Vorapix

每周更新 · 免费复制

提示词库,
每一条都配成品图

图片与视频提示词收集自发布它们的创作者,每张卡片都标注跑出样张所用的工具。复制文字,或者直接送进面板生成。

库里共 478 条

GPT Image 2 MS Paint Drawing Prompt — AI image prompt sample
Low-quality disposable camera high school snapshot prompt — AI image prompt sample
Train Photography Game Simulation — AI image prompt sample
3×3 cinematic storyboard contact sheet from one input image — AI image prompt sample
Convert Image to Editable PowerPoint Slide Prompt — AI image prompt sample
Fantasy Whimsical Downtown Aerial View — AI image prompt sample
Albedo Cosplay Instagram Story — AI image prompt sample
Software UI Desktop Screenshot — AI image prompt sample

按合集浏览

共 478 条,每个合集独立一页。

GPT Image 2 MS Paint 绘画提示词

Redraw the attached image in the most clumsy, scribbly, and utterly pathetic way possible. Use a white background, and make it look like it was drawn in MS Paint with a mouse. It should be vaguely similar but also not really, kind of matching but also off in a confusing, awkward way, with that low-quality pixel-by-pixel feel that really emphasizes how ridiculously bad it is. Actually, you know what, whatever, just draw it however you want.

CHOI

3×3 电影分镜故事板,源自一张输入图像

分析输入图像的整个构图。识别所有存在的关键主体(无论是单人、群体/情侣、车辆还是特定物体)及其空间关系/互动。 生成一个连贯的 3x3 网格“电影印样(Contact Sheet)”,展示在同一环境中完全是这些主体的 9 个不同镜头。 你必须调整标准的电影镜头类型以适应内容(例如,如果是群体,保持群体在一起;如果是物体,构图包含整个物体): 第 1 行(建立背景): 大远景 (ELS): 主体在广阔的环境中显得很小。 全景 (LS): 完整的主体或群体从上到下可见(从头到脚 / 从车轮到车顶)。 中远景 (美式镜头/四分之三): 构图从膝盖以上(针对人物)或 3/4 视角(针对物体)。 第 2 行(核心覆盖): 4. 中景 (MS): 构图从腰部以上(或物体的中心核心)。聚焦于互动/动作。 5. 中特写 (MCU): 构图从胸部以上。主要主体的亲密构图。 6. 特写 (CU): 紧凑构图于脸部或物体的“正面”。 第 3 行(细节与角度): 7. 大特写 (ECU): 强烈聚焦于关键特征(眼睛、手、标志、纹理)的微距细节。 8. 低角度镜头 (仰视/虫眼): 从地面仰望主体(壮观/英雄感)。 9. 高角度镜头 (俯视/鸟瞰): 从上方俯瞰主体。 确保严格的一致性:所有 9 个面板中是相同的人物/物体、相同的衣服和相同的光照。景深应逼真地变化(特写镜头中的背景虚化)。 一个包含 9 个面板的专业 3x3 电影故事板网格。 该网格以全面的焦距范围展示输入图像中的特定主体/场景。 顶行: 宽广环境镜头,全视图,3/4 剪辑(膝上景)。 中间行: 腰部以上视图,胸部以上视图,脸部/正面特写。 底行: 微距细节,低角度,高角度。 所有帧均具有照片般逼真的纹理,一致的电影级调色,以及针对所分析的主体或物体特定数量的正确构图。

松果先森

日本 NEWT 旅行 App 广告

Goal: Create a vibrant Japanese travel-app advertising poster for NEWT, combining editorial travel photography, clean app UI mockups, and bold Japanese typography to promote the feeling that the next trip is already beginning. Canvas: Square 1:1 promotional graphic, bright white and mint-green background, high-key summer lighting, energetic composition, polished commercial ad quality. Layout: A large diagonal Japanese headline dominates the top-left and upper center. The main traveler stands large in the center foreground, smiling and looking up to the right while holding a smartphone showing the green brand screen. A second traveler appears behind her on the left inside an airport scene. Layer multiple travel photo cutouts around the lower half and right side, with floating app interface cards over them. Place a large green rounded brand block on the upper-right. Text content: Use exactly 5 main text groups: 1) huge headline text 次の旅が、もう始まってる。 in vivid green, with the first line filled and the second line outlined; 2) small upper-right Japanese copy 航空券も、ホテルも、アプリひとつで軽やかに。; 3) English tagline “TRAVEL FEELS NEW.” near the top-right; 4) left-side vertical category list with exactly 5 items: “AIRPORT”, “HOTEL”, “CITY”, “BEACH”, “FOOD”; 5) brand block text with a white animal-like logo, the word “NEWT”, and the small Japanese call-to-action “NEWTで旅をみる” with a circular arrow icon. Subject details: Main subject is a cheerful young East Asian woman traveler, mid-20s, short dark bob hair moving naturally, gold hoop earrings, green ribbed top, loose translucent mint-and-white striped overshirt, cream high-waisted pants, woven straw shoulder bag with a small green charm, pulling a dark green rolling suitcase. She holds a phone with a green screen, white brand logo, and “NEWT” text. Secondary subject is a smiling young East Asian woman in an orange cardigan at an airport, holding a drink, with a departures board behind her. Travel image collage: Include exactly 5 travel photo cutouts: 1) bright airport terminal with departures board behind the secondary woman, 2) luxury hotel room with ocean view, 3) close-up seafood dish with shrimp and greens near the suitcase, 4) turquoise beach and ocean with swimmers on the right, 5) colorful resort city street with palm trees along the bottom-right. App UI cards: Include exactly 2 floating white app interface cards with rounded corners and soft shadows. Card 1 is a booking search card at mid-right with tabs for flight, hotel, and package; large destination text “ソウル”, small text “SEOUL, KOREA”, rows showing round trip, dates “6月20日(金) - 6月23日(月)”, passengers “大人1名、エコノミー”, and a green button labeled “検索する”. Card 2 is a hotel recommendation card lower-right with a pool thumbnail, small heart icon, hotel name “NEWT SEOUL 明洞”, rating “4.8”, and five yellow stars. Visual style: Premium Japanese startup travel campaign, fresh mint green brand color, crisp cutout collage, clean sans-serif typography, dynamic diagonal composition, airy negative space, glossy magazine-ad finish, realistic photography mixed with minimal vector UI. Add a dotted flight path with a location pin near the top-right. Constraints: Use no extra logos or watermarks beyond the specified brand. Keep all Japanese text legible and accurately placed. Maintain the strong green-and-white identity, optimistic summer travel mood, and layered depth.

Takaya Shinozuka / CEO of Reiwa Travel

加拿大公民卡样机

Ultra-realistic 16:9 close-up scan of a Canadian citizenship card placed on a clean light grey/white background. The card is horizontally aligned, centered in frame, captured in sharp focus with studio lighting. Design features a modern government-issued ID layout with bilingual English and French text. Top-left includes the Canadian flag with a red maple leaf. Header text reads “CANADA – CANADIAN CITIZENSHIP CARD / CARTE DE CITOYENNETÉ CANADIENNE.” The card includes a passport-style portrait of a young woman: medium-length dark brown hair, center-parted, natural makeup, warm skin tone, neutral expression, direct gaze, subtle freckles, wearing minimal jewelry and a dark top. Personal details section includes: – Surname: MARTIN – Given names: ÉMILIE SOPHIE – Citizenship number: 1234-5678 – Date of birth: 14 APR 1996 – Place of birth: MONTRÉAL, QC, CANADA – Issue date: 20 MAY 2024 – Expiry date: 20 MAY 2034 Background design includes intricate guilloche patterns, microprinting, and soft pastel gradients. A large holographic maple leaf occupies the right side with iridescent rainbow reflections. Additional elements: – Government of Canada emblem in top-right – Embedded hologram square with maple leaf security seal – Fine-line engraving patterns across the surface – Signature at bottom right (“Émilie S. Martin”) Lighting is soft and even, highlighting laminated plastic texture, subtle reflections, and security overlays. No hand visible. Clean, minimal, professional composition. Photorealistic, high detail, 8K quality.

ANKIT PATEL 🇮🇳 | AI

Photorealistic Dual Gym Mirror Selfie Prompt

{ "prompt_type": "photorealistic gym mirror selfie", "main_composition": "mirror selfie of two athletic young women standing side by side with backs to the camera in a dimly lit modern gym, confidently posing with hands on hips and slight arch to emphasize curves, full reflections visible in large mirror showing their front sides and subtle expressions, vibrant colorful workout outfits contrasting moody blue/purple ambient lighting, professional fitness studio with equipment blurred in background", "subject_1_left": { "description": "beautiful young woman in her early 20s, fit curvy athletic build with toned glutes and legs, long wavy light brown or blonde pigtails hair styled in high ponytail with loose strands, fair tanned smooth skin with healthy glow", "clothing": "bright pink long-sleeve crop top with thumb holes and subtle sheen, matching high-waisted seamless short scrunch-butt pink leggings with 'DFYNE' logo on waistband, white athletic socks", "details": "confident pose with hand on hip and slight smile visible in mirror reflection, hair naturally tousled, relaxed athletic stance" }, "subject_2_right": { "description": "beautiful young woman in her early 20s, fit curvy athletic build with toned glutes and legs, long wavy darker brown hair in loose ponytail or braids, fair tanned smooth skin with healthy glow", "clothing": "light yellow halter-style sports bra with thin straps, matching high-waisted seamless short scrunch-butt pink leggings, white athletic socks", "details": "playful confident pose with hand on hip and subtle expression in mirror reflection, hair with natural volume" }, "environment": { "foreground": "dark rubberized gym floor with subtle texture", "midground": "large wall mirror reflecting both women fully and gym interior", "background": "modern gym with dim blue/purple ambient lighting, blurred cardio machines and weight equipment, exposed ceiling ducts and pipes, clean spacious professional fitness center atmosphere" }, "lighting_and_atmosphere": "dim moody indoor gym lighting with cool blue/purple neon accents and overhead spots, subtle highlights on skin, hair, and shiny leggings fabric creating vibrant color pops, energetic confident workout vibe with high contrast between bright outfits and dark surroundings, photorealistic detail", "technical_quality": "highly detailed, sharp focus on subjects with realistic seamless fabric textures (scrunch-butt shine, crop top stretch), skin glow, hair movement, and mirror reflections, 8k resolution, professional mirror selfie photography style with slight wide-angle lens effect and natural depth of field softly blurring background equipment", "negative_prompt_suggestions": "blurry, deformed, extra limbs, phone screen visible, mirror distortion or misalignment, overexposed neon lights, underexposed faces, low quality, cartoon, anime, text watermark, extra pe"

KeorUnreal

一座能按三条路径浏览的提示词库

这里不是那种要一直往下翻、指望刷到能用的一大段文字。每条提示词同时归到三条轴线上——用途是什么、长什么样、画面里有什么——所以像「复古风格的竖版美食照」这种需求,一两次点击就能找到。用途一栏在图片这边覆盖产品摄影、海报设计、社媒缩略图,在视频这边覆盖电影感镜头、Vlog、短片和广告片。风格从照片级真实一路延伸到动漫、3D、定格动画和复古风。主体则按画面里实际出现的东西分类:人物、产品、食物、建筑、动物、文字排版。在这三条轴线之上,库里还按模型品牌分组——Nano Banana、GPT Image、Seedance——并把图片和视频分开,这样你也可以从看到成品的那个工具出发去找,而不必先想清楚要做什么。整个合集大约三分之二是图片,其余是视频。每张卡片都展示它对应提示词跑出来的成品,并署名发布者,这座 ai 提示词库里的每一条都免费复制,不管你会不会在这里实际跑一次。

关于这座库的常见问题

怎么分类、从哪来、浏览要不要钱。

这座提示词库是怎么组织的?

三条轴线加两种分组。用途、风格、主体各自有一套独立的合集页面,在此之上,全部内容还按模型品牌分组,并分成图片和视频两类。单条提示词往往同时落在好几个分类里,所以通常不止一条路径能找到它。

这些提示词是从哪来的?

几乎全部采集自公开发布的帖子,逐字展示,并附上回链到原作者的链接。不做改写也不做润色,因为真正起作用的就是那份原始措辞。如果某条是我们自己写的,卡片上会注明,并列出实际跑出来花了多少积分。

示例图片和片段是 Vorapix 做的吗?

不是,每张卡片上的徽章正是为了把这件事说清楚——它标注的是创作者当时用的第三方工具。Vorapix 提供的是「直接生成」按钮背后的工作台,用的模型不一定和徽章上的一样。把示例当作「这段措辞管用」的证据来看,而不是你自己生成结果的预览。

浏览需要账户吗?

不需要。阅读、筛选、复制对所有人开放——提示词免费、无需登录、复制次数不限。只有生成才需要账户,因为生成要花积分。注册即送 10 积分,够先试几条再决定。

这里多久会更新一批新内容?

每周一批。一条提示词要等样张、来源链接和工具徽章都核实过才会上线,所以总数是一批一批往上跳,而不是连续增长。社区最活跃的那几个模型品牌,往往在每批之间涨得最快。

相关合集

Vorapix

浏览免费,复制也免费。