xixihhhh/clipforge

ClipForge（原『带货剪手』/ daihuo-jianshou）：开源 AI 带货短视频神器——上传一张商品图，AI 自动提炼卖点 + 写种草脚本 + 锁定商品原图不变形 + 配画面/配音/字幕，一键产出抖音小店 / 快手 / 小红书 / TikTok Shop 卖货短视频。0 成本批量出片、开源无水印、本地自部署。也支持一句话主题成片。Open-source AI e-commerce/UGC short-video generator.

What it solves

ClipForge is an open-source tool designed to automate the creation of high-conversion e-commerce short videos for platforms like TikTok Shop, Douyin, Kuaishou, and Xiaohongshu. It eliminates the need for manual scriptwriting, filming, and editing by transforming a single product image or link into a complete video with AI-generated scripts, voiceovers, subtitles, and B-roll, while ensuring the original product image remains undistorted.

How it works

The system follows a pipeline: it extracts selling points from a product image or link, generates multiple script options (vetted by a "judge panel" for quality), and then produces the video. Users can choose between a Free Path (using open-source CC libraries and Edge TTS for zero cost) or an AI Path (using paid models like Seedance 2.5 for high-end image-to-video generation). It utilizes FFmpeg for local synthesis and supports a "Director Mode" for granular control over storyboards, camera movements, and model selection.

Who it’s for

  • E-commerce sellers who need to produce dozens of product videos daily without a production budget.
  • Content creators looking for a "faceless" way to generate UGC-style ads.
  • AI Agents/Developers who want to integrate video production via MCP, CLI, or specialized skills.

Highlights

  • Product Fidelity: Uses image-to-image locking to ensure products don't deform during AI generation.
  • Compliance-First: Built-in AIGC labeling (GB 45438 standard), ad-law banned word scanning, and platform-specific risk checks.
  • Dual-Mode Workflow: "Novice Mode" for one-click automation and "Director Mode" for professional control over shots and costs.
  • Multi-Model Integration: Aggregates 30+ models across 7 platforms for image and video generation.
  • Production Efficiency: Features batch production, viral video replication (analyzing rhythm/cuts of reference videos), and A/B variant testing.

Related

  • Project
    xhongc/ai_story

    AI Story is a Docker‑based web platform that turns a short text prompt into a complete short video. It automatically rewrites the prompt into a script, creates a storyboard, generates images via multiple AI image services, plans camera motions, and renders the final video, all orchestrated with Django, Celery, Redis and a Vue front‑end.

  • Project
    openstory-so/openstory

    OpenStory is a full-stack AI platform that takes a written script and automatically produces a styled video production — generating scene images, motion clips, and audio with consistent visual style across every scene, plus team collaboration features.

  • Project
    sorker/ai-shotlive

    AI ShotLive Director is an open‑source, React + Express (or Electron) platform that turns novels or story outlines into short videos or motion comics. It uses a keyframe‑driven workflow (first/last frames → interpolation) and lets you plug in any text, image, video or audio model (OpenAI, Anthropic, Google, AntSK, etc.). Features include novel‑to‑script conversion, asset generation (character look‑books, scene concepts), a grid storyboard editor, multi‑track video editing with AI subtitles/TTS, and full backup/restore. Deployable via Docker, local SQLite, or as a desktop app, and licensed under CC BY‑NC‑SA 4.0.

  • Project
    ATH-MaaS/Pixelle-Video

    An AI-powered automated short-video engine that generates scripts, visuals, and voiceovers from a single topic to create complete videos without manual editing.

  • Project
    YILS-LIN/short-video-factory

    Short Video Factory is an open‑source desktop tool that uses AI (OpenAI‑style text generation and Edge‑TTS voice synthesis) to turn a short prompt and raw footage into a finished short video, with subtitles, batch processing and cross‑platform support.