Stars
Forks
Watchers
Developer links
Pixelle Video
Backed by Alibaba's AIDC team and carrying over 27,700 GitHub stars, Pixelle-Video turns a single text prompt into a publish-ready short video in approximately three minutes — handling scriptwriting, image generation, voice narration, music selection, subtitle overlay, and final MP4 export in one automated pipeline. The engine supports multiple LLM backends for script generation including GPT-4, Qwen, DeepSeek, and local Ollama deployments, while image and video creation routes through either self-hosted ComfyUI workflows, cloud-based RunningHub pipelines, or direct API connections to DashScope Wan, OpenAI, Seedream, Seedance, and Kling AI. Text-to-speech synthesis uses Edge-TTS, Index-TTS, and other mainstream engines with multi-language voice profiles. Five distinct pipelines cover Quick Create, Standard, Digital Human Avatar broadcasting, Image-to-Video transformation, and Motion Transfer from reference video. The Streamlit web UI on port 8501 provides a visual workflow builder with template selection across portrait (1080x1920), landscape (1920x1080), and square formats, while the FastAPI server on port 8000 exposes a REST API with endpoints for async video generation, task polling, content scripting, TTS and image generation, template listing, and health checks. History persistence tracks all completed generations. HTML-based visual templates support static, image-overlay, and AI-video styles with customizable prompt prefixes. The modular architecture lets operators swap any atomic capability — image model, video model, TTS engine, or VLM — by editing a workflow JSON file without touching Python code. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.
Benefits
- Topic-to-Video in Three Minutes
- Input a single text topic and receive a fully assembled MP4 with AI-generated script, images, voiceover narration, background music, and timed subtitles — zero editing required.
- Multi-Provider AI Model Support
- Connect to GPT-4, Qwen, DeepSeek, or local Ollama for scripting, plus DashScope, Seedream, Seedance, Kling, and OpenAI for image and video generation through configurable API adapters.
- Five Specialized Production Pipelines
- Choose from Quick Create, Standard, Digital Human Avatar, Image-to-Video, and Motion Transfer pipelines — each optimized for distinct content creation workflows with dedicated UI controls.
- Modular Swap-Anything Architecture
- Replace any atomic capability — image model, video model, TTS engine, or VLM — by editing a single workflow JSON file without modifying Python source code.
Features
- Streamlit Web UI
- Visual workflow builder on port 8501 with template selection, pipeline configuration, generation history, and real-time progress tracking for video production.
- FastAPI REST Server
- Full REST API on port 8000 with async video generation, task polling, individual TTS and image endpoints, template and workflow listing, and health checks.
- ComfyUI Workflow Engine
- Orchestrates image and video generation through self-hosted ComfyUI nodes or cloud RunningHub pipelines using configurable JSON workflow definitions.
- Multi-Engine TTS
- Synthesizes voiceover narration using Edge-TTS, Index-TTS, and other mainstream engines with multi-language support and configurable voice profiles.
- Direct API Media Generation
- Bypasses ComfyUI entirely by calling DashScope Wan, Seedream, Seedance, Kling, and OpenAI image APIs directly with retry handling and prompt safety.
- HTML Template System
- Renders visual frames from customizable HTML templates supporting static, image-overlay, and video styles in portrait, landscape, and square dimensions.