LogoAhaPrompt
  • 提示詞
  • 精選
  • 模型
  • AI 反推
  • 定價
  • 投稿
  • 部落格
AhaPrompt

圖片、影片、音訊 AI 提示詞庫

探索

  • 全部提示詞
  • 精選提示詞
  • 圖片提示詞
  • 影片提示詞
  • 音訊提示詞
  • AI 模型

工具

  • AI 反推工作臺
  • 圖片反推提示詞
  • 影片反推提示詞

資源

  • 定價方案
  • 投稿提示詞
  • 部落格

版權所有 © 2026 AhaPrompt 保留所有權利。

隱私政策條款與條件退款政策版權申訴 / DMCA
首頁AI 提示詞庫AI 圖片提示詞电影感混合莓果雪葩广告
电影感混合莓果雪葩广告 — AI image prompt — GPT Image 2 — Macro, Cinematic, Food

电影感混合莓果雪葩广告

OpenAIGPT Image 2OpenAIimage

制作一支10秒、9:16竖屏、电影感十足的高端自制混合浆果雪芭制作视频,分为4个无缝衔接的场景,每个场景2.5秒。采用超写实美食摄影、自然质感、浅景深、柔和自然光、微距特写、逼真的食物动态,以及清脆自然的厨房音效。画面中不出现人物、文字或标志。 场景1——0–2.5秒 | 冷冻浆果 微距电影感特写:透明玻璃碗中盛满新鲜冷冻的覆盆子、黑莓、蓝莓和草莓。浆果表面可见清晰的霜晶与冰霜质感。镜头缓慢推进,带有细微自然的动态,柔美的日光洒落,呈现高端美食广告美学。 场景2——2.5–5秒 | 搅打 透明搅拌机杯内特写冷冻混合浆果。金色蜂蜜缓缓淋在浆果上,随后挤入少许新鲜柠檬汁。食材开始搅打,融合成浓稠鲜艳的红紫色浆体。捕捉蜂蜜真实的黏稠度、浆果的质感、玻璃上的反光,以及自然的厨房声音。 场景3——5–7.5秒 | 冷冻 极近距离特写:浓稠的浆果浆体被顺畅地倒入浅口冷冻容器中。光泽细腻的雪芭浆体落地后自然折叠延展。刮刀轻轻抹平表面。呈现浓郁的树莓红色、逼真的奶油般冷冻质感,电影感微距对焦。 场景4——7.5–10秒 | 成品雪芭 惊艳的主角镜头:造型优美的碗中盛放着完美成形的鲜艳混合浆果雪芭球,周围点缀新鲜覆盆子、黑莓、蓝莓和草莓片。其中一球雪芭清晰对焦,可见冰晶奶油般的质感。镜头缓慢环绕,柔和高光,诱人的冷凝水珠,呈现优雅高端甜点广告的收尾效果。 视觉风格:超写实、电影感美食广告、微距镜头、浅景深、自然日光、真实质感、流畅运镜、浓郁浆果色泽、细腻胶片质感、4K细节、物理精确的食物动态。 音频:自然厨房环境声、浆果翻动声、蜂蜜淋落声、搅拌机运转声、轻柔倒浆与刮刀抹平声。无音乐、无旁白。 格式:9:16竖屏,10秒,4个场景,无缝转场,全程保持食材一致性与视觉风格统一。

詳細資訊
类型
AI 圖片提示詞
畫面比例
2:3
更新於
2026年9月9日
分類
MacroCinematicFood
Source

如何使用這條提示詞

  1. 1點選上方複製按鈕,複製完整提示詞。
  2. 2開啟 OpenAI 的 GPT Image 2,或任何風格相近的圖片生成工具。
  3. 3貼上提示詞,替換主體和風格關鍵詞,改成你想要的畫面。
  4. 4按示例參數(2:3 · Macro · Cinematic · Food)生成,再小步迭代——措辭的細微變化會顯著影響結果。

常見問題

這張圖片是用哪個 AI 模型生成的?

本圖由 OpenAI 的 GPT Image 2 生成,頁面上的提示詞就是生成它的原始文字。

這條提示詞用了哪些參數?

示例由 GPT Image 2 生成,參數:2:3 · Macro · Cinematic · Food。沿用這些參數可獲得最接近的效果。

怎樣才能生成相似的效果?

先原樣複製提示詞,只替換主體、保留風格/光影/構圖關鍵詞,多生成幾次——每次輸出都會有差異。

可以修改這條提示詞嗎?

當然可以。提示詞最適合作為起點——調整描述詞、寬高比或風格標籤,做出屬於你自己的作品。

更多 GPT Image 2 提示詞

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.
檢視詳情
日常快照风格,非精心构图或打光,校道长椅旁,条纹T恤配背带裙,小熊挂饰在背包上,易拉罐可口可乐在手;从道路指示牌后侧拍,牌边与树叶形成双层前景框景,轻微焦外;阴天自然光,低对比、低饱和,面料纹理与小饰 — AI image prompt — GPT Image 2
OpenAIGPT Image 2
日常快照风格,非精心构图或打光,校道长椅旁,条纹T恤配背带裙,小熊挂饰在背包上,易拉罐可口可乐在手;从道路指示牌后侧拍,牌边与树叶形成双层前景框景,轻微焦外;阴天自然光,低对比、低饱和,面料纹理与小饰物清晰,青春可爱。” “60mm,f/2.8,1/400s,ISO 200,WB 5400K;局部锐化仅饰物与眼周,肤色自然白皙,服装面料纹理可见,日系低饱和。略带运动模糊,整体平庸日常,甜美可爱风。
檢視詳情
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.
檢視詳情
Using the provided reference image, ultra-realistic luxury literary magazine cover featuring an eleg — AI image prompt — GPT Image 2
OpenAIGPT Image 2
Using the provided reference image, ultra-realistic luxury literary magazine cover featuring an elegant Korean woman in a rich burgundy velvet Victorian-style midi dress with puffed shoulders, ivory lace collar, pearl button detailing, and a cinched corseted waist. Long loose dark waves cascading over a worn leather-bound book held against her chest. Warm mocha skin, deep berry stained lip, kohl-rimmed eyes, feathery brows. Layered antique gold locket necklace, signet ring, velvet hair ribbon. Background: dusty candlelit library with towering bookshelves, warm amber shadows, soft candlelight glow. "NUMÉRO" in tall aged serif masthead with handwritten-style editorial subtext. 85mm lens, cinematic golden candlelight, ultra-detailed velvet pile texture, aged paper grain overlay, 8K photorealistic. Negative: bright colors, modern setting, cartoon, blurry, watermark, distorted anatomy. 1744x2336
檢視詳情
Use the uploaded food photograph as the primary reference and transform it into a vertical 3:4 edito — AI image prompt — GPT Image 2
OpenAIGPT 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.
檢視詳情
Create a premium, hyper-realistic cinematic travel editorial poster inspired by the uploaded referen — AI image prompt — GPT Image 2
OpenAIGPT Image 2
Create a premium, hyper-realistic cinematic travel editorial poster inspired by the uploaded reference image, but redesign everything into a completely original concept. Do not copy the original text, typography, composition, branding, or exact arrangement. Theme: Adventure is Where You Find Yourself Create a sophisticated vintage expedition / modern explorer aesthetic with a warm cinematic color palette of deep olive green, muted cream, burnt orange, dark brown, and subtle gold accents. Build the scene as a beautifully styled traveler’s desk photographed from directly above, featuring an aged topographic map, vintage passport, leather travel journal, handwritten postcards, old film camera, brass compass, folded hiking map, fountain pen, airplane ticket, small dried leaves, and several cinematic landscape photographs scattered naturally across the surface. In the center, create a strong editorial typography composition: WANDER WITHOUT A MAP Underneath, in elegant handwritten script: “Find the places that change you.” Add a small minimalist mountain-and-sun emblem between the typography elements. At the bottom, include: EXPLORE • DISCOVER • REMEMBER Use bold condensed modern sans-serif typography for the main headline combined with an elegant imperfect handwritten script for the secondary line. Make the typography feel like a premium outdoor lifestyle magazine rather than a generic travel poster. Add subtle realistic imperfections: paper texture, faded ink, worn leather, tiny scratches, natural shadows, slight dust particles, authentic film grain, soft vignette, and gentle warm sunlight entering from one side. Arrange every object with natural photographic depth and overlapping layers, avoiding a perfectly symmetrical layout. Include one partially visible passport, a boarding pass with subtle fictional details, and photographs showing mountains, a remote road, and a small cabin surrounded by pine trees. The final image should feel nostalgic, adventurous, cinematic, expensive, authentic, and editorial, like the cover of a high-end travel magazine. Ultra-photorealistic product photography, realistic materials, physically accurate shadows, cinematic lighting, detailed textures, sophisticated art direction, premium typography, subtle analog film look, 8K detail, sharp focus, no people, no logos, no existing brand names, completely original design.
檢視詳情
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.
檢視詳情
Generate independently for each photo.  {   "name": "Second World",   "version": "1.2",   "task": "U — AI image prompt — GPT Image 2
OpenAIGPT Image 2
Generate independently for each photo. { "name": "Second World", "version": "1.2", "task": "Using each uploaded photo as an independent source, generate one complete poster per photo. Do not merge multiple photos onto the same canvas.", "output": { "aspect_ratio": "3:4", "orientation": "vertical", "one_poster_per_photo": true, "layout": "Canvas horizontally divided at exactly 50% height, with upper and lower sections each occupying 50%, same width", "no_mockup": true }, "core_principle": "The Second World is already hidden in the photo. Let the same scene pass through the midline and continue downward, changing only the physical rules in the lower half. Continuity of the cross-boundary structure is the highest visual priority.", "upper_half": { "source": "The current uploaded photo", "preserve": [ "Subject identity and appearance", "Character poses, expressions, and actions", "Spatial relationships, proportions, and perspective", "Original color atmosphere", "Natural lighting and shadows", "Environment and important details" ], "allowed_change": "Only necessary proportional cropping to fit the upper half, avoiding cutting off key subjects or connection structures", "forbidden": [ "Redesigning the photo", "Redrawing or replacing the subject", "Rearranging characters and objects", "Changing the photo's colors", "Fictional lighting or background" ], "fidelity_rule": "Prioritize directly reusing the original photo; do not claim generative redrawing as lossless preservation of the original. If the tool cannot meet original preservation and precise layout, state the limitations—do not lower requirements and claim full compliance." }, "continuity": { "choose_one_source_structure": "Identify a structure from the original photo that can naturally extend to the midline, such as a road, shoreline, water surface, reflection, tree branch, light beam, architectural line, clothing flow, or body movement", "requirements": [ "The structure must continue into the lower half at the exact midline meeting point", "Maintain believable continuity in direction, position, scale, and occlusion relationships", "Establish a visible connection first, then develop the lower half's imagination", "Both halves must read as the same scene, not like two independent images stacked vertically" ], "transition_edge": { "optional": "Allow irregular torn paper edges", "rule": "Tearing must follow the original image's structure, not just as decoration, and avoid using the same tearing shape for every image", "interaction": "Source elements can touch, cling to, pass through, or cross over the torn edge" } }, "lower_half": { "background": "Warm ivory paper texture, with subtle visible fibers, rich negative space", "media": [ "Restrained photo fragments", "Simple cut-paper shapes", "Minimal black hand-drawn lines" ], "construction": "Extend downward from where the upper half's source structure meets the midline, then gradually reinterpret it as the Second World", "prohibited": "Do not turn it into an isolated entrance, window, stage, platform, or floating vignette, unless the form clearly grows continuously from the original photo", "density": "Bright, airy, restrained—avoid dense drawing or collage buildup" }, "second_world_logic": { "question": "If the structure in the photo could be touched, used, entered, folded, stretched, or changed, what would it naturally become?", "interaction_count": 1, "instruction": "Establish only one specific, clear, and interesting interaction per image, prioritizing possibilities discovered from the original image's shapes and actions, not reverse-engineering from fixed props or templates.", "examples_for_logic_only": [ "Water surface remains connected to the lake while being rolled up or stretched", "Road extends onto the paper, becoming a path that can be continued by drawing", "An existing light beam extends downward, becoming something gently graspable" ], "variation": "Judge each work individually—do not mechanically repeat actions, connection structures, compositions, or jokes. Examples are not required content." }, "tiny_figures": { "count": "0–3", "appearance": "Minimalist, tiny black line figures", "add_only_if": "Figures can engage in necessary and explicit physical interaction with the extending structure", "omit_if": "Source photo already contains strong human actions", "forbidden": "Using little figures as irrelevant decorations or adding crowds just for liveliness" }, "copy": { "language": "Primarily Chinese, paired with a short English accent", "main_text": "A short, witty, cute, humorous Chinese marginal note, or one with a slight surprising insight", "english": "Shorter, lighter English supplement; can complement the Chinese without word-for-word translation", "intent": "Make viewers smile knowingly after seeing the image and then the small text, or suddenly understand one more layer", "requirements": [ "Recreate based on this photo's specific interaction with the Second World", "Don't just name the action or mechanically describe the image", "Can include anthropomorphism, slight contrasts, deadpan little jokes, or gentle self-deprecation", "Can have a wake-up-call vibe, but no grand life lessons", "Don't force self-love, motivational, or emotional comfort templates", "Humor targets the situation, without belittling characters' appearance, identity, or circumstances" ], "avoid": [ "Vague inspirational fluff", "Grand maxims", "Preachiness", "Ad slogans", "Irrelevant internet memes", "Fixed 'same..., different..
檢視詳情
瀏覽全部 GPT Image 2 提示詞探索AI 圖片提示詞