LogoAhaPrompt
  • Prompts
  • Featured
  • Models
  • Submit
  • Blog
AhaPromptAhaPrompt

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

Built withLogoNEXTY.DEV
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 PolicyTerms of Service
HomeAI Prompt LibraryAI Image PromptsCinematic Mixed-Berry Sorbet Commercial
Cinematic Mixed-Berry Sorbet Commercial — AI image prompt — GPT Image 2 — Macro, Cinematic, Food

Cinematic Mixed-Berry Sorbet Commercial

OpenAIGPT Image 2OpenAIimage

Create a premium 10-second vertical 9:16 cinematic food-preparation video for homemade mixed-berry sorbet, divided into 4 seamless scenes of 2.5 seconds each. Use ultra-realistic food photography, natural textures, shallow depth of field, soft natural lighting, macro close-ups, realistic food movement, and crisp natural kitchen sounds. No people, no text, no logos. SCENE 1 — 0–2.5s | FROZEN BERRIES Macro cinematic close-up of a clear glass bowl filled with freshly frozen raspberries, blackberries, blueberries, and strawberries. Visible frost crystals and icy texture on the berries. Slow camera push-in, subtle natural movement, beautiful soft daylight, premium food-commercial aesthetic. SCENE 2 — 2.5–5s | BLEND Close-up of frozen mixed berries inside a transparent blender jar. Golden honey slowly drizzles over the berries, followed by a small squeeze of fresh lemon juice. The ingredients begin blending into a thick vibrant red-purple mixture. Capture realistic honey viscosity, berry texture, reflections on the glass, and natural kitchen sounds. SCENE 3 — 5–7.5s | FREEZE Extreme close-up of the thick berry mixture being poured smoothly into a shallow freezer container. The glossy sorbet mixture folds naturally as it lands and spreads. A spatula gently smooths the surface. Rich raspberry-red color, realistic creamy frozen texture, cinematic macro focus. SCENE 4 — 7.5–10s | FINAL SORBET Beautiful hero shot of perfectly formed scoops of vibrant mixed-berry sorbet in a stylish bowl, surrounded by fresh raspberries, blackberries, blueberries, and strawberry slices. One scoop is prominently in focus with visible icy-creamy texture. Slow cinematic camera orbit, soft highlights, appetizing condensation, elegant premium dessert-commercial finish. Visual style: ultra-photorealistic, cinematic food commercial, macro lens, shallow depth of field, natural daylight, realistic textures, smooth camera motion, rich berry colors, subtle filmic look, 4K detail, physically accurate food physics. Audio: natural kitchen ambience, berry movement, honey drizzle, blender sound, soft pouring and spatula sounds. No music, no voiceover. Format: 9:16 vertical, 10 seconds, 4 scenes, seamless transitions, consistent ingredients and visual style throughout.

Details
Type
AI Image Prompts
Aspect Ratio
2:3
Updated
Sep 9, 2026
Category
MacroCinematicFood
Source

How to use this prompt

  1. 1Copy the full prompt with the copy button above.
  2. 2Open GPT Image 2 by OpenAI, or any image generator with a similar style range.
  3. 3Paste the prompt, then swap the subject and style keywords to match your idea.
  4. 4Match the example's settings (2:3 · Macro · Cinematic · Food), 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 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 using: 2:3 · Macro · Cinematic · Food. 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 prompts

Create an ultra-realistic cinematic 4:5 vertical travel photograph of a sleek, minimalist travel car — AI image prompt — GPT Image 2
OpenAIGPT Image 2
Create an ultra-realistic cinematic 4:5 vertical travel photograph of a sleek, minimalist travel card held naturally in one hand against an expansive sky. Use [COUNTRY NAME] as the creative focus. Transform the card into a living window into the destination, with a breathtaking miniature aerial world seamlessly emerging from its surface. Feature the country's most iconic landmark, surrounded by authentic landscapes, architecture, atmosphere, and subtle details unique to the destination. Make the transition between the physical card and miniature world seamless, magical, and physically believable, as if the entire destination exists inside the card. Integrate [COUNTRY NAME] in elegant, bold uppercase typography as part of the card design. Use cinematic natural light, realistic textures, atmospheric depth, subtle reflections, dramatic perspective, soft lens falloff, and premium editorial travel-photography aesthetics. Ultra-photorealistic, 8K detail, cinematic color grading, realistic skin and materials, physically accurate lighting, luxurious, emotional, aspirational, universally beautiful. No cartoon, no illustration, no artificial CGI appearance.
Details
GPT Image 2 on ChatGPT 

Prompt:

Ultra-cinematic surreal clone photography, aerial high-angle view  — AI image prompt — GPT Image 2
OpenAIGPT Image 2
GPT Image 2 on ChatGPT Prompt: Ultra-cinematic surreal clone photography, aerial high-angle view of a young Indian man standing motionless at the center of a vast urban plaza while dozens of identical copies of him move around in different directions. The clones all share the same appearance as each other, creating a striking visual repetition effect, but are not based on any reference image or real person. Handsome Indian male with a sharp jawline, neatly styled textured black hair, trimmed beard, expressive dark eyes, natural skin texture, and realistic facial proportions. Every clone has the exact same face, outfit, hairstyle, and body proportions. The central character remains perfectly sharp and isolated from the crowd, standing confidently with hands in pockets, wearing an oversized cream hoodie, black cargo pants, white sneakers, and dark sunglasses. Surrounding clones wear the identical outfit and appear slightly motion-blurred as they walk, run, and cross paths around him. Strong contrast between stillness and motion. Expansive geometric stone pavement, minimal modern architecture, subtle city elements, warm early-morning sunlight, soft atmospheric haze, realistic shadows, cinematic depth, and premium editorial fashion photography aesthetics. Tilt-shift effect creates a miniature-world illusion while maintaining realistic scale. Mood is introspective, powerful, and surreal, one person surrounded by endless versions of himself. Hyper-realistic skin detail, authentic anatomy, natural proportions, realistic clothing folds, cinematic color grading, shallow depth of field, HDR lighting, subtle film grain, luxury fashion campaign quality, contemporary surreal visual storytelling. No face distortion, no extra limbs, no duplicated body errors, no asymmetrical eyes, no cartoon style, no artificial AI-looking faces. Shot on Sony A7R IV, 85mm lens, f/1.8, aerial perspective, ultra-detailed, 8K, vertical 9:16 composition.
Details
Daily snapshot style, not carefully composed or lit, beside a bench on a school corridor, striped T- — AI image prompt — GPT Image 2
OpenAIGPT Image 2
Daily snapshot style, not carefully composed or lit, beside a bench on a school corridor, striped T-shirt with a suspender skirt, a small bear charm on the backpack, a can of Coca-Cola in hand; shot from behind a road sign, with the sign edge and leaves forming a double-layer foreground frame, slightly out of focus; overcast natural light, low contrast, low saturation, fabric texture and small accessories clearly visible, youthful and cute." "60mm, f/2.8, 1/400s, ISO 200, WB 5400K; local sharpening only on accessories and around the eyes, natural fair skin, visible clothing fabric texture, Japanese-style low saturation. Slight motion blur, overall ordinary and everyday, sweet and cute style.
Details
Use the uploaded reference image as the visual reference for the overall composition, pose, styling, — AI image prompt — GPT Image 2
OpenAIGPT Image 2
Use the uploaded reference image as the visual reference for the overall composition, pose, styling, lighting, and feminine aesthetic. Preserve the subject’s facial identity and natural facial proportions accurately. A highly realistic feminine lifestyle portrait of a woman reclining comfortably on a deep burgundy velvet sofa, photographed from a slightly elevated close-up angle as if taken casually with a front-facing phone camera. She is leaning back against the sofa with her upper body relaxed, one arm extending naturally toward the camera as if taking a candid selfie. Her expression is playful, soft, and effortlessly feminine, with a subtle open-mouth smile and her tongue slightly peeking out, creating a spontaneous and charming candid moment. She has long, silky dark hair, naturally voluminous with soft loose waves, subtle face-framing layers, and a slightly effortless texture. Her hair falls naturally over both shoulders and across her chest, with a few delicate strands framing her face. Her makeup is soft feminine and naturally glamorous: flawless luminous skin, softly flushed rosy cheeks, subtle warm pink blush, delicate taupe-brown eyeshadow, thin elegant black cat-eye eyeliner, naturally defined lashes, softly groomed brows, subtle rosy-nude lips with a glossy finish, and a healthy radiant complexion. Keep the makeup refined, fresh, youthful, and romantic rather than heavy. She wears an elegant cream-colored feminine top with delicate lace detailing, soft semi-sheer floral lace sleeves, a subtly romantic neckline, and refined pearl embellishments/details along the fabric. The cream tone should look warm, soft, and luxurious, complementing her skin tone and the pastel floral surroundings. The outfit should feel romantic, delicate, sophisticated, and effortlessly feminine. Her nails are neatly manicured, glossy natural nude-pink, medium length with a refined almond shape, adding to the polished feminine aesthetic. Behind her is an extravagant arrangement of enormous blush-pink and pale pink peonies, densely covering the upper background like a luxurious floral installation. The flowers have realistic layered petals in varying shades of soft pink, dusty blush, pale rose, and creamy white, creating an abundant romantic atmosphere. A sheer white curtain filters soft daylight in the background, with subtle hints of an elegant dining area visible behind the flowers. The overall atmosphere is ultra-feminine, romantic, soft, dreamy, luxurious, intimate, and effortlessly elegant, with natural indoor daylight, soft diffused highlights, realistic skin texture, delicate shadows, shallow depth of field, subtle photographic grain, authentic smartphone photography characteristics, and an editorial lifestyle feel. Photorealistic, highly detailed, natural skin texture, realistic hair strands, realistic lace and fabric texture, realistic flower petals, soft natural lighting, candid luxury lifestyle photography, feminine romantic aesthetic, vertical portrait, 9:16. Do not change the facial identity, facial structure, eye shape, nose, lips, skin tone, or natural proportions from the reference image. Do not make the face overly retouched, plastic, doll-like, or AI-looking.
Details
A photorealistic cinematic countryside portrait of a cute young adult woman sitting in a lush green  — AI image prompt — GPT Image 2
OpenAIGPT Image 2
A photorealistic cinematic countryside portrait of a cute young adult woman sitting in a lush green meadow at golden hour, with the same overall composition and atmosphere as the reference. She has natural freckles, soft youthful facial features, expressive green eyes, and long wavy auburn-red hair blowing gently in the wind. She wears a colorful vintage floral dress with a flowing skirt and delicate puff sleeves. She sits naturally in the tall grass while gently holding a fluffy white rabbit beside her. Keep the same meadow, rolling green hillside, blue sky, soft clouds, warm sunset lighting, camera perspective, natural shadows, rabbit placement, and peaceful mood. Preserve the nostalgic analog-film aesthetic with subtle film grain, realistic skin texture, detailed individual hairs, natural fabric texture, authentic grass, soft atmospheric depth, and warm golden highlights. Style: ultra-photorealistic, cinematic photography, natural beauty, authentic outdoor lighting, 35mm film look, shallow depth of field, subtle grain, realistic color grading, highly detailed, editorial countryside portrait, no artificial-looking skin, no CGI appearance. Negative prompt: child, teenager, cartoon, anime, plastic skin, excessive makeup, distorted face, extra fingers, malformed hands, duplicate rabbit, distorted anatomy, oversaturated colors, blurry face, artificial lighting, CGI, text, watermark.
Details
9:16 vertical format, real-life photography snapshot. An adult woman sits on an old wooden plank pat — AI image prompt — GPT Image 2
OpenAIGPT Image 2
9:16 vertical format, real-life photography snapshot. An adult woman sits on an old wooden plank path by a lotus pond in midsummer, her body slightly turned toward the camera as she leans down and reaches out to touch the water surface. Her long natural black hair is gently tousled by the summer breeze, her expression natural, as if the photographer captured a fleeting moment from very close range. She is wearing a complete, lightweight white summer outfit with white thigh-high stockings — the clothing is real and fully intact. The camera is positioned close to the subject at an extremely low angle, using a 24mm ultra-wide lens for close-range shooting, producing noticeable yet natural near-distance perspective. Giant lotus leaves, petals, and thick lotus stems intrude directly into the frame from in front of the lens, occupying a large portion of the image, extremely close to the camera and heavily out of focus, creating strong foreground obstruction. A huge pink lotus flower sits slightly above center frame, its petals just covering the key area of the subject's upper body. Lotus stems run vertically through the center of the frame, and foreground leaves drape down from the top — multiple natural elements together form a visual framing device and partial information occlusion. The woman's face emerges from between the lotus flowers and leaves, with only her clear eyes, face, and part of her hair visible. The rest of her body is naturally cut off by foreground foliage and the environment, creating a visual illusion of "seemingly missing, actually concealed." Her legs are positioned on the right side of the frame, with white thigh-high stockings clearly visible, forming a strong scale contrast with the foreground lotus flowers and leaves. Avoid deliberate posing — the movement is natural, and the body posture matches a real seated position. The background is a real summer rural lotus pond: vast green lotus leaves, blooming pink lotus flowers, shallow water reflections, an old wooden plank path, and low old rural houses and trees in the distance. The sunlight is strong but natural — harsh midday summer light, fine dappled shadows cast by lotus leaves, shimmering highlights on the water surface. The subject sits at the boundary between light and shadow, partially backlit, with genuine lens flare. Shallow depth of field: foreground lotus flowers and leaves are extremely blurred, the mid-ground subject is relatively sharp, and the background is softly and naturally blurred. Authentic snapshot quality from a phone or portable camera, natural skin texture, real hair detail, slight digital noise, delicate highlights, mild overexposure, real optical distortion, atmospheric depth, an unposed candid moment, strong spatial depth, overwhelming foreground pressure, modern East Asian summer photography aesthetics — clean and natural, high-end but not commercialized. Bottom-left corner signature "● DeepBlue," where ● is solid #0B3D91 deep blue, and DeepBlue is in white natural handwriting.
Details
Ultra-realistic cinematic vintage golden-hour portrait of the same woman sitting indoors beside an o — AI image prompt — GPT Image 2
OpenAIGPT Image 2
Ultra-realistic cinematic vintage golden-hour portrait of the same woman sitting indoors beside an old, weathered wooden door. Her dark brown hair is loosely tied into a messy high bun, with a few natural strands falling softly around her face and neck. She is shown in a graceful three-quarter side-profile view, looking gently toward the left with a calm, thoughtful expression. She wears a simple oversized ribbed brown/beige knit sweater with highly realistic woven fabric texture. Warm late-afternoon sunlight enters from the side, illuminating her face, hair, and sweater in rich golden tones while casting a clearly defined natural silhouette of her head and messy bun onto the old wooden door behind her. The environment features a rustic aged interior with cracked and peeling plaster walls, distressed wooden panels, subtle imperfections, and a small vintage framed picture on the wall. Moody nostalgic atmosphere, authentic natural skin texture, realistic pores, subtle film grain, warm earthy color palette, deep shadows, cinematic contrast, volumetric golden sunlight, shallow depth of field, soft natural bokeh, editorial portrait photography, 50mm lens, f/1.8, HDR, highly detailed, photorealistic, cinematic composition, 8K. Use the uploaded reference image as the strict identity and face reference. Preserve the woman's facial identity with 100% face accuracy. Her face must remain exactly recognizable as in the reference, including the same facial structure, proportions, eyes, eyebrows, nose, lips, cheeks, jawline, skin tone, natural skin texture, and distinctive facial details. Do not modify, beautify, reshape, age, de-age, or reinterpret her face. https://t.co/HcGTzKbwBQ face replacement, no facial redesign, no beauty filter, no skin smoothing, no altered facial proportions, no changed eyes, nose, lips, eyebrows, jawline, or cheek structure. Negative prompt: cartoon, anime, CGI, 3D render, plastic skin, beauty filter, over-smoothed face, altered identity, different person, face swap, facial reconstruction, changed facial proportions, excessive makeup, distorted face, asymmetrical eyes, deformed hands, extra fingers, unrealistic hair, oversaturated colors, harsh artificial lighting, blurry image, low resolution, watermark, text, logo.
Details
You are a fun photography action designer, turning unexpected situations from daily life into visual — AI image prompt — GPT Image 2
OpenAIGPT Image 2
You are a fun photography action designer, turning unexpected situations from daily life into visual, picture-worthy photo poses. Subject and photography: Vertical 9:16, adult East Asian female influencer, fair skin; minimalist photography style, direct CCD flash, Song dynasty aesthetics, calm and restrained. 【18 Action Cards】 1. Stomachache: clutching stomach, hands on hips, body curled up 2. Stepping on something sharp: one foot lifted, looking down at the sole of the shoe 3. A stone in the shoe: standing on one foot, taking off the shoe to check 4. Almost falling: body off balance, both hands reaching out, one foot suspended in the air 5. Someone behind: body leaning forward, suddenly turning head back 6. Spotting a bug: body stepping back, pointing at the ground 7. A strong gust of wind: pressing down on hair, body leaning, clothes and hair flying 8. Sudden downpour: covering head from rain, running in a flustered way 9. Stepping into a puddle: one foot stepping into the water, the other lifted, water splashing 10. Door won't push open: both hands pushing the door, body leaning forward, legs pushing hard 11. Object too heavy: hugging the heavy object, body sinking, stumbling 12. Object won't pull: gripping the object, body leaning back, feet braced against the ground 13. Phone falls into water: crouching down, both hands reaching toward the water surface, shocked 14. Phone dead: staring at the phone, scratching head, eyes wide open 15. Something dropped: suddenly turning back, crouching halfway to look for it 16. Caught in the act: movement freezing, slowly turning head back, feeling guilty 17. Socially mortified: covering face, body shrinking 18. Holding back laughter: covering mouth, head down, shoulders trembling 【Randomization】 Each set independently draws 1 different action card at random; no action card may be drawn more than once across the 3 sets. Each set independently pairs the action with random clothing, camera lens, real-life scene, environment, and one incidental factor. Avoid repetition across the 3 sets as much as possible — actions, clothing, camera lens, scenes, and incidental factors should all vary. Random elements serve the action. The composition should be clean, highlighting only one action and one visual focus. Avoid clutter, forced dramatization, and an AI-generated feel. The person's movement, proportions, and the relationship between hands, feet, and objects should follow real physical logic. 【Execution】 When the user specifies a number, generate that many sets. When not specified, generate 3 sets. Re-randomize every time a session starts. First generate the prompts only, without producing images. After the user selects a plan, generate only the corresponding image and keep that plan's content — do not re-randomize. 【Output】 【Fun Photo Shoot | Action Name】 Plan 1: Full image prompt Plan 2: Full image prompt Plan 3: Full image prompt Keep the signature 「● DeepBlue」 in the lower left corner of the image; ● is a solid dark blue circle in pure #0B3D91, and DeepBlue is in white natural handwriting style. Output only the generated result.
Details
Browse all GPT Image 2 promptsExplore AI Image Prompts