Notebooks, code samples and sample apps showing how to build, deploy and manage ML and generative AI workflows on Google Cloud Vertex AI.
GoogleCloudPlatform/genmedia-creative-studio
A Python web app on Google Cloud's Vertex AI for generating images, video, music and speech with Gemini, Veo, Lyria and Chirp models.
- Stars
- 1,226
- Forks
- 377
- Open issues
- 16
- Last commit
- 22 hours ago
What is it?
GenMedia Creative Studio is a web application that gives a single interface to Google Cloud's generative media models. It covers image generation and editing with Gemini image models (Nano Banana variants) plus a virtual try-on feature, video generation with Gemini Omni and Veo, music generation with Lyria, and speech synthesis with Chirp 3 HD and Gemini Text to Speech.
Beyond raw model access, the app includes prebuilt workflows such as character consistency, shop-the-look, a starter-pack moodboard and an interior designer flow, along with an asset library for organizing outputs. It is built with Mesop, a Python framework for AI apps, on FastAPI, and runs locally with uv and Python 3.14 once a Google Cloud project with Vertex AI access is configured.
The project is provided as a demonstration and is not intended for production use. It includes Terraform-based deployment to Cloud Run, optional custom domains behind Identity Aware Proxy, and an experiments folder with stand-alone apps and MCP servers.
Key features
- 01Image generation and editing with Gemini image models, including virtual try-on.
- 02Video generation with Gemini Omni and Veo 3 / 3.1.
- 03Music generation with Lyria 3 and 2.
- 04Speech synthesis with Chirp 3 HD and Gemini Text to Speech.
- 05Prebuilt workflows for character consistency, shop the look and interior design, plus an asset library.
- 06Terraform deployment to Cloud Run with optional IAP and custom domains.
Use cases
- Prototyping creative workflows that combine image, video, music and voice on Vertex AI.
- Learning how to build a generative media web app with Mesop and FastAPI.
- Exploring Gemini, Veo, Lyria and Chirp APIs through a working UI.
- Using the experiments folder as a starting point for MCP-based media tools.
Quick start
- 1
Install uv (macOS/Linux) from the README
- 2
Authenticate to Google Cloud for Application Default Credentials
gcloud auth application-default login - 3
Sync dependencies with uv
uv sync - 4
Run the app, then open http://localhost:8080/
uv run main.py
Things to know
- Requires Python 3.14+ and a Google Cloud project with Vertex AI access.
- Generation calls go to Vertex AI, so usage is billed to your Google Cloud account.
- The README says it is for demonstration only and not for production use.
- This is not an officially supported Google product.
In collections
Topics
FAQ
- What is genmedia-creative-studio?
- A Python web app on Google Cloud's Vertex AI for generating images, video, music and speech with Gemini, Veo, Lyria and Chirp models. GenMedia Creative Studio is a web application that gives a single interface to Google Cloud's generative media models. It covers image generation and editing with Gemini image models (Nano Banana variants) plus a virtual try-on feature, video generation with Gemini Omni and Veo, music generation with Lyria, and speech synthesis with Chirp 3 HD and Gemini Text to Speech.
- Is genmedia-creative-studio free to use? What license does it have?
- genmedia-creative-studio is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is genmedia-creative-studio still maintained?
- Actively maintained. The last commit to genmedia-creative-studio was on Nov 5, 2026.
- What can I use genmedia-creative-studio for?
- Prototyping creative workflows that combine image, video, music and voice on Vertex AI. Learning how to build a generative media web app with Mesop and FastAPI. Exploring Gemini, Veo, Lyria and Chirp APIs through a working UI. Using the experiments folder as a starting point for MCP-based media tools.
- How do I install genmedia-creative-studio?
- Install uv (macOS/Linux) from the README Authenticate to Google Cloud for Application Default Credentials: gcloud auth application-default login Sync dependencies with uv: uv sync Run the app, then open http://localhost:8080/: uv run main.py
- Where can I get genmedia-creative-studio?
- The source code and installation instructions are on GitHub: https://github.com/GoogleCloudPlatform/genmedia-creative-studio
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source generative AI platform offering a unified API for text, image, video, audio, 3D and embeddings generation.
A self-hosted desktop app for building AI image and video generation pipelines visually on an infinite node-based canvas, using your own kie.ai key.
A collection of agent skills that teach AI coding agents to generate images, video, audio and 3D through the Scenario MCP server, plus skills that drive DCC tools and game engines.
Agent skills that let Claude Code, Cursor, Codex and similar coding agents generate images and video, train face identities, and build brand kits via Higgsfield AI.
A Gradio-based web UI for running Stable Diffusion and newer image/video models, continuing the Forge fork with added model support and optimizations.