# 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.

Repository: https://github.com/GoogleCloudPlatform/vertex-ai-creative-studio
Canonical: https://ross.abutalabs.com/products/vertex-ai-creative-studio
Homepage: https://googlecloudplatform.github.io/vertex-ai-creative-studio/
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: google-cloud, vertex-ai, gemini, nano-banana, chirp, lyria, veo, gemini-tts, gemini-omni
Last push: 2026-09-02T08:24:17+00:00

## Health v2 (maintenance only)
Score: 90/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 99, longevity 53
- inputs: {"age_days": 748, "days_push": 0, "days_rel": 4, "gap_med": 0.0, "n_releases_24m": 59}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1199, forks 367 (observed 2026-09-03T02:15:06.057427+00:00)

## What it is
GenMedia Creative Studio is a web application showcasing Google Cloud's generative media APIs including Gemini Image (Nano Banana), Veo video generation, Lyria music, and Gemini TTS/Chirp 3 speech. Built with the Mesop Python framework, it provides creative workflows like character consistency and virtual try-on, plus MCP servers for programmatic access to media generation models.

## Use cases
- generate images with gemini nano banana on vertex ai
- create videos with veo 3 from text prompts
- generate music with lyria api
- convert text to speech with gemini tts or chirp 3
- build character consistency workflows for creative projects
- try mcp tools for generative media models
- demo generative ai media capabilities on google cloud

## When to choose
- you want a ready-made web UI to explore Google Cloud generative media APIs
- you need example workflows and prompt techniques for Veo, Lyria, or Gemini Image
- you want MCP servers to expose media generation to AI agents
- you are prototyping creative AI applications on Vertex AI

## When to avoid
- you need a production-ready application - it is explicitly for demonstration purposes only
- you use browsers other than Chrome, as some features may not work
- you are not using Google Cloud / Vertex AI as your model provider

## Facets
- artifact type: application
- maturity: active
- function: image-processing, video-processing, audio-processing, tts, llm-inference, mcp, prompt-engineering, web-framework
- domain: artificial-intelligence, large-language-models, image-processing, media, cloud-computing, developer-tools
- platform: python, cloud, self-hosted
- tags: generative-media, gemini, vertex-ai, veo, lyria, nano-banana, text-to-speech, demo-app, google-cloud, video, audio, web-server, docker

## Member repositories
- GoogleCloudPlatform/vertex-ai-creative-studio (main) score 90

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:06.057427+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:22:27.334164+00:00, confidence not recorded.
  - readme: https://github.com/GoogleCloudPlatform/vertex-ai-creative-studio (fetched 2026-09-03T02:15:06.057427+00:00, sha e9597e3c3a15)
  - homepage: https://googlecloudplatform.github.io/vertex-ai-creative-studio/ (fetched 2026-08-29T12:29:51.572686+00:00, sha 39a2793edc82)
- Data as of 2026-08-30T08:39:29.467469+00:00.