Communitygithub.com

Aadi-110i/PEP-PROJECT

YouTube 縮圖設計,包含特定尺寸、對比規則與行動裝置預覽最佳化。涵蓋安全區、文字擺放、臉部表情心理學與 A/B 測試。

PEP-PROJECT 是什麼?

這個技能提供了一個完整的 YouTube 縮圖設計框架,主要透過 [inference.sh](https://inference.sh) CLI 的 `bel` 工具來生成高點擊率(CTR)的縮圖。它不僅給出詳細的規格(如 1280x720 最小尺寸、16:9 比例、2MB 限制),還教授「120 像素測試」-確保縮圖在手機上縮小到 120px 寬度時,情緒、主體與文字仍然清晰可辨。技能涵蓋安全區(避免底部角落被時間戳與章節標記遮擋)、顏色策略(三色以內、高對比配色表)、文字規則(最多 6 字、60pt 以上、粗體無襯線)、以及臉部表情心理學(驚訝、好奇、興奮等表情對 CTR 的影響與擺放位置)。此外,它針對教學、前後對比、產品評測、列表清單等不同內容類型提供可直接執行的 CLI 生成指令,並指導 A/B 測試(一次只變一個變數,如人像 vs. 無人像、表情、配色)。最終提供一份完整的檢查清單與常見錯誤修正,幫助創作者產出在 YouTube 動態牆中脫穎而出的縮圖。

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

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。

說明文件

YouTube 縮圖設計

使用 inference.sh CLI 透過 AI 圖片生成,建立高點擊率(CTR)的 YouTube 縮圖。

快速開始

需要 inference.sh CLI(belt)。安裝說明

belt login

# 生成縮圖
belt app run falai/flux-dev-lora --input '{
  "prompt": "YouTube thumbnail style, close-up of a person with surprised excited expression looking at a glowing laptop screen, vibrant blue and orange color scheme, dramatic studio lighting, shallow depth of field, high contrast, cinematic",
  "width": 1280,
  "height": 720
}'

規格

規格數值
尺寸1280 x 720 px(最小)
建議尺寸1920 x 1080 px
比例16:9
最大檔案大小2 MB
格式JPG, GIF, PNG

120 像素測試

你的縮圖在手機上大約只會顯示 120px 寬——這也是大多數觀眾第一次看到它的方式。

在 120px 時,觀眾必須能辨識出:

  1. 情緒/氛圍(從顏色和表情)
  2. 主要主體(從構圖)
  3. 文字(如果有——且必須夠大)

測試方式: 將縮圖縮小到 120px 寬觀看。如果看起來模糊不清,請重新設計。

安全區域

┌─────────────────────────────────────────────┐
│                                             │
│   ✅ 文字與關鍵元素的安全區域                │
│                                             │
│                                             │
│                                             │
│                                             │
│                                       ┌───┐ │
│                                       │ ⏱ │ │ ← 時間戳疊加層
│                              ┌────────┴───┘ │    (右下角)
│   ┌────┐                     │  時長        │
│   │ CH │ 章節標記            └──────────────│
└───┴────┴────────────────────────────────────┘
     ↑ 左下角:章節/進度標記

避免將關鍵元素放在:

  • 右下角(影片時間戳)
  • 左下角(章節標記、進度條)
  • 極端邊緣(不同裝置的裁切方式不同)

顏色策略

有效的高對比配色

組合氛圍最適合
黃色 + 黑色急迫感、注意力科技、商業、列表
紅色 + 白色能量、刺激娛樂、反應
藍色 + 橙色專業對比教育、教學
綠色 + 白色成長、金錢理財、成功故事
紫色 + 黃色高級、創意設計、藝術、創造力
白色 + 深色乾淨、極簡奢華、極簡風格頻道

顏色規則

  • 背景和文字/主體應互補或高對比
  • 避免同色溫的顏色相鄰(紅色配橙色會變模糊)
  • 每個縮圖最多使用 3 種顏色
  • 飽和度要比現實更高——縮圖需要與明亮的 UI 競爭

縮圖上的文字

適合使用文字的時機

  • 列表/數字:「7 個秘訣」、「Top 10」
  • 強烈觀點:「別再這樣做」
  • 成果展示:「30 天賺 10 萬」
  • 比較:「vs」放在兩個事物之間

不適合使用文字的時機

  • 影片標題已經說明(重複)
  • 情緒/視覺本身就能傳達故事
  • 無法將文字放大到在 120px 下可讀

文字規則

規則原因
最多 6 個字縮圖尺寸下的可讀性
至少相當於 60pt在 120px 寬度下必須清晰可辨
粗體無襯線字體細字體在小尺寸下會消失
對比描邊/陰影確保在任何背景上都可讀
不要有過小的文字如果縮小後無法閱讀,就刪掉它

臉部表情心理學

包含人臉的縮圖比沒有人臉的縮圖 CTR 更高。表情至關重要:

表情CTR 影響最適合
驚訝/震驚最高反應、揭露、發現類內容
好奇高教學、指南、秘訣
興奮高開箱、評論、公告
擔憂/擔心中高警告、錯誤、問題類內容
自信中專家建議、權威內容
中性最低除非你的品牌是極簡風格,否則避免使用

臉部構圖規則

  • 臉部應佔縮圖的 30-50%
  • 眼睛看向 文字或主體(引導觀眾注意力)
  • 看向鏡頭 = 連結感。看向物體 = 好奇心。
  • 臉部放在一側(通常是左側),文字或主體放在另一側
# 生成臉部朝前的縮圖
belt app run falai/flux-dev-lora --input '{
  "prompt": "close-up portrait of a man with genuinely surprised expression, mouth slightly open, raised eyebrows, looking at camera, left side of frame, vibrant teal background, dramatic rim lighting, YouTube thumbnail style, high contrast, cinematic",
  "width": 1280,
  "height": 720
}'

# 生成臉部看向主體的縮圖
belt app run bytedance/seedream-4-5 --input '{
  "prompt": "person looking amazed at a glowing holographic chart showing upward growth, dramatic blue and green lighting, right side profile view, dark background, tech aesthetic, high energy",
  "size": "2K"
}'

各類內容的縮圖模式

教學/指南

belt app run falai/flux-dev-lora --input '{
  "prompt": "overhead flat lay of organized workspace with laptop showing code editor, colorful sticky notes, coffee cup, clean bright background, professional setup, tutorial style composition, warm lighting",
  "width": 1280,
  "height": 720
}'

前後對比

belt app run falai/flux-dev-lora --input '{
  "prompt": "split composition, left side dark and messy disorganized desk, right side bright clean organized minimalist workspace, dramatic contrast between chaos and order, clear dividing line in center, high contrast",
  "width": 1280,
  "height": 720
}'

產品評測/比較

belt app run falai/flux-dev-lora --input '{
  "prompt": "two products facing each other with dramatic lighting and sparks between them, competition battle concept, dark background with colorful rim lighting, versus comparison style, high energy, product photography",
  "width": 1280,
  "height": 720
}'

列表/數字

belt app run falai/flux-dev-lora --input '{
  "prompt": "dynamic arrangement of 7 different colorful objects floating in space against dark gradient background, each item distinct and clearly separated, energetic composition, vibrant saturated colors, studio lighting",
  "width": 1280,
  "height": 720
}'

A/B 測試

每次只測試一個變數:

變數測試 A vs B
有人臉 vs 無人臉相同構圖,有/無人物
表情驚訝 vs 好奇
配色暖色 vs 冷色調
有文字 vs 無文字有/無文字疊加層
背景明亮 vs 黑暗
構圖主體朝左 vs 主體朝右
# 生成變體 A
belt app run falai/flux-dev-lora --input '{
  "prompt": "..., bright yellow background, ...",
  "width": 1280, "height": 720
}' --no-wait

# 生成變體 B(相同提示,不同背景)
belt app run falai/flux-dev-lora --input '{
  "prompt": "..., dark navy background, ...",
  "width": 1280, "height": 720
}' --no-wait

縮圖檢查清單

  • 至少 1280x720(建議 1920x1080)
  • 檔案大小小於 2MB
  • 通過 120px 瞇眼測試
  • 無關鍵元素在右下角(時間戳)或左下角(章節)
  • 最多 3 種顏色,高對比
  • 文字(如果有的話)最多 6 字,粗體,帶對比描邊
  • 臉部表情與內容能量相符(如果適用的話)
  • 不與影片標題重複
  • 在周圍縮圖中脫穎而出(請檢查你的領域)
  • 在淺色和深色 YouTube 背景上都有效

常見錯誤

錯誤問題修正
文字過多在縮圖尺寸下無法閱讀最多 6 字或無文字
低對比在動態牆中消失使用互補色
構圖雜亂視線不知道該看哪裡只有一個焦點
像一般圖庫照片沒有個性,容易被跳過真實的表情、獨特的角度
過小的細節在 120px 下消失大膽、簡單的形狀
每部影片風格都一樣觀眾疲勞在品牌指導原則內變化
誤導性縮圖破壞信任、影響留存率與實際內容相符

相關技能

npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@image-upscaling
npx skills add inference-sh/skills@prompt-engineering

瀏覽所有應用程式:belt app list

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

Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts

相關技能