SuperAPI AI 工具集

video-prompting-guide

设计与创作

查看项目

更新于 10-16 06:56

技能介绍

Video Prompting Guide

面向 AI 视频生成的提示词编写指南,汇总有效提示词的最佳实践与技巧。覆盖 Veo、Seedance、Wan、Grok、Kling、Runway、Pika、Sora 等模型的提示方法。

快速开始

需要 inference.sh CLI(belt),安装方式:

npx skills add belt-sh/cli

随后登录:

belt login

一个结构良好的视频提示词示例:

belt app run google/veo-3-1-fast --input '{
"prompt": "Cinematic tracking shot of a red sports car driving through Tokyo at night, neon lights reflecting on wet streets, rain falling, 4K, shallow depth of field"
}'

提示词结构公式

[Shot Type] + [Subject] + [Action] + [Setting] + [Lighting] + [Style] + [Technical]

示例拆解:

"Slow motion close-up of coffee being poured into a white ceramic cup, steam rising, morning sunlight streaming through window, warm color grading, cinematic, 4K, shallow depth of field"

  • Shot Type:Slow motion close-up
  • Subject:Coffee
  • Action:Being poured
  • Setting:White ceramic cup, window
  • Lighting:Morning sunlight
  • Style:Warm color grading, cinematic
  • Technical:4K, shallow depth of field

镜头类型

镜头类型 说明 适用
Wide shot 展示整个场景 建立地点
Medium shot 腰部以上取景 对话、动作
Close-up 面部或细节 情绪、产品细节
Extreme close-up 单一特征 戏剧性、质感
Aerial shot 鸟瞰视角 风景、规模
Low angle 相机向上看 力量、宏伟
High angle 相机向下看 脆弱感
Dutch angle 倾斜相机 不安、紧张
POV shot 第一人称视角 沉浸感

运镜方式

运镜 说明 效果
Tracking shot 相机跟随主体 动态、引人入胜
Dolly in/out 相机推近/拉远 聚焦、揭示
Pan 水平旋转 环视场景
Tilt 垂直旋转 展现高度
Crane shot 垂直+水平 戏剧性揭示
Handheld 轻微晃动 真实感、紧迫感
Steadicam 平稳跟随 专业、电影感
Zoom 镜头变焦 快速切换焦点
Static 无运动 沉思、稳定

光线关键词

关键词 效果
Golden hour 温暖、柔和、浪漫
Blue hour 冷调、情绪化、暮色
High key 明亮、阴影少
Low key 暗调、戏剧性阴影
Rim lighting 主体被光勾勒轮廓
Backlit 光从主体后方来
Soft lighting 柔和、讨喜
Hard lighting 锐利阴影、强对比
Neon 色彩丰富、都市、赛博朋克
Natural lighting 真实、纪录片感

风格关键词

电影风格

cinematic, film grain, anamorphic lens, letterbox, shallow depth of field, bokeh, 35mm film, color grading, theatrical

视觉美学

minimalist, maximalist, vintage, retro, futuristic, cyberpunk, steampunk, noir, pastel, vibrant, muted colors, high contrast, desaturated

质量关键词

4K, 8K, high resolution, photorealistic, hyperrealistic, ultra detailed, professional, broadcast quality, HDR

按用例分类的提示词示例

产品演示

belt app run google/veo-3-1-fast --input '{
  "prompt": "Smooth tracking shot around a sleek smartphone on a white pedestal, soft studio lighting, product photography style, reflections on surface, 4K, shallow depth of field"
}'

自然纪录片

belt app run google/veo-3-1 --input '{
  "prompt": "Slow motion extreme close-up of a hummingbird hovering at a red flower, wings in motion blur, shallow depth of field, golden hour lighting, National Geographic style"
}'

都市生活

belt app run google/veo-3 --input '{
  "prompt": "Tracking shot following a cyclist through busy city streets, morning rush hour, natural lighting, handheld camera feel, documentary style, authentic and candid"
}'

美食内容

belt app run bytedance/seedance-2-0 --input '{
  "prompt": "Close-up of chocolate sauce being drizzled over ice cream, slow motion, steam rising, soft lighting, food photography style, appetizing, commercial quality",
  "generate_audio": true
}'

科技/未来感

belt app run xai/grok-imagine-video --input '{
  "prompt": "Futuristic control room with holographic displays, camera slowly pans across the space, blue and cyan lighting, sci-fi atmosphere, Blade Runner aesthetic, 4K",
  "duration": 5
}'

常见错误

错误 问题 更好的做法
Too vague "A nice video" 明确镜头、主体、风格
Too complex 多个场景 每个提示词一个场景
No motion 静态描述 加入运镜或动作
Conflicting styles "Minimalist maximalist" 选择一种美学
No lighting 氛围不明确 指定光线条件

各模型专属提示

  • Google Veo:擅长真实、电影感内容;支持音频生成(Veo 3+);适合详细、专业的提示词;3.1 支持帧插值。
  • Seedance:擅长舞蹈和人体动作;支持首帧控制;适合一致的角色运动;配合参考图效果好。
  • Wan 2.5:最适合图生视频;可自然动画化静态图像;运动预测良好;适配任意图像风格。
  • Grok:通用视频能力良好;时长可配置(5–10 秒);创意解读;适合抽象概念。

工作流:迭代式提示

# 1. 从基础提示词开始
belt app run google/veo-3-1-fast --input '{
  "prompt": "A woman walking through a forest"
}'

# 2. 增加具体性
belt app run google/veo-3-1-fast --input '{
  "prompt": "Medium tracking shot of a woman in a red dress walking through an autumn forest"
}'

# 3. 加入风格与技术细节
belt app run google/veo-3-1-fast --input '{
  "prompt": "Cinematic medium tracking shot of a woman in a flowing red dress walking through an autumn forest, golden hour sunlight filtering through leaves, shallow depth of field, film grain, 4K"
}'

相关技能

# 生成视频
npx skills add inference-sh/skills@ai-video-generation

# Google Veo 专用
npx skills add inference-sh/skills@google-veo

# 为图生视频生成图片
npx skills add inference-sh/skills@ai-image-generation

# 通用提示工程
npx skills add inference-sh/skills@prompt-engineering

# 完整平台技能
npx skills add inference-sh/skills@infsh-cli

浏览全部视频应用:

belt app list --category video

文档

  • Running Apps - How to run apps via CLI
  • Video Generation Guide - Comprehensive video guide