witty-suckerpunch492/daihuo-jianshou

自动生成电商带货短视频：上传商品图，AI 生成脚本、素材并合成视频，适配抖音、快手、小红书

What it solves

It automates the creation of e-commerce short videos for platforms like Douyin, Kuaishou, and Xiaohongshu. It replaces the manual, time-consuming process of writing scripts, filming, and editing by using AI to analyze product images and generate complete marketing videos.

How it works

The tool follows a multi-step pipeline:

  1. Script Generation: Uses LLMs and category-specific templates (e.g., beauty, electronics) to create scripts based on target audiences and platform SEO strategies.
  2. Asset Generation: Aggregates over 20 AI models from five platforms (including fal.ai, Volcengine, and Alibaba Cloud) to generate high-quality product images and videos (T2V/I2V).
  3. Video Composition: Employs a professional FFmpeg pipeline to combine assets with smart transitions, Ken Burns motion effects, subtitles, and mixed audio/BGM.
  4. Optimization: Automatically generates platform-specific SEO metadata (titles, hashtags, and cover text) and allows for A/B testing of different versions.

Who it’s for

  • E-commerce Sellers: Merchants on platforms like Taobao or Pinduoduo needing high-volume product promos.
  • Short Video Operators: MCN agencies and creators looking to scale content production.
  • Brand Owners: Companies needing rapid asset creation for new product launches.
  • Developers: Those wanting to build an AI video SaaS based on this framework.

Highlights

  • Multi-Model Aggregation: Integrated access to top-tier models like Kling 3.0, Veo 3, and FLUX.2.
  • E-commerce Toolset: Includes a product library, batch generation, and the ability to replicate the logic of viral competitor videos.
  • Platform-Specific SEO: Tailors hooks and interaction guides specifically for the algorithms of Douyin, Kuaishou, and Xiaohongshu.
  • Flexible Video Modes: Offers four distinct styles, ranging from high-realism product close-ups to AI-generated scene demonstrations.

Related

  • Project
    gulucaptain/Camera-Transformer-1

    CT-1 is a Vision-Language-Camera model that estimates precise camera trajectories from images and text prompts to enable spatially aware, controllable video generation.

  • Project
    AkshitIreddy/AI-Powered-Video-Tutorial-Generator

    AI‑Powered Video Tutorial Generator is a Windows‑only desktop app that turns a question or topic into a fully editable video lesson. It handles research, script writing, storyboard creation, narration, illustration, presenter animation and final export, using either local diffusion models (ComfyUI/SDXL) or cloud LLM/image providers. The open‑source stack combines a React/Tauri UI, a Rust core, and a Python pipeline, and it ships with bundled runtimes (Python, Node, Chromium, FFmpeg).

  • Project
    seesee75-commits/ComfyUI-MiniMaxH3-Director

    A timeline editor for MiniMax H3 in ComfyUI that replaces manual storyboard prompting with a visual interface for managing shots, keyframes, and audio.

  • Project
    jamichss/Stream-DiffVSR

    Stream‑DiffVSR is a diffusion‑based video‑super‑resolution system designed for low‑latency, online use. It runs a 4‑step distilled denoiser, an auto‑regressive temporal guidance module, and a lightweight temporal decoder to upscale 720p video frames in ~0.33 s on an RTX 4090, far faster than prior diffusion VSR methods. The repo provides conda environments, CLI and Gradio UI for inference, optional TensorRT acceleration, Docker support, and full training scripts using REDS and Vimeo‑90K datasets.