GPT ImagesGPT Images

ChatGPT Images 2.5 提示词画廊

真实的 ChatGPT Images 2.5 提示词实例与生成效果——从电影感人像到产品主图、海报、游戏场景与图片编辑。每张卡片都可一键复制或直接生成。

Cinematic Minimal Portrait — GPT Image 2 prompt example文生图

极简电影感人像

portraitcinematicminimal

Generate a cinematic minimal portrait of a solitary man standing in an intense orange to red gradient environment, strong silhouette lighting, deep shadow contrast, reflective glossy floor, symmetrical composition, minimal

立即生成
Soft Airy 35mm Portrait — GPT Image 2 prompt example文生图

日系空气感 35mm 人像

35mmfilmjapanese

Analog 35mm film photography, soft airy Japanese-style aesthetic, gentle diffused natural window light, slight overexposure, pastel tones, low contrast, soft highlights, minimal indoor setting near a window with white curtains, clean light-colored wall, natural composition, eye-level, slightly closer full-body framing (mid-thigh to head), young East Asian woman, natural minimal makeup, soft realistic skin texture, long slightly messy dark hair, oversized white button-up shirt, light casual shorts, barefoot, simple and relaxed styling, standing naturally with relaxed posture, arms loosely at sides or slightly behind, facing camera, gentle soft smile, subtle stillness, focus on light, air, and quiet everyday mood, soft film grain, dreamy and understated atmosphere --ar 9:16

立即生成
Boston Spring 2026 City Poster — GPT Image 2 prompt example文生图

波士顿之春城市海报

postertypographycity

A striking Spring 2026 city poster for Boston with an elegant celebratory mood and a bold contemporary design. On a clean off-white textured background with large areas of negative space, a miniature single sculler rows across the lower right corner of the image on a narrow ribbon of reflective water. The wake from the oar sweeps upward in a dynamic calligraphic curve, gradually transforming into the Charles River and then into a dreamlike hand-painted panorama of Boston. Inside this flowing river-shaped composition are iconic Boston elements: the Back Bay skyline, Beacon Hill brownstones, Acorn Street, Boston Public Garden, Swan Boats, Zakim Bridge, Fenway-inspired details, historic brick architecture, harbor ferries, and the city’s waterfront atmosphere. Soft morning fog, golden spring light, subtle festive accents in crimson and gold, rich detail, layered depth, sophisticated city-poster aesthetics, fresh and refined, visually powerful but not overcrowded. Elegant typography in the lower left reads “SPRING 2026” with a vertical slogan “BOSTON, A CITY OF RIVER, MEMORY, AND INVENTION”, text clear and beautifully composed, premium graphic design, 9:16

立即生成
Vintage Amalfi Travel Poster — GPT Image 2 prompt example文生图

阿马尔菲复古旅行海报

retrotravelillustration

Modern pencil illustration of Vintage travel poster illustration of the Amalfi Coast, Italy, panoramic coastal cliff road scene, classic 1960s white car driving along a curved seaside road, deep blue Mediterranean sea with small sailboats, colorful pastel hillside village, bright blue sky with soft clouds, lemon tree branches with vibrant yellow lemons framing the foreground, warm summer sunlight, bold vibrant colors, retro 1950s travel poster style, cinematic composition, high detail, screen print texture, graphic illustration. Hand-drawn style, illustration with loose strokes and defined contours. High-contrast color palette, maintaining chromatic harmony between background and elements. Contemporary and decorative aesthetic.

立即生成
Chengdu Food Map Illustration — GPT Image 2 prompt example文生图

成都美食手绘地图

maphanddrawnfood

一张手绘风格的城市美食地图,以成都为主题。画面以鸟瞰视角的手绘简化城市地图为底,标注主要道路和地标但不追求精确比例而是追求可爱的手绘感。地图上分布着 12 个美食地点的精致手绘小插画:春熙路的串串香(一把竹签插着各种食材冒着热气)、宽窄巷子的三大炮(三个糯米团子飞向铜盘)、建设路的蛋烘糕(金黄酥脆正在翻面)、玉林路的火锅(九宫格锅翻滚冒泡)等,每个插画约占地图的 5% 面积,旁边用手写体标注店名和一句推荐语"凌晨两点还在排队的那家"。地图边缘用手绘藤蔓和辣椒装饰形成边框。右下角有一个手绘指南针和图例说明。左上角标题"成都·吃货暴走地图"使用胖圆的手绘美术字配辣椒装饰。整体画风为水彩+彩铅混合的手绘质感,颜色以暖色系(辣椒红、姜黄、翠绿)为主,图片比例 1:1。

立即生成
ICLR-Style Research Figure — GPT Image 2 prompt example文生图

ICLR 风论文配图

diagramacademicinfographic

Create a polished ICLR-style Figure 1 for an imaginary method called "Hierarchical Memory Routing for Long-Context Multimodal Reasoning (HMR)". The top band shows the failure mode of naive long-context multimodal processing: one overcrowded horizontal token stream mixing text, image patches, retrieved documents, tool traces, and audio snippets, with red-orange warning accents for interference, attention dilution, memory collision, and quadratic compute cost. A clean horizontal divider separates the main lower panel, which presents the HMR framework as a spacious modular loop. Center: a Reasoning Controller with stages Observe_t to Update_t. Left: a three-level Memory Hierarchy with working cache, episodic memory, and semantic knowledge base. Right: Multimodal Streams entering selectively through routing paths. Bottom right: sparse experts activated only when needed. White background, vector-clean styling, neutral gray plus cool accents, minimal but legible labels, conference-paper clarity, no poster aesthetics.

立即生成
Skincare Bottle on Travertine — GPT Image 2 prompt example文生图

洞石上的护肤品瓶

productskincareminimal

Minimalist commercial still life of a single cream-colored skincare pump bottle standing on a polished travertine stone surface. Soft warm window light from the upper left casts a clean elongated shadow to the right. Beige, ivory and putty palette with subtle vein texture in the stone. Sharp focus on the bottle label area, shallow depth of field, no text on the label, no logo, no watermark. Editorial e-commerce hero shot, square 1:1 composition, professional product photography, ultra detailed glass and ceramic textures.

立即生成
Floating Sneaker Hero Shot — GPT Image 2 prompt example文生图

悬浮运动鞋主图

sneakerecommercestudio

A single clean white-and-mint athletic sneaker floating slightly above a soft pink-to-lavender pastel gradient background, casting a small soft shadow directly beneath it. Studio split lighting with a subtle rim highlight on the upper edge of the shoe. Square 1:1 e-commerce hero composition, no laces flying, no logos, no text overlays, no watermark. Crisp product photography, photorealistic fabric and rubber textures, magazine cover quality.

立即生成
Sushi Platter Top-Down — GPT Image 2 prompt example文生图

俯拍寿司拼盘

foodtopdownrestaurant

Overhead top-down photograph of a black slate platter holding eight neatly arranged pieces of nigiri sushi and a small mound of pink ginger and wasabi, with two dark wooden chopsticks resting at a slight diagonal beside the platter. Surface is dark stained oak with subtle grain. Warm tungsten studio light from a single soft box above-left. Square 1:1 framing with generous negative space around the platter. No text, no watermark, no chef hand visible. Premium food photography, sharp focus, glossy rice grains, soy condensation droplets.

立即生成
Espresso Cup on Marble — GPT Image 2 prompt example文生图

大理石上的浓缩咖啡

coffeecafegolden-hour

Close-up of a single small white porcelain espresso cup filled with crema-topped espresso, resting on a polished white Carrara marble countertop. A small cluster of roasted dark coffee beans is scattered to the left of the cup. Soft golden hour window light enters from the right, producing a single specular highlight on the cup rim and gentle warm tones across the marble. Square 1:1 composition, no text, no logo, no watermark. Editorial cafe brand photography, ultra detailed crema bubbles and bean textures.

立即生成
Perfume Bottle in Light Shafts — GPT Image 2 prompt example文生图

光柱中的香水瓶

perfumeluxurylighting

A faceted rectangular glass perfume bottle filled with pale amber liquid, standing on a dark matte surface against a pure black background. Three crisp cubic shafts of warm white light cut diagonally across the bottle, producing hard-edge reflections on the glass facets and sharp highlights on the gold metal cap. No label, no brand text, no watermark. Square 1:1 hero composition, luxury product photography, photorealistic glass refractions, ultra detailed.

立即生成
Black Friday Sale Banner — GPT Image 2 prompt example文生图

黑五促销横幅

bannertypographysale

Horizontal banner advertisement design, 16:9. Left half shows a giant percentage figure "70%" in heavy bold black typography on a vibrant orange background, with the smaller word "OFF" stacked underneath. Right half is a deep matte black background featuring a single floating over-ear headphone product silhouette with subtle rim lighting. A thin yellow horizontal divider runs across the middle. Bottom right shows a small clean white CTA button reading "Shop Now". No brand logo, no real brand name, no watermark. Crisp e-commerce promotional ad design, photorealistic product, sharp typography.

立即生成
Mecha Girl Key Visual — GPT Image 2 prompt example文生图

机甲少女主视觉

animemechakeyvisual

A mecha girl mid-teens, pale skin smudged with soot and salt spray, sharp amber eyes with glowing HUD reticles, waist-length ash-white hair tied in a high ponytail whipping in the sea wind, matte gunmetal exoskeleton armor plating her shoulders, forearms and shins, exposed hydraulic pistons at the joints, chest rig with glowing cyan coolant lines, oversized oil-stained hangar jacket half slipping off one shoulder, a massive rail cannon resting on her right shoulder, dog tags and frayed red ribbon at her collar , standing off-center to the left on the rusted edge of a tilted steel platform jutting out over dark water, weight shifted onto one leg, left hand gripping the cannon strap, head turned slightly toward camera with a quiet defiant stare, steam venting from her back thrusters, her ponytail and jacket streaming sideways in the salt wind , a vast derelict sea-city at dusk, colossal megastructures of unknown purpose rising from the ocean in staggered silhouettes, bone-white monolithic towers fused with barnacled steel, cyclopean ring-shaped constructs canted at broken angles, rusted skeletal gantries threaded with dead cables, dark swells rolling between the pylons, shipwrecks half-swallowed at their feet, thick sea fog clinging to the bases while the upper structures pierce into a bruised sky, scattered faint lights blinking high in the towers like distant eyes , moody low-key lighting, cold teal ambient from the overcast sky, warm amber sodium glow leaking from a distant structure camera-right, hard backlight from a low sun behind the towers carving her silhouette, volumetric god rays cutting through sea mist, wet specular highlights on her armor , 35mm anamorphic lens, slight low angle looking up past her shoulder toward the structures, medium-wide shot, shallow depth of field with foreground rust in soft focus, horizontal lens flares, fine atmospheric haze compressing the distant megastructures into layered silhouettes , cinematic anime key visual, painterly digital illustration with crisp line art, desaturated oceanic palette of teal, bone-white and rust punched by small warm accent lights, film grain, high-contrast editorial poster aesthetic . Format 16:9.

立即生成
Isometric Pixel RPG Village — GPT Image 2 prompt example文生图

像素风日式村庄 RPG

pixelartgameisometric

Create an isometric pixel-art RPG screenshot of a traditional Japanese village during cherry blossom season. Sakura petals drift through the air, a samurai player character practices sword moves in the square, villagers watch nearby, and the interface includes an inventory panel, stamina gauge, skill cooldown timers, and subtle quest UI. Cozy retro console feeling, soft ambient pastel lighting, crisp pixel details, 16:9 gameplay composition.

立即生成
Cyberpunk Game HUD — GPT Image 2 prompt example文生图

赛博朋克游戏 HUD

cyberpunkgamehud

Create a third-person cyberpunk action game screenshot set in a neon-soaked European capital at night. The protagonist has glowing cybernetic implants and stands on rain-slick streets near a famous landmark while holograms, drones, and flying traffic crowd the skyline. Add a polished game HUD with health bar, ammo count, radar, stealth/energy meters, and mission overlays. Vivid cyan-magenta palette, wet reflections, cinematic intensity, 16:9.

立即生成
Low-Poly Samurai Strategy Village — GPT Image 2 prompt example文生图

低多边形武士村庄

lowpolyrtsgame

Create an isometric low-poly strategy game screenshot of a mountainous Japanese village with rice terraces, torii gates, samurai and archer units in formation, and a tactical RTS interface. Include unit selection boxes, resource counters for rice and wood, fog-of-war minimap, command overlays, and warm daylight with soft shadows. Stylized but readable, modern indie strategy game key art, 16:9.

立即生成
Photo → Anime Snapshot — GPT Image 2 prompt example图生图

照片转动漫剧照

animestyle-transferedit

Show me the attached image as a snapshot from an actual anime

立即生成
Character Reference Card — GPT Image 2 prompt example图生图

角色官方设定资料卡

character-sheetanimeedit

基于此角色和背景,请制作一份类似官方设定资料的角色资料卡。 ・包含三视图:正面、侧面和背面 ・添加角色面部表情的变化・分解并展示服装和装备的详细部分 ・添加色板・包含世界观设定的简要说明 ・总体上,使用有组织的布局(白色背景,插画风格)高分辨率、专业概念艺术风格

立即生成
Birdwatching Guide Infographic — Seedream 5.0 Pro prompt example文生图

观鸟入门信息图

infographicbirdsgrid

Generate a beginner birdwatching guide infographic with a fresh color palette and grid layout, showcasing 8 common bird species with scientific illustrations, Chinese and English names, and identification features.

立即生成
Ultra-Realistic Selfie — Seedream 5.0 Pro prompt example文生图

超写实自拍人像

selfieportraitrealistic

Ultra-realistic smartphone selfie of a beautiful young Japanese woman with smooth porcelain skin, soft natural facial features, large warm brown eyes, glossy pink lips, and long silky black hair styled in low twin ponytails with wispy bangs.

立即生成
Woman in a Bustling Crowd — Seedream 5.0 Pro prompt example文生图

人群中的女子

crowdmotionstreet

A woman walking calmly in the middle of a bustling crowd, with everyone else in motion and slightly blurred. She is looking to the side and slightly upward, with a calm, neutral expression and perhaps a very faint, subtle smile. The scene takes place on a city street.

立即生成

来源: HiAPIAI/awesome-gpt-image-2-prompts (GPT Image 2) & AtlasCloudAI/awesome-seedream-5-pro-prompts (Seedream 5.0 Pro) — both CC-BY-4.0; card images are the actual outputs from those galleries

如何写出有效的 ChatGPT Images 2.5 提示词

以上每张卡片背后的五个习惯:

  1. 1

    先说主体,再定风格或媒介(35mm 胶片、丝网印刷海报、像素游戏截图)。

  2. 2

    锁定光线与氛围——窗边自然光、钨丝柔光箱、霓虹雨夜——光线决定画面气质。

  3. 3

    明确构图:俯拍、1:1 主图取景、第三人称 HUD 视角、留白位置。

  4. 4

    列出不要的东西:no text、no logo、no watermark——排除项让结果更干净。

  5. 5

    编辑图片时附上参考图,并说清楚什么不许变——身份、构图、光线。