This is not an officially supported Google product. This project is not eligible for the Google Open Source Software Vulnerability Rewards Program. This project is intended for demonstration purposes only. It is not intended for use in a production environment.
- GenMedia Creative Studio | Vertex AI
- Table of Contents
- GenMedia Creative Studio
- Documentation Hub
- Experiments & MCP Tools
- Contributing changes
- Licensing
- Disclaimer
Browser Compatibility: For the best experience, we recommend using Google Chrome. Some features may not work as expected on other browsers, such as Safari or Firefox.
GenMedia Creative Studio is a web application showcasing Google Cloud's generative media - Veo, Lyria, Gemini Image Generation (Nano Banana), Chirp 3 HD, and Gemini TTS along with custom workflows and techniques for creative exploration and inspiration. We're looking forward to see what you create!
Current featureset:
- Image: Gemini Flash Image Generation (Nano Banana 2), Gemini 3 Pro Image (Nano Banana Pro), Virtual Try-On
- Video: Veo 3.1, Veo 3, Veo 2
- Music: Lyria 3 & 2
- Speech: Chirp 3 HD, Gemini Text to Speech
- Workflows: Character Consistency, Shop the Look, Starter Pack Moodboard, Interior Designer
- Asset Library
This is built using Mesop, an open source Python framework used at Google for rapid AI app development, and the scaffold for Studio style apps.
For comprehensive guides, deployment instructions, architecture details, and developer workflows, please visit our Documentation Hub.
Stay up-to-date with upcoming breaking changes and releases on our Changelog & Notices page.
If you want to quickly run the UI without having to set up a local development environment, use Cloud Shell and follow the tutorial instructions:
The application is designed to be deployed using Terraform and Cloud Run. You have the flexibility to deploy using a custom domain (with Identity Aware Proxy and a Load Balancer) or using the autogenerated Cloud Run domain.
For detailed, step-by-step instructions on setting up your environment, configuring custom domains, and managing Identity Aware Proxy (IAP), please see the Deployment Guide on our Documentation Hub.
The experiments/ folder contains a variety of stand-alone applications, new workflows, and Model Context Protocol (MCP) servers that showcase cutting-edge capabilities with generative AI. This includes combined workflows for video generation, advanced prompting techniques, image recontextualization, and audio exploration.
To explore the available experiments, view architecture diagrams, and find installation instructions for our MCP tools, head over to the Experiments Section of our Documentation Hub.
Interested in contributing? Please open an issue describing the intended change. Additionally, bug fixes are welcome, either as pull requests or as GitHub issues.
See CONTRIBUTING.md for details on how to contribute.
Code in this repository is licensed under the Apache 2.0. See LICENSE.
Caution
This is not an officially supported Google product. This project is not eligible for the Google Open Source Software Vulnerability Rewards Program.