GoogleCloudPlatform/vertex-ai-creative-studio

GenMedia Creative Studio is a generative media user experience highlighting the use of Gemini, Gemini Omni, Veo, Gemini Image 🍌, Gemini TTS, Chirp 3, Lyria and other generative media APIs on Google Cloud.

What it solves

It provides a centralized web application for exploring and experimenting with Google Cloud's suite of generative media models. It simplifies the process of testing various AI-driven creative workflows—such as maintaining character consistency or designing interiors—without needing to build separate interfaces for each model.

How it works

Built with the Mesop Python framework and FastAPI, the application serves as a frontend that interfaces with Vertex AI. It allows users to trigger generations across multiple modalities, including image (Nano Banana), video (Veo), music (Lyria), and speech (Chirp 3 HD and Gemini TTS). It also includes a set of custom workflows and an asset library to manage generated content.

Who it’s for

Creative professionals and developers who want to explore the capabilities of Google's generative media models and test creative workflows in a visual, interactive environment.

Highlights

  • Multimodal Support: Integrated access to image, video, music, and speech generation models.
  • Creative Workflows: Specialized tools for tasks like "Shop the Look," "Character Consistency," and "Interior Designer."
  • ** uma Virtual Try-On**: Built-in capability for virtual clothing trials.
  • Experimental Tools: Includes a collection of standalone applications and Model Context Protocol (MCP) servers for advanced AI exploration.

Related

  • Project
    yangjian102621/geekai

    A multimodal AI content creation platform that integrates text, image, audio, and video generation tools into a single commercial-ready workspace.

  • Project
    GoogleCloudPlatform/genai-for-marketing

    A Google Cloud-based solution that automates marketing content generation, trend analysis, and data querying using Vertex AI and Google Workspace integration.

  • Project
    ashuoAI/SHUO-Canvas

    A multimodal AI creation canvas that uses a node-based interface to connect text, images, video, and audio for complex creative projects.

  • Project
    statmike/vertex-ai-mlops

    A comprehensive collection of 470+ interactive notebooks demonstrating end-to-end MLOps, generative AI, and agent development workflows on Google Cloud Platform.

  • Project
    higgsfield-ai/cli

    A command-line interface for the Higgsfield AI platform that enables the generation of images, videos, 3D assets, and audio using 40+ models, alongside tools for training custom characters and deploying AI websites.