ai-social-media-content

安装 belt CLI 技能： npx skills add belt-sh/cli

AI 社交媒体内容

通过 inference.sh CLI 为所有平台创建社交媒体内容。

快速开始

需要 inference.sh CLI（belt）。安装说明

belt login

# Generate a TikTok-style video
belt app run google/veo-3-1-fast --input '{
  "prompt": "POV walking through a neon-lit Tokyo street at night, vertical format 9:16, cinematic"
}'

平台格式

平台	宽高比	时长	分辨率
TikTok	9:16 竖屏	15-60s	1080x1920
Instagram Reels	9:16 竖屏	15-90s	1080x1920
Instagram Feed	1:1 或 4:5	-	1080x1080
YouTube Shorts	9:16 竖屏	<60s	1080x1920
YouTube 缩略图	16:9	-	1280x720
Twitter/X	16:9 或 1:1	<140s	1920x1080

内容工作流

TikTok / Reels 视频

# Generate trending-style content
belt app run google/veo-3-1-fast --input '{
  "prompt": "Satisfying slow motion video of paint being mixed, vibrant colors swirling together, vertical 9:16, ASMR aesthetic, viral TikTok style"
}'

Instagram 轮播图片

# Generate cohesive carousel images
for i in 1 2 3 4 5; do
  belt app run falai/flux-dev --input "{
    \"prompt\": \"Minimalist lifestyle flat lay photo $i/5, morning coffee routine, neutral tones, Instagram aesthetic, consistent style\"
  }" > "carousel_$i.json"
done

YouTube 缩略图

# Eye-catching thumbnail
belt app run falai/flux-dev --input '{
  "prompt": "YouTube thumbnail, shocked face emoji, bright yellow background, bold text area on right, attention-grabbing, high contrast, professional"
}'

Twitter/X 视觉帖子

# Generate image for tweet
belt app run falai/flux-dev --input '{
  "prompt": "Tech infographic style image showing AI trends, modern design, data visualization aesthetic, shareable"
}'

# Post with Twitter automation
belt app run twitter/post-tweet --input '{
  "text": "The future of AI is here. Here are the top 5 trends reshaping tech in 2024 🧵",
  "media_url": "<image-url>"
}'

对镜讲解内容

# 1. Write script with Claude
belt app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Write a 30-second engaging script about productivity tips for a TikTok. Conversational, hook in first 3 seconds."
}' > script.json

# 2. Generate voiceover
belt app run infsh/kokoro-tts --input '{
  "prompt": "<script>",
  "voice": "af_sarah"
}' > voice.json

# 3. Create AI avatar
belt app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://your-avatar.jpg",
  "audio_url": "<voice-url>"
}'

内容类型模板

热门/病毒式风格

belt app run google/veo-3 --input '{
  "prompt": "Satisfying compilation style video, oddly satisfying content, smooth transitions, ASMR quality, vertical 9:16"
}'

教程/操作指南

belt app run google/veo-3-1 --input '{
  "prompt": "Hands demonstrating a craft tutorial, overhead shot, clean workspace, step-by-step motion, warm lighting, vertical format"
}'

产品展示

belt app run bytedance/seedance-2-0 --input '{
  "prompt": "Product unboxing aesthetic, sleek packaging reveal, soft lighting, premium feel, satisfying unwrap",
  "ratio": "9:16",
  "generate_audio": true
}'

生活方式/美学

belt app run google/veo-3-1-fast --input '{
  "prompt": "Day in my life aesthetic, morning routine montage, golden hour lighting, cozy apartment, coffee steam rising, vertical format"
}'

幕后花絮

belt app run google/veo-3-1-fast --input '{
  "prompt": "Behind the scenes of creative workspace, artist at work, authentic candid moments, documentary style, vertical 9:16"
}'

文案与话题标签生成

# Generate engaging caption
belt app run openrouter/claude-haiku-45 --input '{
  "prompt": "Write an engaging Instagram caption for a sunset beach photo. Include a hook, value, and call to action. Add 10 relevant hashtags."
}'

开场钩子公式

belt app run openrouter/claude-haiku-45 --input '{
  "prompt": "Generate 5 viral TikTok hooks for a video about morning routines. Use proven patterns like: curiosity gap, bold claim, relatable struggle, before/after, or tutorial format."
}'

多平台内容改编

长内容转短内容流程

# Take a concept and create multiple formats
CONCEPT="productivity hack: 2-minute rule"

# TikTok vertical
belt app run google/veo-3-1-fast --input "{
  \"prompt\": \"$CONCEPT visualization, vertical 9:16, quick cuts, text overlays style\"
}"

# Twitter square
belt app run falai/flux-dev --input "{
  \"prompt\": \"$CONCEPT infographic, square format, minimal design, shareable\"
}"

# YouTube thumbnail
belt app run falai/flux-dev --input "{
  \"prompt\": \"$CONCEPT thumbnail, surprised person, bold text space, 16:9\"
}"

批量创建内容

# Generate a week of content
TOPICS=("morning routine" "productivity tips" "coffee aesthetic" "workspace tour" "night routine")

for topic in "${TOPICS[@]}"; do
  belt app run google/veo-3-1-fast --input "{
    \"prompt\": \"$topic content for social media, aesthetic, vertical 9:16, engaging\"
  }" > "content_${topic// /_}.json"
done

最佳实践

1. 在前 3 秒设置钩子 - 从最吸引人的片段开始
2. 优先采用竖屏 - TikTok、Reels、Shorts 使用 9:16
3. 保持风格一致 - 与品牌颜色和风格相匹配
4. 预留文字安全区 - 为平台 UI 元素留出空间
5. 使用热门音频 - 单独添加热门声音
6. 批量创建 - 一次生成多条内容

平台专属技巧

TikTok

• 快速剪辑，使用热门声音
• 文字叠加很重要
• 立即设置钩子

Instagram

• 保持较高的视觉质量
• 使用轮播提高互动
• 保持美学风格一致

YouTube Shorts

• 明确传达价值主张
• 使用订阅号召语
• 改编较长的内容

Twitter/X

• 使用一张引人注目的图片
• 有争议性的钩子效果好
• 可扩展为帖子串

相关技能

# Video generation
npx skills add inference-sh/skills@ai-video-generation

# Image generation
npx skills add inference-sh/skills@ai-image-generation

# Twitter automation
npx skills add inference-sh/skills@twitter-automation

# Text-to-speech for voiceovers
npx skills add inference-sh/skills@text-to-speech

# Full platform skill
npx skills add inference-sh/skills@infsh-cli

浏览所有应用：belt app list