A complete AI-powered video generation pipeline that enhances creative prompts and generates high-quality videos using Google's Veo3 API, requiring only a single API key.
# VEO3 Workflow Agents Workflow agents for AI video prompt enhancement and video generation using Google's Veo3 Fast API. This project combines multiple AI agents to create a comprehensive video generation pipeline: - **Enhancement agent**: `langraph_agents/` - Technical prompt enhancement with cinematography details - **Idea generation agents**: `pydantic_ai_agents/` - Creative prompt variations and viral content ideas - **Veo3 Integration**: Complete notebook workflow for generating videos using Google's latest video AI - **Interactive Interface**: Jupyter notebook with user-friendly UI for the complete workflow ## 🎬 NEW: Streamlined Veo3 Video Generation Notebook We've created a streamlined Jupyter notebook that integrates prompt generation, enhancement, and video creation with **zero Google Cloud setup required**: **`veo3_prompt_generation_workflow.ipynb`** - Streamlined interactive video generation pipeline ### Features: - 🎭 Generate creative prompt variations using `pydantic_ai_agents` - ⚡ Enhance prompts with technical details using `langraph_agents` - 🎬 Generate high-quality videos using Veo3 Fast API - 🎛️ Interactive UI with customizable settings (duration, aspect ratio, audio) - 💾 Automatic video saving and playback - 🔧 Advanced usage examples and batch processing - ✅ **No Vertex AI or Google Cloud Project required!** ### Quick Start with Notebook: ```bash # Install dependencies pip install -e . # Set up environment variable (only requirement!) export GOOGLE_API_KEY="your-google-api-key" # Launch Jupyter Lab jupyter lab veo3_prompt_generation_workflow.ipynb ``` ### Or try the standalone demo: ```bash # Run the command-line demo python notebook_demo.py "A cat playing with a ball of yarn in a sunlit room" ``` See **[NOTEBOOK_SETUP.md](NOTEBOOK_SETUP.md)** for detailed setup instructions. ## Requirements - Python >= 3.11 ## Install ```bash # From repository root pip install -e . # Or with uv uv pip install -e . ``` ## Configure envir
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.