ai-content-pipeline

Installation
Summary

Multi-step AI content creation pipelines combining image, video, audio, and text generation.

  • Chains tools like FLUX (image generation), Wan 2.5 (animation), Kokoro TTS (voice), and OmniHuman (talking heads) into complete workflows via the inference.sh CLI
  • Includes four ready-to-use pipeline templates: YouTube shorts (script → voiceover → background → animation → merge), talking head videos, product demos, and blog-to-video conversion
  • Supports common patterns such as image-to-video-to-audio, script-to-speech-to-avatar, and research-to-content-to-distribution chains
  • Post-production tools include video upscaling, media merging, and caption generation for polished final output
SKILL.md

Install the belt CLI skill: npx skills add belt-sh/cli

AI Content Pipeline

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

AI Content Pipeline

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

# Simple pipeline: Generate image -> Animate to video
belt app run falai/flux-dev --input '{"prompt": "portrait of a woman smiling"}' > image.json
belt app run falai/wan-2-5 --input '{"image_url": "<url-from-previous>"}'
Related skills

More from inferen-sh/skills

Installs
GitHub Stars
500
First Seen
ai-content-pipeline — inferen-sh/skills