
Picva
提示词库
搜索、筛选并复用适配多种 AI 图片模型的高质量提示词
提示词结果 20 个结果
搜索: 图片
全部模型
最新


真人和风格对照直出
创建图片 {\n"title": "真人 × 动画对照创意作品",\n"author": "ZH4O",\n"description": "一张利用垂直拼贴与留白,将同一人物的照片与插画并置的创意作品,突出媒介在语言、质感与情绪上的对比。",\n"layout": {\n"orientation": "vertical",\n"photo": {\n"position": "top-left",\n"aspect_ratio": "3:4",\n"style": "street photo",\n"camera_angle": "eye-level, slightly tilted left",\n"lens": "mild wide-angle",\n"background_elements": ["road", "store signs", "urban perspective lines"]\n},\n"illustration": {\n"position": "bottom-right",\n"scale": "slightly larger",\n"composition"

Nano Banana Pro新玩法:图片加酷炫涂鸦
Fun new prompt for Nano Banana Pro: Take a photo and ask to "add cool scribbles" - on either the entire image or one object. I used it to level up my Gemini 3 merch 😎 https://t.co/Z946AJhsX1

产品图营销广告制作指南
如何将产品图生成营销广告 1. 准备产品图片 2. 准备产品的卖点,或者让 AI 自己生成 3. 与提示词一起提交给Nano banana. 🍌 Nano banana Pro: Commercial photography, scientific knolling infographic style. **CENTER ANCHOR:** A bottle of "MegaRed Advanced CoQ10 200mg" supplement, with its signature red cap, yellow and red gradient label, and bold white "MegaRed" and "CoQ10" text, is placed on a polished, glowing amber and gold pedestal. **INGREDIENT ORBIT:** Surrounding the central bottle are four distinct, meticulously arranged clusters: 1. **Top

钢笔画风格转换
将上传的图片变成钢笔画风格。 🍌 Nano bannana Pro prompt: { "prompt_template": "A detailed ink drawing based on [insert image reference here], isolating the main subject. Rendered in a traditional micron pen sketchbook style. Shading, texture, and patterns are achieved exclusively through dense cross-hatching and fine line work, using high contrast black ink on textured white paper. The subject is centered with vast negative space, completely removing the original photo\'s background." }

生成漂亮的3D激光内雕水晶
生成漂亮的3D激光内雕水晶 1. 可以直接指定主题 2. 也可以通过上传图片作为附件,让其提炼图片中的元素。 🍌 Nano Banana Pro prompt: My Subject: 主题名称 图片比例:9:16 # Role Definition: You are an expert product photographer and creative art director specializing in high-end luxury goods. Your sole task is to generate a photorealistic image of a custom 3D subsurface laser-engraved crystal ornament based on a simple subject provided by the user. # Core Directive: The user will provide only the [Subject]. You must autonomously analyze this subject to det

9格摄影作品
9格图片又来了 Nano banana pro提示词: **[Type]:** A scanned page from a high-end Japanese photobook (Shashin-shu). **A 9-grid photo layout printed on textured matte art paper.** **[Layout Design]:** The 9 photos are arranged in a clean grid with **wide white margins** at the bottom to accommodate typography. **[Subject Consistency - STRICT]:** * **Source:** Based strictly on the uploaded reference image. **[SAME CHARACTER IN ALL PANELS]**. * **Styling Strategy:** **[RANDOMLY SELECT ONE]:** 1. **{Classic}:

一个全新的Instagram账号
Generate a 9-image ‘photo dump’ grid of this person’s weekend: a mirror selfie, a café shot, friends at dinner, a blurry party photo, a walking shot, a laptop/coffee work shot, a pet moment, a sunset, and a candid laugh. 生成一个包含 9 张图片的‘照片合集’,展现这个人周末的点点滴滴:一张镜子自拍、一张咖啡馆照片、与朋友共进晚餐的照片、一张模糊的派对照片、一张步行照片、一张笔记本电脑/咖啡工作照片、一张宠物照片、一张日落照片和一张抓拍的笑声。

纳米香蕉Pro - 图片上传与编辑指南
nano banana pro ①人物の写真をアップロード ②スマホに映したい画像をアップロード ③この JSON をそのまま貼る 1×3グリットで生成 { "layout": { "type": "grid_1x3" }, "global": { "edit_type": "phone_motion_edit", "source": { "mode": "EDIT", "reference_images": { "first": "base_photo_person_and_environment", "second": "screen_content_for_phone" }, "preserve_from_first": { "same_person_or_group": true, "same_faces": true, "same_hairstyles": true, "same_outfits": true, "same_environment_style": true } }, "identity": { "keep_identity_consistent": true,

抖音Cosplay角色视觉分析
之前在抖音看到一个应该是 cosplay 某个角色,不太确定这个角色叫什么但还挺惊艳的,用下面的指令反推了一下提示词。 反推指令👉将此图片的视觉样式提取为 JSON 结构化数据,包括但不止于:颜色、字体、构图、效果…… 没想到出来的效果还挺好看,你是选左边还是选右边呢?😏 提示词跟原图放评论👇 https://t.co/0f9WXiBwXx { "visual_style_analysis": { "art_direction": { "genre": "Hyper-realistic Portrait / Fantasy Cosplay", "style_category": "2.5D Semirealism (2.5D 半写实/破壁风格)", "aesthetic_core": "Douyin/TikTok Glamour (抖音/网红滤镜美学)", "mood": "Ethereal, Haughty, Romantic, Dreamy", "texture_quality": "Smooth porcelain skin vs. Sharp metallic detai

微信读书年终总结图生成过程
我今年没有用微信读书,由@LufzzLiz 的灵感结合@berryxia 的提示词用jason老师的图练手生成了微信年终总结 生成了9:16和16:9的版本,教程如下: 1、用微信读书的图,加上以下提示词 让GPT或Deepseek生成生图提示词 自己看情况做轻微修改 2、用生图提示词,使用Nano Banana Pro设定9:16和2k生图即可 提示词如下: 这些图片是我的微信读书的年终总结,我想把它们融合在一起参考下面的提示词生成一张图片,帮我填充下面提示词中方括号里面的内容,可以让我用Nano Banana pro生成图片,最终生成中文版本: Ultra-realistic professional photography of a premium transparent acrylic signage panel. The panel is suspended in mid-air by two thin metal cables from above, displayed in a [环境类型] environment. Main Subject - Transparent

复刻男友视角咖啡店照片
复刻一张男友视角的照片 在群里看到有人发的一张照片,让AI按照这个思路复刻出来提示词,AI把 主体人物,logo, 环境做成了参数; 其中logo是我没有注意到的,没想到也提取出来了。下面复刻后的照片 和提示词。 prompt: # 图片复刻元提示词 (Image Reproduction Meta-Prompt) ## 1. 角色指定 (Role) 你是一位**资深人像摄影大师 (Senior Portrait Photographer)** 和 **光影构图专家**。你擅长捕捉日常生活中的自然瞬间(Candid Moments),精通室内布光与景深控制,能够完美复刻“男友视角”的社交媒体风格照片。 ## 2. 图片结构与框架 (Structure & Frame) * **画幅比例:** 9:16 (竖屏全画幅) * **构图模式:** 近景人像 (Medium Close-up),人物占据画面前景左侧 60% 区域。 * **核心锚点:** * 前景:浅色木质圆桌边缘(切过画面左下角)。 * 中景:人物上半身,特别是面部和托腮的手臂。 * 背景:虚化的咖啡店柜台与人群。 * **

明星街拍与拼图排版大师
nano banana pro扮演狗仔抓拍,thanks @awesome_visuals for the inspiration prompt:👇 # Role: 明星街拍与拼图排版大师 (Paparazzi Collage Master) ## 1. 角色指定 你是一位顶级的时尚街拍摄影师兼视觉排版总监。你擅长捕捉名人在日常生活中的自然瞬间(Candid Moments),精通使用长焦镜头(Telephoto Lens)在户外强光下拍摄,并能将素材完美地组合成具有叙事感的九宫格拼图。你的审美风格追求:高清晰度、真实光影、自然动态、电影感。 ## 2. 图片结构与框架描述 * **整体框架**: 3x3 九宫格拼图 (9-grid collage layout)。 * **分隔线**: 黑色细边框 (Thin black borders) 分隔每个单元格。 * **长宽比**: 整体比例建议为 3:4 (Vertical)。 * **分辨率**: 8K 超高清。 * **视觉风格**: 狗仔队风格 (Paparazzi style),街头时尚 (Street Style),偷拍感

用花朵美化你的产品
A high-end editorial photo of (PRODUCT NAME OR IMAGE) placed on a white marble pedestal, resting on champagne-colored silk. It is surrounded by pastel flowers whose type and color naturally harmonize with the product’s primary colors (COLOR PALETTE) — complementing and enhancing its tones. Soft natural light from the upper left. 3D realism, luxury product photography, shallow depth of field, 1:1 format. (产品名称或图片)放置在白色大理石底座上,休息在香槟色丝绸上,的高端编辑照片。它被淡色花朵环绕,其类型和颜色自然与产品的主要颜色(调色板)协调——补充并增强其色调。来自左上方的柔和自然光

纳米香蕉Pro菜单图片添加
Nano Banana Pro can add food photos to the menu prompt: Add photos of food to this menu to each item of food Made in Adobe Firefly app https://t.co/ITvLe6aDIo

超现实几何艺术风格的数字插画
Transform this image into a digital illustration with a surreal, geometric art style. Apply glitch textures, abstract shapes, and cinematic composition. Use the original photo’s lighting and color palette to guide the atmosphere, while reimagining the scene in a stylized, dreamy, retro-futuristic way. 将这张图片转换为具有超现实几何艺术风格的数字插画。应用故障纹理、抽象形状和电影化构图。以原始照片的光线和色彩为基调来营造氛围,同时以一种风格化、梦幻且复古未来主义的方式重新构想这个场景。

文字生成精美的杂志文章的照片
Put this whole text, verbatim, into a photo of a glossy magazine article on a desk, with photos, beautiful typography design, pull quotes and brave formatting. The text: [...the unformatted article] 请将这段文字原封不动地复制到一张精美杂志文章的照片中,照片需包含图片、漂亮的排版设计、精选语录和大胆的格式。原文如下:[……未格式化的文章]

纹理化图片
Retexture the image attached based on the json below\n{\n "style": "C4D hyper-realistic 3D render",\n "object_form": "detailed mechanical design",\n "geometry": {\n "shape": "sharp edges with smooth curves",\n "scale": "real-world proportion",\n "detailing": "high-poly mesh with intricate mechanical features"\n },\n "material": {\n "base": "polished plastic and carbon fiber",\n "texture": "fine surface variation with specular maps",\n "finish": "high gloss with realistic reflections"\n },\n "des

食谱信息图制作
Create step-by-step recipe infographic for creamy garlic mushroom pasta, top-down view, minimal style on white background, ingredient photos labeled: "200g spaghetti", "150g mushrooms", "3 garlic cloves", "200ml cream", "1 tbsp olive oil", "parmesan", "parsley", dotted lines showing process steps with icons (boiling pot, sauté pan, mixing), final plated pasta shot at the bottom 奶油大蒜蘑菇意面分步食谱信息图制作要求\n呈现视角:俯视角度\n设计风格:简约风格,白色背景\n食材配图及标注:需包含“200克意大利面”“150克蘑菇”“3瓣大蒜”“200毫升淡奶油”“1汤匙橄榄油”“帕玛森奶酪”“欧芹”的图片,并分别

已加载全部提示词