Loading...
精选可直接复制的提示词，覆盖 Midjourney、Stable Diffusion、FLUX、Sora、Runway、Kling，配合写实/插画/动漫/电影感/产品/概念多种风格。
Portrait of a young woman with windblown hair, soft natural light coming from a window on her left, shallow depth of field f/1.8, 85mm lens, slight rim light, warm color grading, freckles visible, photographed on a Canon R5, magazine-quality skin retouch, ultra-detailed eyes
blurry, oversharpened, plastic skin, distorted face, low resolution
推荐模型： Midjourney v7, Stable Diffusion XL, FLUX.1
指明相机型号、焦段、光圈。摄影元数据训练过的模型对这些参数响应强烈。
A cozy fairytale village built into the side of a mossy hill, hand-painted in the style of a 1960s Polish childrens book, warm autumn palette of ochre and burnt orange, soft watercolor textures with visible brushstrokes, lanterns glowing in the windows, a winding cobblestone path, a black cat watching from a window, no text
photo realistic, harsh lines, digital art, text, signature
推荐模型： Midjourney, NovelAI
引用某地区+某年代的插画传统，能让风格更统一。
Anime style, two highschool girls leaning on a chainlink rooftop fence, late afternoon golden hour, distant city haze, cherry blossom petals drifting through frame, Makoto Shinkai inspired lighting, ultra-detailed background, soft cel-shading, 4k
3d render, photo, distorted hands, extra fingers
推荐模型： NovelAI, AnythingV5, SDXL anime checkpoints
点名导演（新海诚、宫崎骏、汤浅政明）比单写"动漫风格"效果好得多。
Studio product render of a minimalist white ceramic coffee mug, floating against a soft gradient background fading from teal to off-white, dramatic side lighting casting a soft long shadow, subtle reflections, octane render quality, ultra clean, 8k
cluttered background, hand, person, text, logo, watermark
推荐模型： Midjourney, FLUX.1, Imagen 3
"studio product render" + 光线方向是关键。加上 octane/cinema4d 等渲染器名让画面更精致。
Concept art of a tiny noodle stall in a cyberpunk Tokyo alley, neon kanji reflecting on wet asphalt, steam billowing from the pot, a lone customer in a translucent rain jacket, color palette dominated by magenta and cyan with deep shadow areas, painterly digital art, Beeple meets Syd Mead, ultra-detailed
推荐模型： Midjourney, FLUX.1
用 "X meets Y" 组合两个艺术家风格融合。
Overhead flat lay food photography of a rustic ramen bowl with soft-boiled egg, scallions, nori, and chashu, on a dark wooden table with chopsticks, small bowl of chili oil, golden side lighting, professional food magazine style, shallow depth of field on the bowl, 50mm lens, natural shadow
unappetizing, soggy, dim, blurry, distorted text
推荐模型： Midjourney v7, SDXL, FLUX.1
"Flat lay 俯拍" + 黄金光是出片率最稳的美食组合。
A perfectly organized top-down knolling flat-lay of a vintage 35mm film camera completely disassembled, every screw, gear, spring, lens element and circuit board spaced on a precise grid and aligned to invisible guidelines, arranged by size on a matte charcoal surface, soft even overhead softbox lighting with crisp micro-shadows, hyper-realistic macro product photography, razor-sharp focus across the whole frame, subtle reflections, 4K detail, organized chaos turned into satisfying order.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
把任意复杂物件拆成零件做整齐排布,适合科普/拆解类封面。
A moody black-and-white photograph showing the blurred silhouette of a person pressing one hand flat against frosted shower glass, only the hand and fingertips in sharp contact-focus while the body dissolves into soft grey gradients behind the textured pane, single cold window light from the left, heavy film grain, high contrast, minimalist negative space, shot on medium format, fine-art editorial mood, mysterious and quiet.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
情绪化人像封面,把主体藏在材质后面制造悬念。
A tilt-shift miniature-effect photograph of a dense downtown intersection shot from a high rooftop at golden hour, tiny toy-like cars and pedestrians, exaggerated shallow depth of field with only a thin band of crosswalk in focus and everything else melting into creamy blur, oversaturated candy colors, warm raking sunlight casting long miniature shadows, hyper-real but doll-house surreal, 3:2 aspect.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
移轴让真实街景变成玩具世界,城市内容必用。
A high-end commercial photograph of a glass perfume bottle floating mid-air just above a still black water surface, surrounded by fresh white peonies and a single drifting petal, perfect mirror reflection in the water below, dramatic single spotlight from above creating a glossy highlight on the cap, fine mist suspended in the air, deep shadows, ultra-clean luxury advertising aesthetic, razor-sharp macro detail, hero shot composition.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
香水/护肤品高级广告主图,换产品即可复用。
A photorealistic cinematic scene rendering the exact mood of the GPS coordinate 35.6586 N 139.7454 E at 19:00, a rain-slicked Tokyo crossing glowing under neon signage, wet asphalt reflecting red and cyan light, blurred umbrellas in motion, distant tower lights bokeh, shot on 35mm with subtle grain and chromatic aberration, atmospheric haze, evening blue hour color grade, documentary realism, 16:9.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
把经纬度+时间渲染成真实街景,旅行/地理内容很吸睛。
A surreal hyper-real macro editorial photograph of a miniature chrome clothes iron, held by a tiny pair of hands, gliding across the corner of a human eye and visibly smoothing the fine wrinkles into glassy flawless skin behind it, steam rising in soft wisps, extreme close-up with shallow depth of field, beauty-campaign lighting, pristine retouched skin texture, witty anti-aging concept, ultra-sharp, 1:1.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
护肤/抗衰广告的超现实视觉梗,概念一目了然。
A high-angle surveillance-camera still of a busy train-station concourse, slight fisheye distortion and low-fidelity CCTV color, crisp white bounding boxes auto-tracking multiple faces in the crowd with small ID numbers and confidence percentages floating beside them, one enlarged zoom-in inset of a single face in the top corner, timestamp and camera label burned into the frame, gritty realistic security-footage aesthetic.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
科技/AI 监控题材封面,有强烈纪实+未来感。
A photorealistic orange tabby cat sitting on a sofa holding a tablet in its paws, and on the tablet screen is the exact same cat holding the same tablet showing the same scene, repeating into infinity in a perfect Droste recursion that spirals smaller toward the center, soft living-room window light, sharp fur detail, slightly absurd and uncanny, mind-bending infinite-loop composition, 1:1.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
无限递归视觉容易病毒传播,宠物题材尤佳。
A glossy 3D-rendered mascot where a bottle of orange juice has been given big cartoon eyes, stubby waving arms and little sneakers, posed mid-jump with a cheerful grin and a juice-splash cape behind it, studio gradient background in matching citrus tones, soft three-point product lighting, subsurface plastic-toy sheen, blind-box collectible aesthetic, clean commercial composition, ultra-crisp render.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
把任意产品拟人成吉祥物,品牌营销超吸睛。
A photorealistic packaging mockup of a bold modern cereal box standing on a clean white studio pedestal, bright flat-color brand design with a friendly mascot and chunky display typography on the front panel, three-quarter angle showing front and side panels, soft shadow beneath, even softbox lighting, subtle cardboard texture and matte finish, e-commerce hero render, crisp readable label, 4:5.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
快消品包装提案样机,换图案即出多版本。
A hyper-real product hero shot of a running sneaker entirely constructed from living green moss, ferns and tiny wildflowers, the laces formed of braided vines and the sole of cross-sectioned bark, floating on a clean misty forest-green gradient backdrop, dewdrops catching soft daylight, studio macro detail with crisp focus on the texture, sustainability campaign aesthetic, made of nature concept.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
X 用 Y 材质做的爆款套路,环保/材质故事都能用。
A dramatic dark-studio advertising photograph of a stainless-steel chronograph watch shot from a low three-quarter hero angle, motorsport aesthetic with carbon-fiber and brushed-metal accents, a single hard rim light raking across the bezel and crisp specular highlights on the crown, deep black background, faint red tachymeter glow, precision macro detail on the dial, luxury campaign mood, room for clean typography.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
高端腕表/数码广告主图,暗调高级。
A high-resolution 3D render of a single emoji reimagined as a glossy inflatable puffy balloon object, plump rounded volumes with taut vinyl seams and stitched edges, bright candy color with soft latex sheen and realistic air-pressure highlights, floating and casting a soft drop shadow on a pure white background, playful toy-product aesthetic, studio lighting, ultra-clean, centered.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
充气膨胀质感图标,贴纸/UI 资产都好用。
A hyper-realistic isometric 3D render of a tiny complete computer workstation built inside the hollow of a single transparent ESC keycap, miniature desk, glowing monitor, swivel chair and a sleeping cat the size of a grain of rice, warm desk-lamp glow spilling from within, the keycap resting among full-size keyboard keys for scale, macro depth of field, satisfying micro-world detail.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
微缩世界藏在日常物件里,极易引发好奇。
A studio product render of a flagship smartphone split down a hard vertical centerline: the left half is a photorealistic finished device with glossy glass and reflections, the right half is an exploded technical wireframe showing glowing blue circuit traces, internal components and labeled callout lines, seamless hard-cut boundary between the two worlds, dark gradient background, dramatic edge lighting, high-tech reveal aesthetic.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
左实拍右线框,科技产品发布会风,直观展示内部。
A close-up photograph of a hand holding a sleek matte-black business card designed to look exactly like a formatted JSON file, with syntax-highlighted key-value pairs spelling out the persons name, title and contact info in monospace code font, subtle embossed bracket logo in a corner, soft directional light raking across the card to reveal spot-UV texture, shallow depth of field, clean tech-minimal aesthetic, 3:2.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
程序员名片创意,开发者社群传播力强。
A cute 3D isometric miniature diorama of an entire country shaped as a tiny floating tabletop model, its most iconic landmarks rendered as chubby low-poly buildings dotted across rolling green terrain, soft clay-toy materials with rounded edges, tiny trees, rivers and cars, gentle ambient occlusion and warm soft lighting, blind-box collectible aesthetic, clean pastel background, Cinema 4D render, charming and orderly.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
国家/城市地标做成等距微缩,地理科普神器。
A clean 3D cartoon infographic showing a citys five tallest skyscrapers lined up side by side in correct relative height order, each rendered as a stylized rounded model with soft pastel materials and a small floating label noting its name, height in meters and year built, neutral light-grey studio backdrop, gentle top-down soft shadows, isometric-leaning perspective, friendly educational data-visualization aesthetic, crisp and tidy.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
高度对比信息图,建筑/数据内容直观又好看。
A charming voxel 3D icon of a tiny camera built entirely from crisp cubic blocks like a Minecraft-style model, bright saturated palette with clean stepped edges, soft three-quarter isometric angle, gentle studio lighting with subtle ambient occlusion between the cubes, floating on a soft pastel gradient background with a small drop shadow, playful collectible app-icon aesthetic, centered, ultra-clean render.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
体素图标统一一套,游戏/工具品牌资产。
A handmade claymation stop-motion scene of a cozy breakfast table, every element sculpted from soft plasticine with visible thumbprints and tool marks: a wobbly fried egg, lumpy toast, a smiling clay coffee mug with steam curls, slightly imperfect charming proportions, warm tabletop lighting with soft shadows, shallow miniature-set depth of field, tactile handcrafted Aardman-style aesthetic, cheerful pastel palette.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
黏土定格质感温暖讨喜,美食/生活内容可用。
A 3D chibi-style miniature concept store rendered like a blind-box collectible, a whimsical oversized coffee-shop building with exaggerated rounded architecture, a giant cup-shaped roof, tiny glowing windows and a cute awning, soft matte plastic toy materials, warm interior glow, gentle ambient occlusion, displayed on a clean circular podium with a soft pastel backdrop, Cinema 4D render, adorable and pristine.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
品牌门店做成盲盒微缩店,潮玩营销风。
A 3D isometric cutaway render of a cozy multi-floor house with the front wall removed to reveal every furnished room at once, a kitchen, a plant-filled living room, a tiny bedroom and an attic studio, warm individual lighting glowing in each room, soft clay-like materials with rounded furniture, gentle ambient occlusion, miniature dollhouse charm, neutral background, crisp detailed render, 4:5.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
剖面展示多个房间,室内/生活内容信息量大。
A hyper-detailed 3D macro render of a single suspended water droplet, and refracted upside-down inside it is an entire tiny mountain landscape with pine forests, a winding river and a misty sunrise, the droplet clinging to the tip of a green leaf, dewy surroundings softly blurred, crisp caustics and refraction, dreamy magical-realism, studio macro lighting, ultra-sharp focus on the drop, 1:1.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
水滴折射出微缩世界,治愈系超现实视觉。
A professional character-design reference sheet on a light neutral backdrop, one stylized adventurer character shown in front, side and back full-body turnaround poses lined up across the sheet, plus an expression row of four head close-ups, small callout swatches for the color palette and a prop detail of their satchel, clean line art with flat cel shading, labeled annotations, concept-art studio presentation, balanced grid layout.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
角色设定表三视图+表情,游戏/动画立项必备。
A digital collectible character card in glossy RPG trading-card style, a programmer hero illustrated in a heroic pose at the center holding a glowing laptop like an artifact, an ornate frame with stat bars for Caffeine, Focus and Debug, a class banner, a rarity gem in the corner and a holographic foil sheen across the card, rich painterly fantasy illustration, dramatic rim lighting, vertical card layout.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
把任意职业/人物做成游戏卡牌,趣味个人 IP。
A digital illustration of a hummingbird portrayed as a network of glowing clean cyan lines and luminous nodes mapping its anatomy against a deep navy background, delicate circuit-like internal structure visible through a translucent body, thin elegant labeled callout lines pointing to key parts, subtle particle glow, futuristic scientific-diagram aesthetic, crisp vector precision, balanced negative space.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
发光线框解剖,科普/科技感图解都适用。
A striking minimalist poster: the clean black silhouette of a leaping deer filled with a dense intricate scene of a forest, mountains and a rising sun visible inside the outline, set against a flat bright-yellow background, bold sans-serif title text along the bottom edge, high-contrast negative-space composition, screen-print vector aesthetic, balanced and graphic, gallery-print quality.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
剪影里藏场景,极简海报视觉冲击强。
A vertical childlike crayon-style travel-journal illustration on textured cream paper, a winding hand-drawn dotted route looping past wobbly landmarks, little local-food doodles, smiling sun and clouds, scribbled labels in crayon handwriting, bright waxy primary colors with visible crayon strokes and uneven coloring, charming naive innocence, scrapbook layout, warm and playful, 9:16.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
蜡笔手账风行程图,旅行内容亲切讨喜。
A serene daytime photograph-style illustration of a vast blue sky where scattered white clouds have naturally arranged themselves into the unmistakable shape of a galloping horse, soft fluffy cumulus volumes with believable wispy edges, gentle sunlight rimming the cloud forms, a small bird for scale, dreamy minimal composition with lots of open sky, calm uplifting mood, 16:9.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
云朵拼成任意形状,治愈/文案配图百搭。
A technical engineering blueprint of a mechanical dragon drafted in white line-work on classic cyan blueprint paper, orthographic side, top and front schematic views with dimension lines, gear and joint detail callouts, exploded wing-mechanism inset, handwritten engineer annotations and a title block in the corner, faint grid, aged paper texture, precise drafting aesthetic, 16:9.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
把幻想生物画成工程蓝图,设定/科幻感拉满。
A surreal trans-dimensional composite where a real hand tips a glass and a stream of glowing blue liquid pours out of the physical world and splashes through the surface of a laptop screen, rippling into the digital scene displayed inside, the boundary between real desk and on-screen world dissolving with droplets crossing dimensions, dramatic side lighting, hyper-real textures with magical glow, mind-bending concept art.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
打破物理/数字边界的超现实概念,科技叙事吸睛。
A clean Google-style emoji-design mashup fusing a banana and sunglasses into one cohesive new emoji, smooth glossy vector shading, friendly rounded forms, the cool banana wearing the shades at a jaunty angle with a confident smirk, soft inner highlights and a subtle cast shadow, centered on a pure white background, crisp icon-design aesthetic, balanced and instantly readable.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
两个 emoji 融合成新表情,趣味贴纸/品牌彩蛋。
A polished McKinsey-style Sankey flow diagram visualizing a companys income statement, smooth flowing colored ribbons branching from a single revenue source on the left into costs, taxes and net profit on the right, each band proportional to its value with clean labels and dollar figures, flat corporate brand-color palette, generous white space, crisp grid alignment, professional infographic aesthetic, 16:9.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
资金/数据流向用桑基图,商业汇报高级清晰。
A realistic close-up of an open passport page stamped with a fresh circular entry stamp for a named city, slightly smudged ink at a casual angle, embossed security guilloche patterns, faint watermark, the page edge and binding visible, soft natural window light raking across the paper grain and revealing texture, shallow depth of field, authentic travel-document detail, warm nostalgic tone.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
护照盖章页,旅行打卡/目的地内容代入感强。
A handcrafted multi-layer papercut diorama of a misty mountain valley, five to seven stacked sheets of colored paper receding into depth, each layer a cleanly cut silhouette of ridgelines, pine trees and a rising sun, soft cast shadows between layers giving real dimensional depth, warm-to-cool gradient palette from front to back, gentle directional light, tactile lightbox craft aesthetic, 16:9.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
分层纸雕营造纵深,封面/装饰图精致。
A single sheet arranged as a clean 3x3 grid of nine cinematic storyboard frames telling a wordless coffee-brand TVC: a sunrise window, a hand grinding beans, steam rising, a slow pour, a satisfied first sip, all in consistent warm filmic color grading and shallow depth of field, thin black panel borders with tiny shot-number labels, moody golden cinematography, vertical-friendly framing, continuity across panels.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
一张图给出整支广告分镜,提案/短视频脚本可视化。
A 1940s film-noir black-and-white movie still, landscape 16:9, high contrast, a trench-coated detective half-lit by venetian-blind shadows in a smoky office, a single hard key light carving deep blacks and bright highlights, curling cigarette smoke catching the beam, rain streaking the window behind, shot on 35mm with visible grain, dramatic chiaroscuro, tense mysterious mood, classic Hollywood composition.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
黑色电影质感剧照,悬疑/复古内容氛围满分。
A horizontal strip of four cinematic keyframes expanding one establishing shot into a continuous camera move: a lone astronaut walking toward a glowing alien monolith across a red desert, each frame pushing closer with consistent lighting, lens flare and dust, unified teal-and-orange color grade, anamorphic widescreen framing, filmic grain, dramatic sci-fi atmosphere, smooth narrative continuity between panels.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
把一个镜头扩成连贯关键帧,视频分镜/概念片用。
A cinematic street photograph at golden hour just after rain in a bustling old-town market, warm low sun breaking through to backlight rising steam and rain mist, wet cobblestones mirroring glowing shopfront lights, a vendor framed in soft bokeh of passing crowds, rich teal-and-amber grade, shallow depth of field, 35mm filmic grain, atmospheric depth, emotional documentary mood, 16:9.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
雨后黄金时刻街拍,旅行/人文封面氛围强。
A photorealistic capture of a green classroom chalkboard on which a single anime character has been drawn entirely in colored chalk, confident chalky linework with soft dusty smudges and visible chalk texture, the character mid-action with flowing hair, faint eraser ghosting around the edges, an empty classroom with soft afternoon window light grazing the board, slightly out-of-focus desks in foreground, charming hand-made feel.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
黑板粉笔动漫,校园/二次元内容反差萌。
A hyper-realistic anime-style portrait of a young swordswoman lit by a single sharp-edged narrow spotlight from above, a tight beam carving her face out of near-total darkness with deep dramatic shadows and a thin rim of light along her hair and blade, dust motes drifting in the beam, cinematic high-contrast lighting, glossy detailed eyes, moody mysterious atmosphere, semi-realistic rendering, 4:5.
推荐模型： gpt-image-2, FLUX.1, Nano Banana Pro
单光束戏剧打光的写实系动漫像,头像/封面高级。
Cinematic aerial drone shot, slow flythrough over snow-covered mountain peaks at sunrise, golden light kissing the ridges, soft mist drifting between valleys, dramatic camera push-in, anamorphic lens flare, 24fps, IMAX scale, 5 seconds, smooth motion
推荐模型： Sora, Runway Gen-3 Alpha, Veo
对 Sora/Runway，明确写镜头运动（推进、平移、环绕）。模糊的镜头描述会出抖动画面。
Studio product video, white minimalist sneaker rotating slowly 360 degrees on a glossy black turntable, soft top-down key light with subtle rim, gradient grey backdrop, shallow depth of field, 5 seconds, perfectly smooth rotation, no human in frame
推荐模型： Runway Gen-3 Alpha, Pika 1.5, Kling
告诉模型主体只旋转不移动位置，否则容易漂移。
Handheld vlog shot inside a cozy small cafe, late morning warm light through window, slight camera shake, racking focus from latte art on table to barista in background, ambient bokeh, 5 seconds, natural color grading, real-world physics
推荐模型： Runway Gen-3, Pika, Sora
"racking focus" + "handheld" + "ambient bokeh" 组合出纪录片感。
Anime style 2D animation, a teenage girl in a yellow raincoat walking through a Tokyo street at night, raindrops, puddle reflections of neon signs, gentle camera tracking sideways, Makoto Shinkai inspired lighting, 5 seconds, hand-drawn feel, no morphing characters
推荐模型： Sora, Kling, Hailuo (MiniMax)
加 "no morphing characters" 抑制人脸变形——这是当前视频模型最常见的瑕疵。
Cinematic underwater shot, slow forward dolly toward the ruins of an ancient submerged city, beams of sunlight cutting through clear blue water, schools of fish swimming past, particles drifting, mysterious atmospheric score implied, 6 seconds, IMAX scale, smooth tracking
推荐模型： Sora, Veo, Runway Gen-3
水下场景明确写 particles 与 light beams，能出标志性的水下质感。
Editorial fashion photograph of a young Asian model in oversized streetwear, standing in a brutalist concrete underpass in Tokyo, shot on Hasselblad medium format, soft overcast daylight, slightly desaturated film grain, full body composition, magazine layout sensibility
studio backdrop, smiling, beauty filter, plastic skin, low resolution
推荐模型： Midjourney v7, FLUX.1
点名真实相机（Hasselblad / Leica）比写 "professional" 效果稳定得多。
Wide-angle landscape photograph of black volcanic sand beach with basalt sea stacks rising from crashing North Atlantic waves, low storm clouds, golden hour light breaking through, long exposure smoothing the water, shot on Sony A7R V with 16-35mm lens, 4 stop ND filter, ultra-detailed foreground texture
people, distorted horizon, oversaturated, HDR halos, blurry
推荐模型： Midjourney v7, FLUX.1, Imagen 3
长曝光术语（ND filter / smoothed water）摄影元数据训练过的模型能识别。
3D character design of a friendly round-bellied raccoon mascot for a tech brand, soft pastel color palette, large expressive eyes, holding a tiny coffee cup, isometric pose, soft global illumination, Octane render, no background, neutral white floor with soft shadow
cartoon style, flat shading, sharp angles, distorted proportions
推荐模型： Midjourney, FLUX.1
品牌吉祥物要写 "neutral background"，否则模型会自作主张加奇怪背景。
Isometric illustration of a small tech city — server racks, satellite dishes, a tiny coffee shop, fiber cables glowing between buildings, cyan and magenta accent lighting against a deep navy background, flat-shaded with subtle gradients, similar in spirit to Antonio Uve and Studio MUTI
推荐模型： Midjourney, FLUX.1
等距 + 平面着色 + 具体配色 = SaaS 引导页那种插画风。
Cyberpunk anime portrait of a young woman with neon pink hair, wearing a high-collar tactical jacket with subtle LED trim, rain-slick Tokyo street at night reflecting holographic billboards in the background, dramatic side lighting, cel-shaded with sharp linework, in the style of Ghost in the Shell
photoreal, 3d, extra fingers, blurry, low quality
推荐模型： NovelAI, AnythingV5, Midjourney --niji
点名具体动漫（攻壳机动队/阿基拉）比模糊的 "cyberpunk anime" 出图稳定。
Concept art of a cozy fantasy tavern interior at night, warm fireplace casting orange glow, wooden beams overhead, a bard playing lute in the corner, patrons laughing at long tables, mugs and copper cookware on the walls, dust motes in the firelight, painted in the style of Magali Villeneuve, ultra-detailed
推荐模型： Midjourney, FLUX.1
点名奇幻插画家（Magali Villeneuve、John Howe）能立刻得到辨识度高的风格。
Macro product photograph of a luxury automatic mechanical watch, sapphire crystal showing the movement inside, brushed steel bracelet, dramatic 45-degree key light from the upper left, deep black background with a single soft rim light, shallow depth of field, Hasselblad H6D, 4k, magazine-quality retouch
cluttered, person, watermark, low resolution, soft focus on the dial
推荐模型： Midjourney v7, FLUX.1
产品摄影三要素：明确主光方向、纯黑背景、微距构图。
Black and white documentary portrait of an elderly fisherman with weathered face and kind eyes, harbor in the soft-focus background, shot on Leica M with 50mm Summilux, natural window light from the left, deep contrast, film grain, in the style of Sebastiao Salgado
color, smiling for camera, studio lighting, retouched skin
推荐模型： Midjourney v7, FLUX.1
黑白纪实人像要点：真实摄影师参考 + 颗粒感胶片描述。
Studio 3D product video, a wireless earbud charging case slowly disassembles into its components — case, two earbuds, internal battery — components float apart and rotate, soft top light against a gradient grey background, 5 seconds, smooth choreography, no human in frame, end with all parts settled in space
推荐模型： Runway Gen-3 Alpha, Kling, Sora
告诉模型相机静止，否则它会自作主张推拉，与爆炸动画冲突。
Cinematic shot of a small specialty coffee shop at 7am, golden morning light streaming through tall windows, barista in apron pulling a shot of espresso, steam rising slowly, dust particles visible in the light, shallow depth of field on the cup, gentle camera push-in, 6 seconds, Roger Deakins inspired color grading
推荐模型： Sora, Runway Gen-3, Veo
点名摄影指导（Roger Deakins、Emmanuel Lubezki）能锁定特定光影风格。
Anime style, a young girl with a school bag flies above a Japanese city at dusk, hands outstretched, gentle wind moving her hair and clothes, warm orange sky with scattered clouds, distant Mt. Fuji silhouette, camera tracks alongside her, 6 seconds, hand-drawn cel shading, Hayao Miyazaki inspired sky
推荐模型： Sora, Kling, Hailuo
飞行场景需要 "camera tracks alongside"，否则模型容易出静帧。
Macro video shot of fingers typing on a mechanical keyboard, warm desk lamp light, individual keys depressing in detail, slight camera dolly along the keys, shallow depth of field, soft bokeh of monitor light in background, 5 seconds, hyper-detailed, smooth motion
推荐模型： Runway Gen-3, Pika, Sora
微距 + 单一主体 + 推轨运镜 = 多数模型都能稳定出片。
Close-up of rain droplets sliding down a window pane, blurred city lights in the background, slight bokeh, gentle wide-aperture cinematography, soft natural light, lo-fi music video aesthetic, 6 seconds, no camera movement, gentle natural variation in droplet flow
推荐模型： Pika, Runway Gen-3
相机静止 + 自然物理（droplet flow）比要求运镜的结果干净得多。
iPhone 16 Pro mockup floating in three-quarter perspective, displaying a fintech mobile app dashboard with dark mode, neumorphic cards, soft cyan and purple accent gradients, subtle particle background, premium SaaS aesthetic, ultra-clean typography, 8k product render
cluttered, text artifacts, distorted, low resolution, fake-looking
推荐模型： Midjourney v7, FLUX.1
UI 模型图要明确写手机型号 + 视角 + 渲染品质，模型对"mockup"理解需要具体锚点。
Stylized 3D character of a friendly young fox wearing a tiny scarf, big expressive eyes, soft fur with subsurface scattering, neutral standing pose, three-quarter view, soft three-point lighting, Pixar-inspired character design, white seamless background, Octane render quality
photorealistic, scary, distorted anatomy, multiple characters
推荐模型： Midjourney, FLUX.1
角色设计要明写姿势 + 视角 + 中性背景，否则模型会自作主张加环境。
Documentary photojournalism shot inside a busy modern newsroom, editor in mid-conversation gesturing at a wall of monitors showing live news, shallow depth of field on the editor, ambient bokeh of fluorescent lights, shot on Leica Q3, slight grain, in the style of Magnum photography
staged, beauty filter, stock photo aesthetic, clean and tidy
推荐模型： Midjourney v7, FLUX.1
引用 Magnum / VII Photo 才有真纪实感 —— 笼统 "photojournalism" 容易出 stock 风。
Minimalist logomark design for a sustainability-focused tech startup, geometric leaf motif fused with a circuit pattern, single-color (forest green), clean negative space, vector-style flat design, isolated on white background, multiple variant exploration, professional brand identity
text, photographic, complex shading, multiple colors, ornate
推荐模型： Midjourney, FLUX.1
Logo 探索写 "multiple variant exploration"，能拿到一组变体挑选。
Editorial illustration for a New Yorker-style article on AI in healthcare, a doctor and a robot working together over a glowing diagnostic screen, muted blue and warm beige palette, subtle texture, expressive but restrained, hand-drawn feel with digital polish, in the style of Christoph Niemann
cute mascot, 3d render, photo, comic book, oversaturated
推荐模型： Midjourney, FLUX.1
编辑插画跟一般数字艺术不同。点名刊物（纽约客、NYT）能拿到对的调性。
Abstract 3D data visualization, intertwining ribbons of light flowing through a dark space, representing data streams, soft glow with chromatic aberration at edges, deep navy background with cyan and magenta highlights, organic curves with mathematical precision, suitable as a hero image for a tech company
推荐模型： Midjourney, FLUX.1
抽象数据图最好用具象短语（ribbons of light、data streams），纯抽象描述效果差。
Anime style, vast magical library interior with towering bookshelves reaching impossibly high, floating books and glowing magical orbs drifting through warm beams of light from stained glass windows, a young apprentice in robes reading in a cozy nook, Studio Ghibli inspired warm color palette, painterly background
photoreal, 3d, modern setting, distorted perspective
推荐模型： NovelAI, Midjourney --niji
"Studio Ghibli inspired" 能稳定唤起温暖手绘感（提示词本身不涉版权）。
Architectural photograph of a modern minimalist museum building, clean geometric concrete forms with large reflective glass panels, taken at the blue hour with the interior lights just beginning to glow, dramatic long shadow from late sun, ultra-sharp, shot on Hasselblad H6D, in the style of Iwan Baan
people in frame, motion blur, distorted perspective, vignetting
推荐模型： Midjourney v7, FLUX.1
建筑题材点名真实建筑摄影师（Iwan Baan、Hélène Binet），模型懂这些惯例。
Cinematic POV shot from the passenger seat of a car driving slowly through a neon-lit Tokyo street at night, rain on the windshield blurring the colorful signs, gentle motion blur, anamorphic lens flare from passing lights, soft city ambient lighting, 6 seconds, smooth tracking
推荐模型： Sora, Runway Gen-3, Veo
POV 镜头写明座位（"passenger seat"）锚定取景。
Seamless morphing transition video, a snowy mountain landscape gradually transforms into a tropical beach, sky color shifts from cold blue to warm orange, particles drifting through the transition, 5 seconds, smooth interpolation, dreamlike quality, no harsh cuts
推荐模型： Runway Gen-3, Kling
变形转场最好让天/地有物理映射（地平线对地平线）。
Macro slow-motion video of espresso pouring into a white ceramic cup, golden crema forming on top, steam rising slowly, dramatic side lighting against dark background, shallow depth of field, 1000fps style smoothness, 5 seconds, no camera movement
推荐模型： Runway Gen-3, Sora
液体视频：明写慢动作 + 蒸汽/油脂细节 + 相机不动 = 稳定出诱人成片。
Looping abstract animation of luminous particles drifting upward through deep navy void, with occasional bright flashes, cyan and purple bioluminescent palette, slow ethereal motion, suitable as a background for product launch hero section, 8 seconds, seamless loop
推荐模型： Runway Gen-3, Pika
背景视频写 "seamless loop"，结尾接回开头才能循环播放。
A rainy city street at night, wet asphalt reflecting pink and cyan neon signs, a lone figure with an umbrella walking away, shallow puddles, bokeh of distant car lights, cinematic 35mm, moody low-key lighting, slight film grain, Blade Runner atmosphere
flat lighting, daytime, empty dull scene, oversharpened, watermark
推荐模型： Midjourney v7, FLUX.1
反光 + 散景 + 单一主体能营造纵深。可少量引用参考氛围（如 Blade Runner）来定调,别堆太多。
Studio product photography of a frosted glass serum bottle with a gold dropper, floating on a soft beige podium, gentle gradient background, soft box lighting with a subtle reflection underneath, a few water droplets on the glass, minimalist, high-end skincare advertising, ultra sharp, 100mm macro
cluttered background, harsh shadows, fingerprints, cheap plastic look, text, logo
推荐模型： Midjourney v7, FLUX.1, Stable Diffusion XL
做电商图:写清材质（磨砂玻璃）、托台/背景、布光方式（柔光箱）。
Minimalist concrete and glass building photographed at golden hour, strong diagonal shadows, clean geometric lines, a single tree casting a long shadow, deep blue sky, architectural photography, tilt-shift sharpness, warm rim light on edges, no people
cluttered, power lines, distorted perspective, cars, crowds, low contrast
推荐模型： Midjourney v7, FLUX.1
黄金时刻 + 斜向阴影让建筑更有层次。"no people" 保持线条干净。
Flat vector illustration for a SaaS landing page, a person working at a laptop surrounded by floating UI cards and charts, soft pastel palette with one accent color, rounded shapes, subtle long shadows, clean negative space, modern corporate illustration style
photorealistic, gradient mesh noise, cluttered, harsh outlines, text
推荐模型： Midjourney v7, Stable Diffusion XL
做 UI/营销插画就写 "flat vector"、限制配色、留白,这样能衬在文字后面。
A cozy children-book illustration of a small fox reading a book under a glowing lantern in an autumn forest, warm watercolor textures, soft edges, gentle dappled light, leaves drifting, storybook composition, hand-painted feel, whimsical and heartwarming
scary, dark, photorealistic, harsh lines, text, distorted anatomy
推荐模型： Midjourney v7, Stable Diffusion XL
水彩质感 + 暖光 + 明确的角色动作,出来就像真正的绘本一页。
Anime style illustration, a teenage girl in a school uniform standing on a rooftop at sunset, wind in her hair, dramatic orange and purple sky with volumetric clouds, distant city skyline, lens flare, detailed cel shading, Makoto Shinkai inspired atmosphere, highly detailed background
realistic, 3d render, blurry, extra limbs, bad hands, low detail background
推荐模型： NovelAI, Stable Diffusion XL, Midjourney v7 (niji)
点一个氛围参考（如 "Makoto Shinkai inspired"）可引导天空和光线,又不抄具体作品。
Cute isometric 3D render of a cozy home office, tiny plants, a desk with a glowing monitor, warm bookshelf, soft global illumination, clay-like materials, pastel color scheme, blender style, soft ambient occlusion, miniature diorama feel, centered composition
flat 2d, photorealistic, harsh lighting, cluttered, text, watermark
推荐模型： Midjourney v7, Stable Diffusion XL
"isometric" + "clay materials" + "soft GI" 就是那种流行的可爱 3D 风配方。
High-end 3D product render of a futuristic sneaker floating against a soft gradient studio backdrop, dramatic studio lighting, crisp reflections, detailed fabric and rubber materials, subtle motion of laces, octane render quality, sharp focus, advertising key visual
low poly, flat lighting, blurry, dirty, text, logo, busy background
推荐模型： Midjourney v7, FLUX.1
做 3D 广告图,提渲染引擎质感（如 "octane render"）和材质细节能推高真实度。
Epic fantasy concept art of a floating island with cascading waterfalls into clouds below, ancient ruins on top, a lone traveler for scale, dramatic god rays breaking through storm clouds, painterly brushwork, cinematic wide shot, rich atmospheric perspective, matte painting quality
flat, low detail, cartoonish, text, watermark, oversaturated
推荐模型： Midjourney v7, Stable Diffusion XL
奇幻大场景加 "a lone traveler for scale"——放个小人当比例尺,景就显得宏大。
Character concept art of a wandering desert mage, layered sand-worn robes, intricate brass accessories, weathered leather satchel, full body front view, neutral grey background, detailed costume design, painterly rendering, game art style, soft studio lighting
multiple characters, busy background, blurry, bad anatomy, extra fingers, text
推荐模型： Midjourney v7, Stable Diffusion XL
角色设定图写 "full body front view" + "neutral grey background",设计才看得清。
Dramatic black and white studio portrait of an older man with a weathered face, deep wrinkles telling a story, single hard key light from the side (Rembrandt lighting), dark background, sharp catchlights in the eyes, fine skin texture, fine-art monochrome, 85mm
color, flat lighting, smooth plastic skin, blurry, distorted features
推荐模型： Midjourney v7, FLUX.1
拍肖像点明布光法（如 "Rembrandt lighting"）——模型认识这些经典布光。
A sleek wireless earbud case slowly rotating 360 degrees on a reflective dark surface, soft studio rim lighting catching the edges, shallow depth of field, smooth continuous turntable motion, premium advertising look, 6 seconds, clean loop
推荐模型： Runway Gen-3, Kling, Pika
旋转展示:写 "rotating 360 degrees" + "clean loop",镜头保持不动。
Timelapse of fast-moving clouds rolling over a mountain ridge at dawn, warm sunrise light sweeping across the peaks, long shadows shifting, deep valleys filling with mist, static wide shot, cinematic color grade, 8 seconds, smooth motion
推荐模型： Runway Gen-3, Kling
做延时要写清什么在动（云、影、雾）,机位保持固定。
A minimal logo mark for a coffee brand, single continuous line forming a coffee cup and a leaf, geometric balance, flat monochrome on white, generous negative space, vector style, centered, no text, scalable icon design
realistic, gradients, 3d, clutter, text, multiple variations, watermark
推荐模型： Midjourney v7, Stable Diffusion XL
做 Logo 写 "single continuous line""flat monochrome""no text"——AI 出的字不可靠,文字部分自己加。
A seamless repeating geometric pattern of interlocking hexagons and thin lines, two-tone muted teal and cream palette, flat vector, balanced density, suitable for packaging and wallpaper, tileable, no seams
photorealistic, harsh contrast, visible seams, gradient noise, text
推荐模型： Stable Diffusion XL, Midjourney v7
要做可平铺背景就写 "seamless / tileable / no seams"。
A set of flat line-and-fill icons on a soft grid, themes of cloud, lock, chart and gear, consistent stroke weight, rounded corners, one accent color, clean tech infographic style, white background, evenly spaced
inconsistent styles, photorealistic, heavy shadows, text labels, clutter
推荐模型： Midjourney v7, Stable Diffusion XL
做图标组要强调 "consistent stroke weight" + "one accent color",才像一套。
A bright Scandinavian living room, light oak floor, a linen sofa with knitted throw, large window with sheer curtains, a few green plants, warm morning light, interior design magazine photography, wide angle, natural color, airy and clean
cluttered, dark, fisheye distortion, oversaturated, people, text
推荐模型： Midjourney v7, FLUX.1
室内图用一个风格名（如 Scandinavian）、一个光源（morning light）、广角,效果最好。
Extreme macro photograph of a single dewdrop on a green leaf at dawn, the drop refracting a tiny inverted landscape, razor-thin depth of field, soft bokeh background, glistening highlights, 100mm macro lens, ultra detailed, natural light
blurry subject, flat lighting, artificial look, dust, oversharpened halos, text
推荐模型： Midjourney v7, FLUX.1
微距写明镜头（100mm macro）和单一焦点;"razor-thin depth of field" 强调微观尺度。
A studio portrait of a fluffy golden retriever puppy, head tilted, soft catchlight in the eyes, seamless pastel blue backdrop, soft box lighting, sharp fur detail, shallow depth of field, adorable and warm, commercial pet photography
blurry, harsh shadows, red eye, distorted anatomy, busy background, text
推荐模型： Midjourney v7, FLUX.1
"catchlight in the eyes"（眼神光）能让动物/人像活过来,值得专门写上。
A cute chibi mascot character, round body, big sparkling eyes, small cat ears, holding a tiny coffee cup, soft cel shading, pastel palette, simple background, sticker-ready, thick clean outline, kawaii style, centered
realistic proportions, complex background, bad hands, blurry, text, extra limbs
推荐模型： NovelAI, Stable Diffusion XL, Midjourney v7 (niji)
"chibi / thick clean outline / sticker-ready" 能出可抠图做贴纸/表情的吉祥物。
Concept art of a sleek hovering rescue vehicle, aerodynamic plated armor, glowing energy thrusters, three-quarter view, neutral background with light ground shadow, hard-surface design, detailed panel lines, cinematic studio lighting, game/film concept quality
busy background, blurry, low detail, melted shapes, text, watermark
推荐模型： Midjourney v7, Stable Diffusion XL
hard-surface + "three-quarter view"（四分之三视角）+ panel lines,出来像正经的载具设定图。
Artistic double exposure of a man's side profile blended with a misty pine forest, the trees forming the silhouette, muted earthy tones, fine grain, fine-art photography, clean negative space on one side, evocative and moody
messy blend, oversaturated, harsh edges, text, watermark, low resolution
推荐模型： Midjourney v7, Stable Diffusion XL
双重曝光:点明两个主体,让其中一个构成另一个的轮廓。
A lone traveler in a long coat walking slowly toward the camera down a misty forest path at dawn, leaves drifting, soft volumetric light through the trees, gentle handheld camera, cinematic depth of field, 6 seconds, natural motion
推荐模型： Runway Gen-3, Kling, Pika
人物动作越简单越稳（如 "walking slowly toward camera"）,复杂动作现阶段视频模型容易崩。
Extreme slow-motion of golden honey pouring onto a stack of pancakes, glistening highlights, soft natural light, droplets and slow ribbons of liquid, shallow depth of field, appetizing food commercial, static camera, 5 seconds
推荐模型： Runway Gen-3, Kling
慢镜液体是现在模型的强项——写 "extreme slow-motion",机位别动。
A smooth cinematic orbit shot circling around a vintage motorcycle parked in an empty warehouse, shafts of light from high windows, dust motes in the air, slow steady camera arc, dramatic side lighting, 8 seconds, seamless motion
推荐模型： Runway Gen-3, Kling
把运镜写明白（如 "orbit shot circling around"）——这是视频模型最吃的指令。
A stylized 3D character of a friendly young explorer, large expressive eyes, soft rounded forms, Pixar-like appeal, subtle subsurface scattering on skin, soft three-point studio lighting, neutral background, full body, polished render, appealing proportions
realistic photo, low poly, bad anatomy, dead eyes, harsh shadows, text
推荐模型： Midjourney v7, Stable Diffusion XL
想要讨喜的 3D 角色,皮肤写 "subsurface scattering"、布光写 "soft three-point lighting"。
A cute glossy 3D render of a single bubble tea cup with a smiling face, soft clay material, pastel background, big rounded straw, soft ambient occlusion, app-icon style, centered, playful, clean studio lighting
realistic, flat 2d, harsh reflections, cluttered, text, watermark
推荐模型： Midjourney v7, Stable Diffusion XL
"glossy clay material" + "app-icon style" 能出 App 和贴纸常用的那种软糯 3D 图标。
A 3D inflated balloon-style letterform shape (no specific text), glossy candy material, soft pink and mint colors, plump rounded volume, floating on a clean gradient, soft studio lighting, playful typographic art, high detail render
flat, realistic photo, sharp edges, dull material, busy background
推荐模型： Midjourney v7
AI 拼准字母很难——先生成气球质感,文字到设计软件里自己合成更稳。
A clean motion-graphics logo reveal, a simple geometric mark assembling from thin animated lines and particles, soft glow, dark gradient background, smooth ease-in-out timing, premium tech brand feel, 4 seconds, ends on a static mark
推荐模型： Runway Gen-3, Pika
Logo 揭示保持抽象（线条/粒子聚合）——模型渲染不准确切的品牌文字。
Energetic kinetic typography motion background (no readable words), bold abstract shapes sliding and popping in rhythm, high-contrast black and yellow, sharp transitions, dynamic camera shake, music-video energy, 5 seconds, loopable
推荐模型： Runway Gen-3, Pika
当背景层用,真正的文字动画在 AE/剪映里叠上去。
A sleek smartphone mockup showing a finance app, smooth UI micro-interactions: cards sliding in, a number counting up, a toggle switching, soft depth and shadows, clean light theme, gentle camera push-in, product demo style, 6 seconds
推荐模型： Runway Gen-3, Kling
UI 演示要逐个写微交互（卡片滑入、数字滚动）,配一个缓慢推近镜头。
A top-down flat-lay of a leather travel wallet surrounded by curated props — a passport, sunglasses, a watch, dried flowers and a coffee cup, warm neutral palette, soft natural light, linen background, lifestyle product photography, balanced composition
cluttered, harsh shadows, oversaturated, plastic look, text, watermark
推荐模型： Midjourney v7, FLUX.1
平铺图靠精选道具讲故事;具体点名 3-4 件物品,别写 "各种物品"。
Aerial drone photograph of a turquoise coastline, waves rolling onto a white sand beach, dramatic cliffs, a tiny boat for scale, top-down perspective, vivid natural colors, crisp midday light, high altitude, ultra detailed, travel photography
low resolution, blurry, oversaturated cartoon colors, distorted, text
推荐模型： Midjourney v7, FLUX.1
写 "aerial drone / top-down" 并放一个小物体 "for scale",才能体现高度。
High-fashion editorial photograph, a model in an avant-garde structured outfit against a bold colored seamless backdrop, dramatic studio strobe lighting, confident pose, sharp detail on fabric texture, Vogue-style composition, strong shadows, 85mm
casual, snapshot, soft focus, distorted face, bad hands, low contrast, text
推荐模型： Midjourney v7, FLUX.1
时尚大片 = 纯色硬背景 + 影室闪光 + 有张力的姿势。点明面料能保住质感。
Environment concept art of an abandoned overgrown library, shafts of light through a broken ceiling, vines climbing the bookshelves, dust in the air, scattered books, moody atmospheric perspective, painterly rendering, cinematic composition, game environment quality
flat lighting, low detail, modern clean, text, watermark, oversaturated
推荐模型： Midjourney v7, Stable Diffusion XL
场景概念靠光柱 + 氛围（尘埃、藤蔓）+ "atmospheric perspective"（空气透视）活起来。
Anime food illustration of a steaming bowl of ramen, glossy broth, perfectly arranged toppings, visible steam wisps, warm appetizing colors, detailed cel shading, cozy late-night diner vibe, mouth-watering, Studio-quality background blur
realistic photo, dull colors, messy, blurry, text, distorted bowl
推荐模型： NovelAI, Stable Diffusion XL, Midjourney v7 (niji)
动漫美食就吃 "glossy / steam wisps / warm appetizing colors"——这是招牌的诱人感。
A loose watercolor painting of rolling lavender fields at dusk, wet-on-wet washes, soft blooming edges, visible paper texture, muted purple and warm ochre palette, a few suggestive brushstrokes for distant trees, airy negative space, hand-painted feel
photorealistic, hard outlines, digital smoothness, oversaturated, text
推荐模型： Midjourney v7, Stable Diffusion XL
"wet-on-wet" + "visible paper texture" + "blooming edges" 才像真水彩,而不是套滤镜。
A minimalist single continuous line drawing of two faces in profile, elegant flowing curves, black ink on cream paper, no shading, plenty of negative space, modern gallery print style, delicate and refined
shading, color fills, broken lines, clutter, photorealistic, text
推荐模型： Midjourney v7, Stable Diffusion XL
线条画要 "continuous line""no shading" 加大量留白——很适合纹身和装饰画。
A vintage 1950s travel poster of a seaside town, bold flat color blocks, limited retro palette, stylized clouds and waves, gentle grain, art-deco shapes, screen-print texture, nostalgic and clean composition, space at the top for a title
photorealistic, modern gradients, busy detail, harsh contrast, text
推荐模型： Midjourney v7, Stable Diffusion XL
定一个年代（1950s）+ 工艺（screen-print texture）,并 "space for a title" 方便后期加文字。
A precise knolling photograph of everyday carry items neatly arranged at right angles — a pocket knife, pen, notebook, keys, watch and coins, top-down, even soft lighting, dark slate background, organized grid, sharp detail, satisfying symmetry
messy, tilted objects, harsh shadows, cluttered, blurry, text
推荐模型： Midjourney v7, FLUX.1
物品成 90° 整齐排列的拍法专有名词就叫 "knolling",直接写它就行。
A dramatic backlit silhouette of a person standing on a hill at sunset, arms slightly raised, deep orange and magenta sky, sun flare behind them, long shadow, high contrast, minimal foreground, evocative and cinematic, 35mm
flat lighting, visible facial detail, busy background, low contrast, text
推荐模型： Midjourney v7, FLUX.1
拍剪影把光源放主体背后,写 "high contrast" 让细节压成黑色。
Anime mecha key visual, a towering humanoid robot standing in a ruined city at dusk, glowing cockpit and thrusters, intricate mechanical paneling, dynamic low-angle shot, dramatic rim light, detailed cel shading, epic scale, atmospheric haze
realistic, low detail, messy mechanics, bad proportions, blurry, text
推荐模型： NovelAI, Stable Diffusion XL, Midjourney v7 (niji)
低角度让机甲显得巨大;"intricate mechanical paneling" 防止机械细节糊成一团。
Game item concept of an ornate magical potion bottle, glowing swirling liquid, carved cork and brass label holder, three-quarter view, neutral dark background with subtle glow, painterly rendering, RPG inventory art style, crisp detail, centered
multiple items, busy background, blurry, flat, low detail, text
推荐模型： Midjourney v7, Stable Diffusion XL
做物品图标:单个物体、"three-quarter view"、深色中性背景、居中,方便抠图。
A long-exposure night photograph of a highway interchange from above, red and white car light trails weaving through the curves, city glow on the horizon, deep blue hour sky, sharp static structures, smooth flowing light streaks, tripod-steady
daytime, frozen cars, blurry buildings, noise, low resolution, text
推荐模型： Midjourney v7, FLUX.1
写 "long-exposure" + "light trails" + 静物清晰,只让灯光拉丝、其余不糊。
A charming low-poly 3D scene of a tiny island with a lighthouse, faceted geometric trees and rocks, flat shaded triangles, soft gradient sky, gentle ambient light, pastel palette, miniature diorama, clean and minimal, isometric-ish angle
high detail realism, smooth surfaces, photorealistic, busy, text
推荐模型： Midjourney v7, Stable Diffusion XL
低多边形是独特风格——写 "faceted / flat shaded triangles",免得渲染成光滑 3D。
A charming claymation-style animation of a small clay character waving hello, visible fingerprints and clay texture, stop-motion feel with slight frame jitter, warm handmade set, soft studio light, playful, 5 seconds
推荐模型： Runway Gen-3, Kling
写 "stop-motion feel / slight frame jitter"——太流畅反而没了手工黏土定格的味道。
Top-down cinematic shot of hands chopping fresh vegetables on a wooden board, colorful peppers and herbs, natural window light, shallow steam, smooth deliberate motion, food-channel quality, warm tones, static overhead camera, 6 seconds
推荐模型： Runway Gen-3, Kling
俯拍烹饪用固定机位 + 简单手部动作（切、搅）最稳。
Cinematic timelapse-feel video of dark storm clouds rolling over a wide open plain, distant lightning flashes, wind bending the grass, dramatic shifting light, ominous mood, wide static shot, deep contrast, 8 seconds
推荐模型： Runway Gen-3, Kling
天气的戏剧感来自运动（翻滚的云、弯倒的草）+ 偶发事件（闪电）。机位保持广角固定。
A dynamic American comic book panel, a hero leaping between rooftops, bold ink outlines, halftone dot shading, dramatic foreshortening, high-contrast cel colors, speed lines, dynamic diagonal composition, empty speech-bubble space, graphic novel style
photorealistic, soft pastel, blurry, flat pose, text inside bubbles
推荐模型： Midjourney v7, Stable Diffusion XL
半调网点 + 粗墨线 + 速度线 = 美漫味。留 "empty speech-bubble space" 方便后期加对白。
A retro 16-bit pixel art scene of a cozy wizard study at night, glowing potions, a cat on a stack of books, warm candlelight, limited palette, crisp pixels, dithering for gradients, side-scroller game art style, detailed but readable
smooth anti-aliasing, blurry, high resolution photo, 3d render, text
推荐模型： Stable Diffusion XL, Midjourney v7
写 "16-bit / crisp pixels / dithering"——不然模型会把像素糊平。
Macro product photography of a diamond ring on black velvet, brilliant sparkle and fire in the stone, crisp reflections on the gold band, soft gradient spotlight, ultra sharp focus stacking, luxury jewelry advertising, deep shadows, 100mm macro
dust, fingerprints, dull stone, flat lighting, busy background, text
推荐模型： Midjourney v7, FLUX.1
拍珠宝写 "focus stacking" + 单束柔光,让宝石出火彩又不过曝。
A cyberpunk portrait of a woman, face lit by pink and teal neon, subtle holographic reflections on skin, rain droplets, dark wet city bokeh behind, cinematic moody lighting, sharp detailed eyes, futuristic fashion, 85mm, shallow depth of field
flat daylight, plastic skin, low contrast, distorted face, text, watermark
推荐模型： Midjourney v7, FLUX.1
脸上打双色霓虹（粉 + 青）是赛博朋克招牌;加雨滴和散景增加纵深。
Creature concept art of a majestic forest guardian beast, part deer part moss-covered stone, glowing antlers, bioluminescent markings, full body side view, neutral misty background, painterly detail, believable anatomy, cinematic creature design for film
cute cartoon, multiple creatures, busy background, bad anatomy, blurry, text
推荐模型： Midjourney v7, Stable Diffusion XL
把两种真实事物组合（"part deer part stone"）能造出解剖可信的原创生物。
A peaceful anime countryside landscape, rice fields under a vast blue sky with towering cumulus clouds, a winding road, distant mountains, telephone poles, warm afternoon light, highly detailed background, no characters, Makoto Shinkai inspired clarity
characters, blurry, low detail, dull sky, realistic photo, text
推荐模型： NovelAI, Stable Diffusion XL, Midjourney v7 (niji)
动漫背景靠大而细的天空 + 日常细节（电线杆、小路）出彩。"no characters" 保持纯风景。
A stylized 3D game asset of a treasure chest, hand-painted texture style, exaggerated chunky proportions, warm wood and gold trim, soft baked lighting, neutral background, World of Warcraft inspired art direction, clean topology look, centered
photorealistic, low detail, flat 2d, harsh shadows, cluttered, text
推荐模型： Midjourney v7, Stable Diffusion XL
手绘贴图 + 夸张厚重比例 = 风格化游戏资产味（区别于写实 PBR 渲染）。
A high-speed sports photograph freezing a basketball player mid dunk, sweat droplets suspended in air, motion-frozen by fast shutter, dramatic arena lighting, shallow depth of field isolating the subject, intense expression, dynamic angle, 200mm telephoto
motion blur on subject, flat lighting, dull, low resolution, distorted limbs, text
推荐模型： Midjourney v7, FLUX.1
写 "fast shutter / motion-frozen" 加长焦,凝固运动高潮瞬间最清晰。
An ornate tarot card illustration in art-nouveau style, a celestial figure surrounded by symbolic moons and stars, intricate gold linework borders, rich jewel-tone palette, symmetrical composition, decorative flourishes, mystical and elegant, flat illustration
photorealistic, messy, asymmetric, dull colors, modern minimal, text
推荐模型： Midjourney v7, Stable Diffusion XL
新艺术风 + 金色线描 + 对称构图,出经典塔罗/神谕牌的味道。
A moody still life in chiaroscuro, a few ripe fruits, a glass of wine and an old book on a dark wooden table, a single dramatic side light, deep shadows, rich painterly tones, Dutch-master inspired, fine texture, fine-art photography
flat bright lighting, cluttered, modern objects, oversaturated, text
推荐模型： Midjourney v7, FLUX.1
明暗对照 = 单束硬侧光 + 浓重阴影。点 "Dutch-master inspired" 引导色调。
A cinematic drone shot rising and tilting up to reveal a vast mountain valley at golden hour, a river winding below, layers of ridges fading into haze, smooth ascending camera motion, epic scale, warm light, 8 seconds
推荐模型： Runway Gen-3, Kling
揭示镜头:写清运镜（"rising and tilting up to reveal"）和最后展开的大场面。
A subtle cinemagraph of a woman by a window, only her hair and the steam from a coffee cup gently moving, everything else perfectly still, soft natural light, shallow depth of field, calm and intimate, seamless loop, 5 seconds
推荐模型： Runway Gen-3, Pika
Cinemagraph 只让一处动、其余全静——点明动的是什么（头发、热气）才出效果。
A premium 3:4 city tourism campaign poster, theme "Misty Rainy Night · Mountain City". Cinematic night view of layered hillside buildings glowing through rain and fog, reflections on wet streets, cable car light trails, moody teal-and-amber palette. Bold modern editorial typography with a large title set in clean sans-serif, a small kicker line, and a thin baseline credit bar. Balanced negative space, high-end travel-brand look. Place the exact headline text "MOUNTAIN CITY" top-left.
推荐模型： gpt-image-2, Nano Banana Pro, Midjourney v7
先定画幅(3:4),需要出现的文字用直引号包住——改写措辞会让文字渲染变差。
A high-fashion magazine cover, 3:4 portrait, Vogue Paris editorial aesthetic. Subject: a tall female model in an avant-garde sculptural gown, confident gaze, studio beauty lighting with a soft falloff. Masthead "VOGUE" across the top partly occluded by the model's head, cover lines in small elegant serif down the left edge, issue line bottom-right. Glossy print texture, refined color grade, fashion-editorial composition.
amateur, cluttered text, low resolution, distorted face, extra fingers
推荐模型： gpt-image-2, Midjourney v7, FLUX.1
让主体压住刊头(局部遮挡),这个遮挡关系才像真实杂志封面。
A vintage 1950s science-fiction pulp magazine cover, 3:4 portrait, classic "Astounding Science Fiction" aesthetic. A retro chrome rocket and an astronaut facing a giant alien creature on a red planet, gouache illustration with visible brush texture, saturated mid-century palette, slight paper aging and halftone print grain. Big bold title banner top, a lurid tagline, and a price corner. Hand-lettered retro display type.
推荐模型： gpt-image-2, Midjourney v7
锚定真实年代+刊物("1950s Astounding")+媒材("gouache"),复古风格才统一。
A high-end commercial poster for a product called "Aurora Oolong Cold Brew". A single chilled bottle centered on a clean gradient backdrop, condensation droplets, a swirl of oolong tea and floating ice as a dynamic accent, soft studio rim light. Minimalist composition with generous negative space, one bold product name in modern sans-serif, a short tagline, brand mark bottom-center. Premium, clean, appetite-appeal lighting.
clutter, busy background, distorted text, low quality, watermark
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
极简产品海报靠留白 + 单一主光方向;文字只留产品名 + 一句标语。
A square high-end brand identity showcase board for a fictional brand "Moss Radio". One clean modular grid presenting: a primary logo, a monogram mark, a color palette swatch row (deep moss green, cream, rust), type specimen, a business card mockup, a tote bag, and a packaging label. Consistent spacing, subtle paper shadows, editorial designer-portfolio aesthetic, neutral studio background, true-to-life mockup lighting.
推荐模型： gpt-image-2, Nano Banana Pro
让它出一整块"modular grid board"(模块化网格板),比拆成单件构图好得多。
Design 3 UI screens for a "calm habit-tracker" app, shown as realistic phone mockups side by side: 1) Onboarding with a friendly hero illustration and a primary CTA; 2) Today dashboard with habit rings and a streak counter; 3) Stats page with a weekly bar chart. Style: iOS native design language, soft sage-green accent, light mode, rounded cards, SF-style typography, generous whitespace, crisp 1x pixel-perfect look.
推荐模型： gpt-image-2, Nano Banana Pro
把每屏编号并说明用途,模型会在多屏间保持一致的设计系统。
A playful brand kit for "Mochi Metro", a fictional dessert chain, presented as one square modular board: bold rounded logo, bouncy custom wordmark, candy color palette (peach, matcha, ube), pattern tile, sticker set, cup and bag packaging mockups, and a mascot. Fun modern layout, soft drop shadows, consistent corner radius, cheerful but premium, neutral background.
推荐模型： gpt-image-2, Nano Banana Pro
开头先定调性词("playful/premium/brutalist"),它会同时影响字体、配色与间距。
Generate a museum-catalog-style disassembly infographic of a vintage film camera. Top-down exploded view with every component — body, lens elements, gears, springs, screws — laid out on a precise grid and connected to neat numbered callout labels with short captions. Clean off-white background, fine hairline leader lines, elegant serif headings and small-caps labels, restrained two-color accent, archival reference-plate aesthetic, razor-sharp detail.
推荐模型： gpt-image-2, Nano Banana Pro
写明"编号标注 + 引线 + 短说明",才会出真正的图解,而不是单纯摆拍。
Generate a high-quality vertical encyclopedia-style field-guide infographic about the giant panda. Not a normal poster — a dense, structured reference page: a large central labeled illustration, surrounded by anatomy callouts, a habitat map, a diet pie, a size-comparison silhouette, and a fact sidebar. Natural-history textbook aesthetic, muted scientific palette, clean grid, legible serif captions, vertical 3:4.
推荐模型： gpt-image-2, Nano Banana Pro
把想要的子模块列出来(解剖/地图/食性/尺寸),模型会排成一整页连贯图鉴。
Make a 35mm-film-style reference board diagramming camera styles and presets: a clean grid of sample frames, each labeled with the look (e.g. "anamorphic", "macro", "fisheye", "tilt-shift", "golden hour", "high-key") plus a one-line note on when to use it. Editorial cheat-sheet layout, warm film grain, consistent thumbnail size, tidy typographic labels, 16:9.
推荐模型： gpt-image-2, Nano Banana Pro
带标签的小样网格,是最稳定的"速查表"信息图格式。
An original AAA dark-fantasy action-RPG screenshot. A silver-haired monster hunter in layered leather armor stands in a ruined marsh facing a towering swamp boss wreathed in fog, third-person over-the-shoulder camera, dynamic rim lighting, subtle motion blur, volumetric god rays. Minimal in-world HUD: health/stamina bars bottom-left, ability icons bottom-center, objective marker. Photoreal Unreal-Engine look, cinematic color grade, 16:9.
flat lighting, broken anatomy, cluttered UI, low resolution, watermark
推荐模型： gpt-image-2, Midjourney v7, FLUX.1
写清 HUD 元素 + 镜头("第三人称越肩"),画面才像实机,而不是宣传原画。
A third-person cyberpunk action-game screenshot set in a neon-soaked European capital at night, rain-slick streets reflecting magenta and cyan signage, the player character vaulting between rooftops. Game HUD: minimap top-right, ammo counter bottom-right, quest log left, crosshair center. Gritty photoreal rendering, anamorphic lens flares, shallow depth of field, high-contrast neon grade, 16:9.
daytime, empty HUD, flat colors, distorted limbs, text gibberish, watermark
推荐模型： gpt-image-2, Midjourney v7, FLUX.1
霓虹赛博靠湿地反光 + 品红/青为主色对,最出味。
An isometric pixel-art RPG screenshot of a traditional Japanese village during cherry-blossom season. Clean 16-bit-era sprite work, tidy isometric tile grid, wooden houses with tiled roofs, a torii gate, falling sakura petals, a small NPC party and a dialogue box at the bottom. Cohesive limited palette, crisp dithering, soft ambient occlusion, charming JRPG art direction.
推荐模型： gpt-image-2, Midjourney v7
写"16-bit + 等距瓦片网格 + 有限调色板",像素才统一,不会糊。
A square 3×3 worldbuilding set for an original dark-fantasy universe called "Saltwind Reach". Nine cohesive concept panels: a hero, a villain, a creature, a weapon, an environment, an architecture style, a faction crest, a key prop, and a wide establishing vista. Unified palette and art direction across all nine, painterly concept-art finish, thin captions under each cell, neutral border.
推荐模型： gpt-image-2, Midjourney v7
用一个命名世界 + 3×3 设定集,能在差异很大的题材间保持风格与配色统一。
Render a premium commercial food photograph from this config:
{ "product": "Chocolate Wafer — Hazelnut Edition", "hero": "single bar with a clean snapped piece, molten chocolate drip", "surface": "dark slate with scattered roasted hazelnuts", "lighting": "dramatic side key + soft fill, glossy highlights", "background": "warm bokeh gradient", "lens": "100mm macro, f/4", "mood": "indulgent, premium", "aspect": "4:5" }
Ultra-realistic, appetite-appeal, razor-sharp focus on the break, subtle steam.plastic look, dull lighting, messy crumbs everywhere, text, watermark
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
JSON 式提示词能精确控制离散属性(镜头/光/情绪),特别适合产品图。
Assemble the provided packaging dieline into a flawless 3D product box: accurate panel mapping, clean folds, undistorted typography and barcodes, correct perspective. Place it as a hero product shot on a soft gradient studio backdrop, dramatic key light with a soft shadow, subtle edge reflections, crisp material (matte coated card with a spot-gloss logo), 4:5, commercial packaging render quality.
warped text, broken folds, wrong perspective, blurry edges, watermark
推荐模型： gpt-image-2, Nano Banana Pro
强调"文字不变形 + 面映射准确"——刀版转盒最容易在这里翻车。
A miniature-diorama advertisement for a skincare serum: a tiny crew of figurines "maintaining" a giant serum bottle as if it were a monument — abseiling down the glass, polishing the dropper, planting a tiny garden at the base. Tilt-shift macro look, soft commercial lighting, pastel set design, the product in pristine sharp focus, whimsical premium brand tone, 4:5, hero ad composition.
cluttered, dull, distorted product label, low detail, watermark
推荐模型： gpt-image-2, Nano Banana Pro, Midjourney v7
尺度反差("小人 vs 巨型产品")是稳定的吸睛广告点子——产品本体务必锐利清晰。
Create a single image: a hero product shot of a gourmet burger plus a 3×3 grid of nine advertising storyboard cells beneath/around it, telling a 15-second TVC — ingredients falling, the patty searing, assembly, the reveal, a satisfied bite, brand close. Consistent product and lighting across every cell, cinematic warm grade, clean thin gutters, tiny shot-note captions, no panel borders clutter, 16:9.
推荐模型： gpt-image-2, Nano Banana Pro
把主图 + 分镜放进一张图,产品/配色/光线一致,方便后续动画化。
A completely RAW, unprocessed, unedited image with full smartphone camera quality. A crowded subway station, slightly imperfect framing, mild motion blur on a passing train, mixed fluorescent and daylight color casts, visible sensor noise in shadows, no beautification, no HDR, authentic candid look, ordinary people mid-stride, 4:3.
over-processed, HDR, cinematic grade, perfect composition, studio lighting, watermark
推荐模型： gpt-image-2, FLUX.1
想去掉"AI 油光感",就明确要 RAW/未修 + 不完美构图 + 传感器噪点。
A photorealistic photo of a wooden chess board mid-game during a serious tournament: a plausible legal-looking position with captured pieces beside the board, a paused analog chess clock, two players' hands hovering in thought, shallow depth of field on the board, soft venue lighting, quiet competitive atmosphere, 3:2.
impossible piece layout, toy pieces, cartoon, harsh flash, distorted hands, watermark
推荐模型： gpt-image-2, FLUX.1
加上配套道具(棋钟、被吃的子、手),才讲得出"正在进行的真实对局"。
A 360° equirectangular panorama of a dense prehistoric jungle: towering ferns, hanging vines, shafts of light through the canopy, a misty river, distant volcanic peaks wrapping seamlessly across the frame. Strict 2:1 aspect ratio, seamless left-right wrap, even exposure, cinematic detail, suitable for VR/skybox use.
seams, visible stitching errors, wrong aspect ratio, people, text, watermark
推荐模型： gpt-image-2, FLUX.1
做 VR/天空盒,要明确"等距柱状、严格 2:1、左右无缝衔接"。
An anime action still in the visual style of a modern MAPPA TV production, landscape 16:9. A silver-white-haired young man mid-technique, cursed energy crackling around his fist, dynamic foreshortening, speed lines and debris, dramatic low angle, high-contrast cel shading with painterly effects, vivid rim light, ultra-detailed background, broadcast-quality key frame.
3d render, photo, extra fingers, muddy colors, static pose, watermark
推荐模型： gpt-image-2, NovelAI, Midjourney v7 (niji)
点名工作室("MAPPA")+ 画面类型("动作定格/关键帧"),比只写"动漫"锁得更准。
Create a 16-panel expression grid (4×4) of a silver-haired, blue-eyed anime girl. Her face shape, hairstyle and outfit stay highly consistent across all panels; only the expression changes — happy, shy, angry, crying, smug, surprised, sleepy, determined, etc. Clean cel shading, uniform panel size, neutral light-gray gutters, character-sheet aesthetic, labels optional.
inconsistent character, drifting hairstyle, extra fingers, messy layout, watermark
推荐模型： gpt-image-2, NovelAI
强调"脸/发/服装保持一致,只换表情"——这个约束才让表情表可用。
A black-and-white shōnen manga two-page spread (landscape 16:9 as one composition) of a basketball climax. Five irregular panels plus one large diagonal hero panel of the protagonist soaring for a dunk; screentone shading, bold inking, dynamic speed lines, sweat and motion, empty speech balloons left blank for lettering, clear right-to-left reading flow, dramatic paneling.
color, photo, 3d, filled-in random text, flat boring panels, watermark
推荐模型： gpt-image-2, NovelAI
要求空对话气泡 + 网点 + 阅读方向,出真正可后期填字的漫画页。
A landscape editorial illustration in layered paper-cut style: a tiny forest night market hidden beneath giant glowing mushrooms, stalls strung with lanterns, little woodland creatures shopping. Distinct stacked paper layers with soft drop shadows between them, warm amber glow against a deep blue night, intricate cut silhouettes, cozy whimsical storybook mood.
photorealistic, flat single layer, harsh, dull palette, text, watermark
推荐模型： gpt-image-2, Midjourney v7
写"分明的层叠纸层、层间带投影",才有真剪纸的纵深,而非平贴纸感。
A horizontal Chinese ink-and-wash handscroll of a Song-dynasty riverside night market: figures crossing an arched bridge, lantern-lit stalls, boats on misty water, distant mountains in pale wash. Traditional brushwork with varied ink density, atmospheric negative space, subtle aged-silk texture, refined classical composition, panoramic ultra-wide aspect.
western style, heavy color, photo, harsh outlines, modern objects, watermark
推荐模型： gpt-image-2, Midjourney v7
水墨靠"墨色浓淡 + 留白",这份呼吸感就是它的全部气质。
A nostalgic pixel-art breakfast still life: a tall stack of fluffy golden pancakes with a melting butter pat and dripping syrup, a fried egg, crisp bacon, a glass of orange juice, on a checkered cloth. 16-bit-era palette, clean dithering, soft pixel shading, cozy warm light, centered composition, crisp non-anti-aliased edges.
blurry, anti-aliased, photorealistic, smeared pixels, text, watermark
推荐模型： gpt-image-2, Midjourney v7
一定要写"无抗锯齿/干净抖动",否则像素会被糊成一团。
A modern pencil-and-screenprint illustration in vintage travel-poster style of the Amalfi Coast: pastel cliffside houses, a winding coastal road, a tiny Vespa, deep blue sea and a sailboat. Cinematic stylized composition, limited mid-century palette, visible screen-print texture and slight registration offset, an elegant place-name banner at the bottom reading "AMALFI".
推荐模型： gpt-image-2, Midjourney v7
中世纪配色 + 丝网印纹理 + 地名横幅 = 经典铁路/旅行海报配方。
A Pixar-quality 3D animation still, landscape 16:9, cinematic feature-film look. A cozy apartment kitchen at dawn; a curious kitten on the counter eyeing a wobbling stack of pancakes, warm window light and soft global illumination, expressive appealing character design, shallow depth of field, subsurface scattering on fur, polished render, heart-warming mood.
photoreal human, uncanny, flat lighting, low detail, text, watermark
推荐模型： gpt-image-2, Midjourney v7
组合"Pixar 级 + 院线质感 + 讨喜角色设计"+ 一个清晰的小剧情瞬间。
A 1940s film-noir black-and-white movie still, landscape 16:9, high contrast. A trench-coated detective lit by venetian-blind shadows in a smoky office, a single hard key light, deep blacks, cigarette haze catching the beam, shot on 35mm with visible grain, dramatic chiaroscuro, classic Hollywood composition.
color, soft flat lighting, modern objects, clean digital look, text, watermark
推荐模型： gpt-image-2, FLUX.1, Midjourney v7
百叶窗投影 + 单束硬主光 + 35mm 颗粒,就是黑色电影的全部用光语言。
A 6-panel film storyboard laid out as a 3×2 grid, landscape 16:9 overall. Each panel a rectangular pencil-and-marker sketch with camera-direction arrows, shot-size labels (WS/MS/CU) and a one-line action note beneath. A chase sequence: establish, pursue, obstacle, near-miss, turn, resolve. Consistent character and location, rough but readable storyboard-artist style, clean white gutters.
推荐模型： gpt-image-2, Nano Banana Pro
加景别标注 + 运镜箭头 + 动作说明,这些信息才让它成为可用分镜。
Create an official-style character reference sheet for a mystical elven archer: front, side and back full-body views in a neutral A-pose on a clean white background, plus a head turnaround with three expressions, a hand close-up, and callouts for key gear (bow, quiver, runic bracer). Consistent proportions across all views, clean line art with flat color fills, small annotations, model-sheet aesthetic, 4:3.
inconsistent proportions, busy background, dramatic lighting, extra limbs, watermark
推荐模型： gpt-image-2, Midjourney v7, NovelAI
要求中性姿势 + 白底 + 比例一致,设定表才能用于建模/动画。
Concept key-art of a teenage mecha pilot on a rusting sea-fortress at dusk: pale skin smudged with soot and salt spray, sharp amber eyes overlaid with glowing HUD reticles, a worn flight suit, a colossal mecha shoulder looming behind in fog. Painterly sci-fi illustration, cinematic rim light, atmospheric haze, gritty detailed textures, dramatic low angle, splash-art composition.
clean studio look, flat lighting, cute chibi, extra fingers, text, watermark
推荐模型： gpt-image-2, Midjourney v7
脏污细节(煤灰、盐渍、锈) + HUD 叠层,营造有生活感的科幻世界。
Cinematic brand advertisement, slow steady camera push-in toward the product centered in frame, warm side lighting, soft background blur, gentle dust particles in the light, no people, premium calm mood, 4 seconds.
推荐模型： Seedance 2.0, Kling, Runway Gen-3
配合 GPT-Image-2 出的主图/分镜帧。运镜单一(推近)+ 时长短,出片更干净。
Follow the storyboard sequence of the 12 reference frames in image1, edited as a fast-cut memory montage. Match each panel's composition, framing and action, keep perfect character and scene continuity, smooth transitions on the beat. Visual style: nostalgic 1990s film, shot on 35mm Kodak Portra, soft grain, dreamy blur, warm highlights.
推荐模型： Seedance 2.0
先用 GPT-Image-2 出 12 格网格(单图、无边框),再让 Seedance "严格按 image1 走"。
Ultra-realistic cinematic 15-second vertical video (9:16), 4K, dark rustic wooden table, soft dramatic lighting, shallow depth of field. [0-2s] top-down: hands touch a bowl. [2-5s] side close: slow-motion pour. [5-8s] macro: sizzling sear. [8-11s] 45° angle: plating and garnish. [11-14s] close-up: a steam-rising finished dish. [14-15s] frontal hero hold. Smooth motivated camera moves between beats.
推荐模型： Seedance 2.0, Kling
带时间码的镜头表([0-2s]…[14-15s])能精确控节奏——Seedance 做广告最强的技巧。
Smooth app UI transition animation from image1: a finger taps a button, the screen slides to the next page with a natural ease, cards animate in with subtle spring, clean modern interface motion, soft shadow under the tap, no jitter, 3 seconds.
推荐模型： Seedance 2.0, Kling
把 GPT-Image-2 的 UI 稿当 image1 喂入;描述交互(点按→滑动)才有可信的界面动效。
Animate this comic page (image1) as a cinematic sequence. Follow panel order top-left to bottom-right, give each panel a subtle parallax and a motivated camera move, smooth transitions between panels, maintain exact character consistency, add gentle ambient motion (hair, dust, light), cinematic grade, hold each beat ~1.5s.
推荐模型： Seedance 2.0
视差 + 逐格运镜,把静态漫画变成动态漫画,又不破坏角色一致性。
Japanese full-color anime, fast cuts, high frame count, 24fps, dark-fantasy anime opening style. Epic battle between the protagonist and massive supernatural creatures, dynamic camera whip-pans, speed lines, impact frames and bloom, only the named hero appears, driving rhythmic pacing synced to an OP beat, 6 seconds.
推荐模型： Seedance 2.0
要 OP 的爆发感,写"快切 + 高帧 + 冲击帧",并限定出场角色以保持一致。
From the four-panel casting board (image1), generate a 15-second audition reel: [0-3.5s] actor 1, [3.5-7s] actor 2, [7-10.5s] actor 3, [10.5-14s] actor 4 — each in matching wardrobe and lighting delivering the same line straight to camera; [14-15s] return to the full four-up board. Consistent grade and framing, subtle handheld energy.
推荐模型： Seedance 2.0
先用 GPT-Image-2 出四宫格选角板,再给每位演员分配时间码,得到整齐的对比试镜片。
An anime action still in the visual style of MAPPA's Jujutsu Kaisen (2020 TV anime). Landscape 16:9. A silver-white-haired young man in a dark navy school-uniform jacket, a blue blindfold across his eyes, in a mid-fight stance — one palm extended outward releasing a swirling dense-blue energy sphere with lightning-like crackles around its edge. Opposite him, a demonic shadow creature made of liquid black mass with multiple eyes lunges from the right. Backdrop: ruined urban street at dusk, shattered asphalt, cracked neon kanji sign "呪術" in split red LED, destroyed vehicles, rubble suspended mid-air by the shockwave, rain particles caught mid-flight. Art direction: MAPPA-style digital 2D animation — heavy cel shading, crisp line-art, rim-light on both figures, motion-blur streaks around the energy sphere. Palette of deep navy, electric cyan, crimson splashes.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
A shōnen anime battle key-visual in the visual style of Studio Pierrot's Naruto Shippuden. Landscape 16:9. Two ninja figures clash mid-air at the exact instant their signature jutsu collide — a glowing blue spiral of swirling chakra on the left fighter's right palm, a crackling white lightning blade on the right fighter's right palm. The collision point sends a circular shockwave outward. Both fighters wear hitai-ate forehead protectors, jounin-style tactical vests with scroll pouches, ninja sandals. Left: spiky blond hair, whisker cheek marks, focused snarl, blue eyes.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
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 mega
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
Create a cyberpunk character-and-city design board in a premium magazine-layout format, landscape 16:9. Title text: "NEON ORCHID DISTRICT". The board is divided into five asymmetric panels: one large cinematic street scene of a rain-soaked elevated night market, two close-up portrait panels of original adult cyberpunk couriers with glowing orchid tattoos, one small isometric map panel showing alleys and drone routes, and one artifact panel showing encrypted transit passes, cybernetic gloves, and vending-machine stickers. Use layered neon magenta, cyan, acid green, wet asphalt reflections, holographic signage, dense but readable composition, editorial margins, small labels, and a cohesive retro-future anime/cyberpunk style. Original characters only, no existing IP, no explicit content.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
Design a 3:4 vertical poster for a new Chinese trendy tea launch. Use a New Chinese visual style that feels light-luxury and restrained. The palette should be dark green, off-white, and gold, with rice-paper texture, elegant negative space, landscape accents, and modern layout design. Main subject: a visually appealing cold-brew tea with tea leaves, citrus, ice cubes, and touches of gold foil. The poster must accurately display the following exact Chinese copy: "山川茶事" / "山柚观音" / "冷泡系列" / "新品上市" "一口清醒，半城入夏" / "限定尝鲜价" "中杯 16 元" / "大杯 19 元" "门店活动" / "第二杯半价" / "加 3 元升级轻乳版" / "每日前 100 名赠限定杯套" "推荐风味" / "观音茶底 / 西柚果香 / 轻乳云顶 / 冰感回甘" "活动时间 4月20日 至 5月10日" / "扫码点单" / "SHANCHUAN TEA" Fine print: "图片仅供参考，请以门店实际售卖为准" Maintain a clear promotional hierarchy while keeping the overall feeling sophisticated rather than cheap or overly e-commerce-like.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
Generate a 1980s propaganda poster. Use the exact slogan "热烈庆祝GPT-Image-2全量开放". Include Sam Altman, Dario Amodei, and Elon Musk, and give Dario Amodei a red scarf.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
Create a landscape editorial illustration in layered paper-cut style: a tiny forest night market hidden beneath giant mushrooms and fern leaves. Include warm lantern stalls selling acorn cakes, beetle taxis, a fox calligrapher, a badger tea vendor, children holding leaf umbrellas, and fireflies forming soft dotted paths. Style anchor: mid-century children’s book illustration meets contemporary layered paper diorama, visible cut-paper edges, soft shadows between layers, muted moss green, pumpkin orange, cream, and ink-blue palette. First glance: a cozy glowing market silhouette. Second glance: many small vendor stories. Third glance: handmade paper texture, tiny signage, and playful animal gestures. No photorealism, no 3D plastic look, no cluttered unreadable faces.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
Dreamy watercolor illustration of a young woman in a cream linen dress sitting on a weathered stone bench, contemplating a lily pond at late golden hour. Impressionist-light aesthetic, loose confident brush strokes, translucent washes in muted teal and warm ochre tones with soft lavender shadows. Soft blur of water lilies and reflected clouds in the pond surface. Gentle sunlight filters through overhanging willow branches. Cold-pressed paper texture visible throughout, edges of wet-on-wet bleeds, delicate lighting, clean composition with generous negative space, minimalist focus on mood, sense of calm, lightness, and ephemeral beauty. Editorial high-quality illustration, in the tradition of Turner's watercolor studies and modern editorial magazine illustration.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
A detailed isometric 3D miniature scene of a two-block cafe district, clean geometric forms, precise 30° isometric perspective alignment. A corner cafe with outdoor umbrella seating, a bookstore next door with stacks of books visible through the window, a bakery with a window display of pastries, a bicycle parked at the curb, a small fountain in a mini-plaza, planter boxes with tiny trees, a food cart on the corner selling coffee, stylised miniature pedestrians in various poses, tiled roof tops with ventilation details. Soft ambient lighting from upper-left, no harsh shadows, pastel-plus-muted palette (terracotta rooftops, cream walls, sage greens, dusty blue accents), slight atmospheric haze, subtle ambient occlusion in corners, high-detail miniature texturing. Professional rendering quality, suitable for editorial or marketing materials.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
Create a vibrant isometric fantasy village map with a clean grid-based layout using 3x3 meter tiles. Include wooden houses with thatched roofs, cobblestone paths, and a central stone fountain. One corner of the map rises into a small grassy hill about 2 meters high with stairs connecting to the lower ground. Keep the isometric angle precise and game-ready. Warm sunlight sends clear rays and long shadows across the rooftops. Make the scene readable like a handcrafted strategy-game map, with crisp tile logic, charming environmental detail, and rich but controlled color.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
Assemble the dieline into a flawless 3D box with accurate panels, clean folds, undistorted type, and artwork preserved exactly. Shoot it upright at a refined three-quarter angle in a minimal premium studio setting with a soft neutral background, diffused light, subtle shadows, no props, true colours, matte paperboard texture, and realistic editorial detail. The box front reads "AURAE / COLD-BREW MATCHA / 12 fl oz" in clean sans-serif. Side panel shows small ingredient list in 8pt type, nutrition-facts-style block. Clean, editorial, award-winning packshot aesthetic.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
/* PRODUCT_RENDER_CONFIG: Chocolate Wafer Hazelnut Edition
VERSION: 2.0.1
AESTHETIC: Premium Commercial Food Photography */
{
"ENVIRONMENT": {
"Background": "Gradient(Dark_Warm_Brown)",
"Atmospheric_FX": ["Floating_Particles", "Depth_Blur", "Cinematic_Bokeh"],
"Lighting": { "Type": "Directional_Studio_Warmer", "Highlights": "Specular_Glossy_Reflections", "Shadow_Softness": "High" }
},
"CORE_ASSETS": {
"Primary_Subject": "Wafer_Rolls",
"Physics": "Zero_Gravity_Diagonal_X_Composition",
"Material_Properties": {
"Outer": "Milk_Chocolate_Coating",
"Surface_Texture": "Irregular_Nut_Clusters_Embedded",
"Interior_Cross_Section": { "Structure": "Crispy_Hollow_Wafer", "Core": "Silky_Chocolate_Cream_Filling" }
}
},
"PARTICLE_SYSTEMS": [
{ "Object": "Chocolate_Blocks", "Detail": "Rectangular_Embossed_Letter_B", "State": "Floating" },推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
Create a completely RAW quality, unprocessed, unedited image with full iPhone camera quality. A subway station in USA, a momentary blur. The subway is in motion. In front of the subway, there is an elderly woman and man.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
Amateur photo of an open notebook lying flat, filled with handwritten notes in black ballpoint pen. The handwriting is casual and slightly messy, like personal notes, natural imperfections, crossed out words, underlined headings. Shot from slightly above, natural daylight from a window, no flash. Casual desk setting, shot on iPhone
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
"Song Dynasty People's Moments"/"SONG DYNASTY SOCIAL MEDIA FEED", Ancient and modern time-travel humor fusion interface design style, The image simulates a mobile phone social media interface, but the content is entirely Song Dynasty scenes, The avatar is a portrait of a Song Dynasty literati, Username "Su Dongpo SuShi_Official", Post content "Just arrived in Huangzhou, demoted but feeling okay. Made Dongpo pork myself today, tastes amazing, recipe attached:", The attached image is a close-up of Dongpo pork in Gongbi painting style, Likes list "Huang Tingjian, Qin Guan, Fo Yin etc.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
Please automatically generate a "museum catalog-style Chinese disassembly infographic" based on the [Subject]. The entire image is required to combine a realistic main visual, structural disassembly, Chinese annotations, material descriptions, pattern meanings, color meanings, and core feature summaries. You need to automatically determine the most appropriate main subject, clothing system, artifact structure, era style, key components, material craftsmanship, color scheme, and layout structure based on the [Subject], and the user does not need to provide any other information. The overall style should be: national museum exhibition boards, historical clothing catalogs, and cultural/museum thematic infographics, rather than ordinary posters, ancient-style portraits, e-commerce detail pages, or anime illustrations.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
Create a Nature Medicine / Science Translational Medicine style research paper figure, landscape 3:2 (1536×1024), soft literature-science palette, minimal and elegant. Figure title: "Patient cohort and multimodal biomarker workflow". Layout: a clean 4-panel academic figure labeled A–D with small bold panel letters. A. CONSORT-style patient cohort flow diagram: "Screened n=1,248" → "Eligible n=612" → branch into "Training cohort n=428" and "External validation n=184". Include exclusion side boxes: "missing imaging n=81", "insufficient follow-up n=43", "quality-control fail n=32". B. Multimodal sample-processing flow: icons for "CT imaging", "blood proteomics", "EHR timeline", "outcome labels" flowing into a pale-blue fusion box "feature harmonization". C.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
Create a polished Nature / Cell style biomedical research figure, landscape 3:2 (1536×1024), soft minimal palette, publication-ready. Figure title: "Single-cell immune atlas reveals treatment-response states". Layout: 4-panel figure labeled A–D. A. Large UMAP scatter plot with 8 softly colored immune clusters; labels: "CD8 T", "CD4 T", "B cells", "NK", "Mono", "DC", "Treg", "Plasma". Use pastel teal, sage, lavender, peach, slate, amber. B. Dot plot of marker genes with rows "GZMB", "IFNG", "CXCL13", "MS4A1", "LYZ", "FOXP3" and columns matching immune clusters; dot size = fraction, color = expression. C. Small stacked bar chart comparing "Responder" vs "Non-responder" cell-state proportions, with 5 muted segments and a tidy legend. D.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
Full-body lookbook photography of a model standing in the center of a rain-slicked Shibuya crossing at twilight. The model wears an oversized, multi-pocketed technical puffer jacket in 'Electric Cobalt' with reflective silver detailing, paired with wide-leg cargo trousers in matte black and chunky platform sneakers. The composition is a sharp medium-wide shot using a 35mm lens, capturing the vibrant neon signs of the background blurred into a soft bokeh of pinks and cyans. Lighting is dramatic and directional, sourced from the surrounding digital billboards, creating high-contrast highlights on the jacket's texture. The mood is urban and fast-paced, with a subtle film grain characteristic of Portra 400. The image features a clean vertical layout suitable for a fashion magazine, with the text 'NEO-URBAN' subtly embossed in the corner in a minimalist sans-serif font.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。
High-angle editorial photograph of a haute couture runway show set within a brutalist concrete cathedral. The model is draped in a sculptural gown made of pleated iridescent organza that mimics the fluid movement of liquid mercury. The color palette is dominated by 'Champagne Gold' and 'Shadow Grey'. Lighting is a single, powerful overhead spotlight that creates sharp, dramatic shadows and emphasizes the architectural volume of the garment. The model has a minimalist, ethereal makeup look with silver leaf accents on the brow. The camera uses a 50mm prime lens with a deep depth of field to capture both the intricate texture of the fabric and the cold, vast scale of the concrete architecture in the background. The atmosphere is solemn, artistic, and high-fashion, focusing on the intersection of textile and space.
推荐模型： gpt-image-2, Nano Banana Pro, FLUX.1
选自开源 image-prompt-library(CC BY 4.0)。