revise that clause and keep the rest verbatim — the model's instruction-following makes targeted fixes stick.

Frequently asked questions

What is GPT Image 2 best at?

Complex, multi-requirement images: infographics, diagrams, UI mockups, scenes with several distinct elements, and anything that needs readable text. Because it plans and self-checks before drawing, it is among the strongest models at following long, precise instructions without dropping details.

How do I write good GPT Image 2 prompts?

Treat the prompt as a design brief. List every element, its position, and any exact text in quotes, then state your style and constraints as explicit rules. The tested prompts on this page show the pattern in action — copy one and swap in your own content.

Can GPT Image 2 render text inside images?

Yes, and reliably — legible signs, labels, headlines, and packaging copy are one of its signature strengths. Put the exact wording in quotation marks and describe where it should appear; the model's self-check pass helps keep the spelling intact.

Where can I use GPT Image 2?

GPT Image 2 is available through ChatGPT and via the OpenAI API for developers. Copy any prompt from this page, paste it there, and adjust the elements or text to fit your project.

Related models

GPT Image 2.5

OpenAI's GPT Image 2.5 — up to 50% faster than Images 2, with pinpoint local edits that leave the rest of the frame untouched and reference subjects that stay recognizable across repeated rounds.

image

181 prompts

GPT-6 Astra

OpenAI's GPT-6 Astra — the frontier reasoning model inside ChatGPT that plans first, then directs image and video generation from a single conversational prompt.

imagevideo

28 prompts

Nano Banana

Google's fast, free conversational image generation and editing model.

image

97 prompts

Nano Banana Pro

Google's Gemini image flagship with 4K output, Thinking mode and search grounding for reference-accurate results.

image

61 prompts

Browse AI Image Prompts All models