ai-content-pipeline

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

AI Content Pipeline

AI内容流水线

Build multi-step content creation pipelines via inference.sh CLI.

通过inference.sh CLI构建多步骤内容创建流水线。

Quick Start

快速开始

bash

curl -fsSL https://cli.inference.sh | sh && infsh login

bash

curl -fsSL https://cli.inference.sh | sh && infsh login

Simple pipeline: Generate image -> Animate to video

简单流水线：生成图像→转为动画视频

infsh app run falai/flux-dev --input '{"prompt": "portrait of a woman smiling"}' > image.json infsh app run falai/wan-2-5 --input '{"image_url": "<url-from-previous>"}'

undefined

infsh app run falai/flux-dev --input '{"prompt": "微笑女性肖像"}' > image.json infsh app run falai/wan-2-5 --input '{"image_url": "<上一步生成的URL>"}'

undefined

Pipeline Patterns

流水线模式

Pattern 1: Image -> Video -> Audio

模式1：图像→视频→音频

[FLUX Image] -> [Wan 2.5 Video] -> [Foley Sound]

[FLUX 图像生成] -> [Wan 2.5 视频动画] -> [拟音音效]

Pattern 2: Script -> Speech -> Avatar

模式2：脚本→语音→虚拟形象

[LLM Script] -> [Kokoro TTS] -> [OmniHuman Avatar]

[LLM 脚本生成] -> [Kokoro TTS 语音合成] -> [OmniHuman 虚拟形象]

Pattern 3: Research -> Content -> Distribution

模式3：调研→内容→分发

[Tavily Search] -> [Claude Summary] -> [FLUX Visual] -> [Twitter Post]

[Tavily 搜索] -> [Claude 内容摘要] -> [FLUX 视觉素材] -> [Twitter 发布]

Complete Workflows

完整工作流示例

YouTube Short Pipeline

YouTube Shorts内容流水线

Create a complete short-form video from a topic.

bash

undefined

从一个主题生成完整的短视频。

bash

undefined

1. Generate script with Claude

1. 使用Claude生成脚本

infsh app run openrouter/claude-sonnet-45 --input '{ "prompt": "Write a 30-second script about the future of AI. Make it engaging and conversational. Just the script, no stage directions." }' > script.json

infsh app run openrouter/claude-sonnet-45 --input '{ "prompt": "撰写一段关于AI未来的30秒脚本，风格生动口语化，仅需脚本内容，无需舞台提示。" }' > script.json

2. Generate voiceover with Kokoro

2. 使用Kokoro生成旁白

infsh app run infsh/kokoro-tts --input '{ "text": "<script-text>", "voice": "af_sarah" }' > voice.json

infsh app run infsh/kokoro-tts --input '{ "text": "<脚本内容>", "voice": "af_sarah" }' > voice.json

3. Generate background image with FLUX

3. 使用FLUX生成背景图

infsh app run falai/flux-dev --input '{ "prompt": "Futuristic city skyline at sunset, cyberpunk aesthetic, 4K wallpaper" }' > background.json

infsh app run falai/flux-dev --input '{ "prompt": "日落时分的未来主义城市天际线，赛博朋克风格，4K壁纸画质" }' > background.json

4. Animate image to video with Wan

4. 使用Wan将图像转为动画视频

infsh app run falai/wan-2-5 --input '{ "image_url": "<background-url>", "prompt": "slow camera pan across cityscape, subtle movement" }' > video.json

infsh app run falai/wan-2-5 --input '{ "image_url": "<背景图URL>", "prompt": "镜头缓慢扫过城市景观，动作轻柔" }' > video.json

5. Add captions (manually or with another tool)

5. 添加字幕（手动或使用其他工具）

6. Merge video with audio

6. 合并视频与音频

infsh app run infsh/media-merger --input '{ "video_url": "<video-url>", "audio_url": "<voice-url>" }'

undefined

infsh app run infsh/media-merger --input '{ "video_url": "<视频URL>", "audio_url": "<旁白URL>" }'

undefined

Talking Head Video Pipeline

虚拟主播视频流水线

Create an AI avatar presenting content.

bash

undefined

生成AI虚拟形象讲解内容的视频。

bash

undefined

1. Write the script

1. 撰写脚本

infsh app run openrouter/claude-sonnet-45 --input '{ "prompt": "Write a 1-minute explainer script about quantum computing for beginners." }' > script.json

infsh app run openrouter/claude-sonnet-45 --input '{ "prompt": "撰写一段面向初学者的1分钟量子计算讲解脚本。" }' > script.json

2. Generate speech

2. 生成语音

infsh app run infsh/kokoro-tts --input '{ "text": "<script>", "voice": "am_michael" }' > speech.json

infsh app run infsh/kokoro-tts --input '{ "text": "<脚本内容>", "voice": "am_michael" }' > speech.json

3. Generate or use a portrait image

3. 生成或使用肖像图

infsh app run falai/flux-dev --input '{ "prompt": "Professional headshot of a friendly tech presenter, neutral background, looking at camera" }' > portrait.json

infsh app run falai/flux-dev --input '{ "prompt": "友好科技主播的专业头像，中性背景，直视镜头" }' > portrait.json

4. Create talking head video

4. 生成虚拟主播视频

infsh app run bytedance/omnihuman-1-5 --input '{ "image_url": "<portrait-url>", "audio_url": "<speech-url>" }' > talking_head.json

undefined

infsh app run bytedance/omnihuman-1-5 --input '{ "image_url": "<肖像图URL>", "audio_url": "<语音URL>" }' > talking_head.json

undefined

Product Demo Pipeline

产品演示视频流水线

Create a product showcase video.

bash

undefined

生成产品展示视频。

bash

undefined

1. Generate product image

1. 生成产品图

infsh app run falai/flux-dev --input '{ "prompt": "Sleek wireless earbuds on white surface, studio lighting, product photography" }' > product.json

infsh app run falai/flux-dev --input '{ "prompt": "白色背景上的简约无线耳机，影棚灯光，产品摄影风格" }' > product.json

2. Animate product reveal

2. 制作产品展示动画

infsh app run falai/wan-2-5 --input '{ "image_url": "<product-url>", "prompt": "slow 360 rotation, smooth motion" }' > product_video.json

infsh app run falai/wan-2-5 --input '{ "image_url": "<产品图URL>", "prompt": "缓慢360度旋转，动作流畅" }' > product_video.json

3. Upscale video quality

3. 提升视频画质

infsh app run falai/topaz-video-upscaler --input '{ "video_url": "<product-video-url>" }' > upscaled.json

infsh app run falai/topaz-video-upscaler --input '{ "video_url": "<产品视频URL>" }' > upscaled.json

4. Add background music

4. 添加背景音乐

infsh app run infsh/media-merger --input '{ "video_url": "<upscaled-url>", "audio_url": "https://your-music.mp3", "audio_volume": 0.3 }'

undefined

infsh app run infsh/media-merger --input '{ "video_url": "<高清视频URL>", "audio_url": "https://your-music.mp3", "audio_volume": 0.3 }'

undefined

Blog to Video Pipeline

博客转视频流水线

Convert written content to video format.

bash

undefined

将文字内容转为视频格式。

bash

undefined

1. Summarize blog post

1. 总结博客内容

infsh app run openrouter/claude-haiku-45 --input '{ "prompt": "Summarize this blog post into 5 key points for a video script: <blog-content>" }' > summary.json

infsh app run openrouter/claude-haiku-45 --input '{ "prompt": "将这篇博客总结为5个核心要点，用于制作视频脚本：<博客内容>" }' > summary.json

2. Generate images for each point

2. 为每个要点生成对应图像

for i in 1 2 3 4 5; do infsh app run falai/flux-dev --input "{ "prompt": "Visual representing point $i: <point-text>" }" > "image_$i.json" done

for i in 1 2 3 4 5; do infsh app run falai/flux-dev --input "{ "prompt": "可视化呈现第$i个要点：<要点内容>" }" > "image_$i.json" done

3. Animate each image

3. 将每个图像转为动画

for i in 1 2 3 4 5; do infsh app run falai/wan-2-5 --input "{ "image_url": "<image-$i-url>" }" > "video_$i.json" done

for i in 1 2 3 4 5; do infsh app run falai/wan-2-5 --input "{ "image_url": "<第$i张图的URL>" }" > "video_$i.json" done

4. Generate voiceover

4. 生成旁白

infsh app run infsh/kokoro-tts --input '{ "text": "<full-script>", "voice": "bf_emma" }' > narration.json

infsh app run infsh/kokoro-tts --input '{ "text": "<完整脚本内容>", "voice": "bf_emma" }' > narration.json

5. Merge all clips

5. 合并所有片段

infsh app run infsh/media-merger --input '{ "videos": ["<video1>", "<video2>", "<video3>", "<video4>", "<video5>"], "audio_url": "<narration-url>", "transition": "crossfade" }'

undefined

infsh app run infsh/media-merger --input '{ "videos": ["<视频1>", "<视频2>", "<视频3>", "<视频4>", "<视频5>"], "audio_url": "<旁白URL>", "transition": "crossfade" }'

undefined

Pipeline Building Blocks

流水线构建组件

Content Generation

内容生成

Step	App	Purpose
Script	`openrouter/claude-sonnet-45`	Write content
Research	`tavily/search-assistant`	Gather information
Summary	`openrouter/claude-haiku-45`	Condense content

步骤	应用	用途
脚本生成	`openrouter/claude-sonnet-45`	撰写内容
调研	`tavily/search-assistant`	收集信息
内容摘要	`openrouter/claude-haiku-45`	浓缩内容

Visual Assets

视觉素材

Step	App	Purpose
Image	`falai/flux-dev`	Generate images
Image	`google/imagen-3`	Alternative image gen
Upscale	`falai/topaz-image-upscaler`	Enhance quality

步骤	应用	用途
图像生成	`falai/flux-dev`	生成图像
图像生成	`google/imagen-3`	替代图像生成工具
画质增强	`falai/topaz-image-upscaler`	提升画质

Animation

动画制作

Step	App	Purpose
I2V	`falai/wan-2-5`	Animate images
T2V	`google/veo-3-1-fast`	Generate from text
Avatar	`bytedance/omnihuman-1-5`	Talking heads

步骤	应用	用途
图转视频	`falai/wan-2-5`	图像动画化
文本转视频	`google/veo-3-1-fast`	从文本生成视频
虚拟形象	`bytedance/omnihuman-1-5`	生成虚拟主播视频

Audio

音频处理

Step	App	Purpose
TTS	`infsh/kokoro-tts`	Voice narration
Music	`infsh/ai-music`	Background music
Foley	`infsh/hunyuanvideo-foley`	Sound effects

步骤	应用	用途
文本转语音	`infsh/kokoro-tts`	生成旁白语音
音乐生成	`infsh/ai-music`	生成背景音乐
拟音音效	`infsh/hunyuanvideo-foley`	添加音效

Post-Production

后期制作

Step	App	Purpose
Upscale	`falai/topaz-video-upscaler`	Enhance video
Merge	`infsh/media-merger`	Combine media
Caption	`infsh/caption-video`	Add subtitles

步骤	应用	用途
视频增强	`falai/topaz-video-upscaler`	提升视频画质
媒体合并	`infsh/media-merger`	整合多媒体素材
字幕添加	`infsh/caption-video`	添加字幕

Best Practices

最佳实践

Plan the pipeline first - Map out each step before running
Save intermediate results - Store outputs for iteration
Use appropriate quality - Fast models for drafts, quality for finals
Match resolutions - Keep consistent aspect ratios throughout
Test each step - Verify outputs before proceeding

先规划流水线 - 运行前梳理清楚每个步骤
保存中间结果 - 存储输出内容以便迭代优化
选择合适的模型质量 - 草稿用快速模型，最终版用高质量模型
保持分辨率一致 - 全程使用统一的宽高比
分步测试 - 确认每一步输出无误后再进行下一步

Related Skills

Video generation models

视频生成模型

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

Image generation

图像生成

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

Text-to-speech

文本转语音

npx skills add inference-sh/skills@text-to-speech

LLM models for scripts

用于脚本生成的LLM模型

npx skills add inference-sh/skills@llm-models

Full platform skill

完整平台技能

npx skills add inference-sh/skills@inference-sh


Browse all apps: `infsh app list`

npx skills add inference-sh/skills@inference-sh


浏览所有应用：`infsh app list`

Documentation

文档

Content Pipeline Example - Official pipeline guide
Building Workflows - Workflow best practices

内容流水线示例 - 官方流水线指南
构建工作流 - 工作流最佳实践