Communitygithub.com

Aadi-110i/PEP-PROJECT

AI 影片生成提示詞的最佳實踐與技巧,涵蓋 Veo、Seedance、Wan、Grok、Kling、Runway、Pika、Sora 等平台的提示策略,幫助你提升影片品質、獲得一致結果並產出專業級影片提示。

PEP-PROJECT 是什麼?

這是一個專為 AI 影片生成提示詞設計的技能指南,適用於 Veo、Seedance、Wan、Grok、Kling、Runway、Pika、Sora 等多個主流平台。技能本體提供了一套完整的提示詞結構公式:[鏡頭類型] + [主體] + [動作] + [場景] + [燈光] + [風格] + [技術參數],並透過豐富的範例與分類表格(如鏡頭類型、攝影機運動、燈光關鍵詞、風格關鍵詞)幫助開發者快速建立專業級提示詞。此外,還包含了各模型的特定技巧(如 Google Veo 擅長寫實影視內容、Seedance 擅長舞蹈與人體動作、Wan 2.5 擅長圖片轉影片)以及迭代優化工作流程。開發者可透過 `belt` CLI 直接執行提示詞範例,並與相關技能(如 AI 圖片生成、提示工程)搭配使用。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Aadi-110i/PEP-PROJECT/tree/HEAD/skills/video-prompting-guide

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

預覽

來自技能 README

影片提示指南

說明文件

影片提示指南

撰寫有效 AI 影片生成提示詞的最佳實踐,來自 inference.sh。

影片提示指南

快速開始

需要 inference.sh CLI (belt)。安裝說明

belt login

# 結構良好的影片提示
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"
}'

提示結構公式

[鏡頭類型] + [主體] + [動作] + [場景] + [燈光] + [風格] + [技術參數]

範例解析

"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"
  • 鏡頭類型:慢動作特寫
  • 主體:咖啡
  • 動作:正在被倒入
  • 場景:白色陶瓷杯、窗戶
  • 燈光:早晨陽光
  • 風格:暖色調、電影感
  • 技術參數:4K、淺景深

鏡頭類型

鏡頭類型說明用途
廣角鏡頭顯示整個場景確立地點
中景鏡頭腰部以上構圖對話、動作
特寫臉部或細節情感、產品細節
極特寫單一特徵戲劇感、質感
空拍鏡頭鳥瞰視角風景、規模
低角度鏡頭向上力量、氣勢
高角度鏡頭向下脆弱感
荷蘭角度傾斜鏡頭不安、張力
主觀鏡頭第一人稱視角沉浸感

攝影機運動

運動說明效果
跟拍鏡頭攝影機跟隨主體動態、引人入勝
推軌(進/出)攝影機向主體靠近/遠離聚焦、揭示
水平搖攝水平旋轉環顧場景
垂直搖攝垂直旋轉揭示高度
起重機鏡頭垂直+水平戲劇性揭示
手持輕微晃動真實感、緊迫感
斯坦尼康平穩跟隨專業、電影感
變焦鏡頭縮放進/出快速焦點變換
靜態無運動沉思、穩定

燈光關鍵詞

關鍵詞效果
黃金時刻溫暖、柔和、浪漫
藍色時刻清冷、陰鬱、暮光
高調光明亮、陰影極少
低調光黑暗、戲劇性陰影
輪廓光主體邊緣被光勾勒
逆光光線從主體後方來
柔光柔和、討喜
硬光銳利陰影、高對比
霓虹多彩、都會、賽博龐克
自然光寫實、紀錄片風格

風格關鍵詞

電影風格

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

視覺美學

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

品質關鍵詞

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

按使用場景的提示範例

產品展示

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"
}'

自然紀錄片

belt app run google/veo-3 --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"
}'

城市生活

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"
}'

美食內容

belt app run bytedance/seedance-1-5-pro --input '{
  "prompt": "Close-up of chocolate sauce being drizzled over ice cream, slow motion, steam rising, soft lighting, food photography style, appetizing, commercial quality"
}'

科技/科幻

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
}'

常見錯誤與避免方法

錯誤問題更好做法
太過模糊「好看的影片」指定鏡頭、主體、風格
太過複雜多個場景每個提示只寫一個場景
沒有動態靜態描述加入攝影機運動或動作
風格衝突「極簡主義極繁主義」選擇一種美學
沒有燈光未定義氛圍指定光線條件

各模型專屬技巧

Google Veo

  • 擅長寫實、電影感內容
  • 支援音訊生成(Veo 3+)
  • 搭配詳細、專業的提示詞效果最佳
  • 3.1 版本提供影格插值功能

Seedance

  • 擅長舞蹈與人體動作
  • 支援首影格控制
  • 角色動作一致性良好
  • 可搭配參考圖片使用

Wan 2.5

  • 最適合圖片轉影片
  • 能自然生成靜態圖片的動畫
  • 動作預測準確
  • 可搭配任何圖片風格

Grok

  • 通用型影片生成表現良好
  • 可設定時長(5-10 秒)
  • 富有創意解讀
  • 適合抽象概念

工作流程:迭代式提示

# 1. 從基礎提示開始
belt app run google/veo-3-1-fast --input '{
  "prompt": "A woman walking through a forest"
}'

# 2. 增加具體性
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. 加入風格與技術細節
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"
}'

相關技能

# 產生影片
npx skills add inference-sh/skills@ai-video-generation

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

# 產生圖片(用於圖片轉影片)
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

瀏覽所有影片應用:belt app list --category video

文件

Individual skills in this repo

This repo contains 13 individual skills — each has its own dedicated page.

Aadi-110i/PEP-PROJECT

Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human

Aadi-110i/PEP-PROJECT

Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video

Aadi-110i/PEP-PROJECT

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse

Aadi-110i/PEP-PROJECT

ElevenLabs text-to-speech with 22+ premium voices, multilingual support, and voice tuning via inference.sh CLI. Models: eleven_multilingual_v2 (highest quality), eleven_turbo_v2_5 (low latency), eleven_flash_v2_5 (ultra-fast). Capabilities: text-to-speech, voice selection, stability/style control, 32 languages. Use for: voiceovers, audiobooks, video narration, podcasts, accessibility, IVR. Triggers: elevenlabs, eleven labs, elevenlabs tts, premium tts, professional voice, ai voice, high quality tts, multilingual tts, eleven labs voice, voice generation, natural speech, realistic voice, voice over, speech synthesis

Aadi-110i/PEP-PROJECT

Explainer video production guide: scripting, voiceover, visuals, and assembly. Covers script formulas, pacing rules, scene planning, and multi-tool pipelines. Use for: product demos, how-it-works videos, onboarding videos, social explainers. Triggers: explainer video, how to make explainer, product video, demo video, video production, video script, animated explainer, product demo video, tutorial video, onboarding video, walkthrough video, video pipeline

Aadi-110i/PEP-PROJECT

Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use each. Use for: animating images, creating video from stills, adding motion, product animations. Triggers: image to video, i2v, animate image, still to video, add motion to image, image animation, photo to video, animate still, wan i2v, image2video, bring image to life, animate photo, motion from image

Aadi-110i/PEP-PROJECT

Landing page conversion optimization with layout rules, hero section design, and CTA psychology. Covers above-the-fold formula, social proof placement, mobile design, and F-pattern reading. Use for: startup landing pages, product pages, SaaS marketing, conversion optimization. Triggers: landing page, hero section, above the fold, conversion optimization, landing page design, cta button, hero image, landing page layout, saas landing page, product page design, conversion rate, landing page best practices

Aadi-110i/PEP-PROJECT

Generate talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI. Turn a portrait image into a realistic speaking video with built-in TTS. 18x faster and 6x cheaper than competitors. Models: P-Video-Avatar, P-Image (for portrait generation). Capabilities: text-to-avatar, audio-driven avatars, 30 voices, 10 languages, 720p/1080p, built-in TTS, dynamic backgrounds, full-body control. Use for: AI presenters, product demos, explainer videos, virtual influencers, marketing, education, multilingual content, UGC, gaming avatars. Triggers: avatar video, talking head, ai avatar, p-video-avatar, pruna avatar, video avatar, ai presenter, digital human, virtual presenter, lipsync, talking avatar, ai spokesperson, heygen alternative, synthesia alternative, veed alternative, fabric alternative, omnihuman alternative

Aadi-110i/PEP-PROJECT

Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio support, 720p/1080p, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna video, p-video, pruna ai video, fast video generation, optimized video, wan t2v, wan i2v, economic video generation, cheap video generation, pruna text to video, pruna image to video

Aadi-110i/PEP-PROJECT

Render videos from React/Remotion component code via inference.sh. Pass TSX code, get MP4. Supports all Remotion APIs: useCurrentFrame, useVideoConfig, spring, interpolate, AbsoluteFill, Sequence. Configurable resolution, FPS, duration, codec. Use for: programmatic video generation, animated graphics, motion design, data-driven videos, React animations to video. Triggers: remotion, render video from code, tsx to video, react video, programmatic video, remotion render, code to video, animated video, motion graphics code, react animation video

Aadi-110i/PEP-PROJECT

Three.js animation - keyframe animation, skeletal animation, morph targets, animation mixing. Use when animating objects, playing GLTF animations, creating procedural motion, or blending animations.

Aadi-110i/PEP-PROJECT

Video ad creation with exact platform-specific specs for TikTok, Instagram, YouTube, Facebook, LinkedIn. Covers dimensions, duration limits, AIDA framework, and caption requirements. Use for: video ads, social media ads, paid media creative, video marketing, ad production. Triggers: video ad, social media ad, tiktok ad, instagram ad, youtube ad, facebook ad, linkedin ad, video creative, ad specs, paid media, video marketing, ad production, reels ad, stories ad, pre roll, bumper ad

Aadi-110i/PEP-PROJECT

YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A/B testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image

相關技能