OpenSource-Hub
P

Pixelle-Video

SHA-256
15.4k stars·Video & Audio Download·SHA-256 checksum verified

AI fully automated short video engine. Enter a theme and AI generates scripts, images, voiceover, music, and compiles a complete video automatically.

Enter a topic, AI automatically generates a complete short video with script, images, voice, and music.

Core Features

  • Fully automated generation from topic to final video
  • Intelligent script writing with multiple LLM support
  • AI-generated images and videos for each scene
  • Multi TTS engines (Edge-TTS, Index-TTS) with voice cloning
  • Background music: built-in or custom upload

What It Can't Do

  • Requires at least one LLM API key (e.g., Qwen) or a local Ollama; image generation needs local ComfyUI or RunningHub API key
  • Local ComfyUI requires a GPU (NVIDIA recommended); cloud options incur costs
  • Generation time varies with scene count, network speed, and AI inference speed; typically a few minutes

Use Cases

  • Content creators for Douyin, Kuaishou, YouTube Shorts needing batch video production
  • Bloggers generating explanatory, educational, or emotional short videos from a single topic

Detailed Introduction

Pixelle-Video is an AI-driven tool that automates the entire short video creation process. Simply input a topic, and it will generate the script, create AI illustrations or videos, synthesize voice narration, add background music, and produce a finished video — all without any manual editing. It supports multiple AI models (GPT, Qwen, DeepSeek, Ollama), various TTS engines, and ComfyUI workflows for flexible customization. Features include digital human speaking, image-to-video, motion transfer, and pre-built templates for different aspect ratios. The project is Apache-2.0 licensed with over 15,000 stars.

Troubleshooting & FAQ (1)

Troubleshooting
Why does the ComfyUI workflow tool seem to only support paid APIs and has no updates?

The repository is no longer actively maintained because the original developers have moved on, leaving no one with access rights to push updates. Despite appearances, the project has no commercial ties to any third-party paid platforms—those links are only suggestions for users who lack local GPUs. If you have your own GPU, you can run inference locally using the tool’s built-in support. To bypass paid workflows entirely, generate prompts with the tool and manually import them into a locally installed ComfyUI (make sure it’s up-to-date). This ensures full control without relying on any online services.

GitHub Issue #127

Tags

AI video generationshort videoautomationComfyUItext-to-videodigital human

Getting Started

1

Download installer

Click the button above to download the installer for your system

2

Install the software

Double-click the downloaded installer and follow the prompts

3

Download the Windows all-in-one package and extract it

4

Double-click start.bat to launch the web UI, browser opens http://localhost:8501 automatically

5

In 'System Configuration', fill in LLM API Key and image generation service (e.g., use Qwen free tier)

Install Guide
  1. Download the Windows all-in-one package and extract it
  2. Double-click start.bat to launch the web UI, browser opens http://localhost:8501 automatically
  3. In 'System Configuration', fill in LLM API Key and image generation service (e.g., use Qwen free tier)
File Integrity

SHA-256 checksum verified

Checksum extracted from GitHub official Release page

SHA256 Checksum

12f110ad26df1cda2cf3fdc5009c458c4a1b1e3091af23209f79ae3168ab00f3

This checksum is extracted from the GitHub Release page. Verify file integrity after download.

All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.

Open Source Transparency

View GitHub Source
Environment Guide

Uninstall Info

Simply delete the extraction folder. For source installation, delete the project directory and virtual environment.

No Extra Dependencies

Ready to use after download. No additional runtime required.

Project Info
LicenseApache-2.0
Last Updated2026-06-27 14:35:13
GitHub RepositoryOfficial Website

Having issues? Check the FAQ below

1 FAQ

Similar Projects