Using GenMedia Creative Studio

GenMedia Creative Studio provides a centralized interface for experimenting with Google Cloud’s generative media models. The application is organized into three primary areas: Foundation models, Creative Workflows, and Studio management tools.

1. Navigating the Studio

• The Library: A centralized repository to browse, manage, and download all your generated media.
• Settings & Configuration: Manage your application settings, API configurations, and experimental feature flags.

2. Foundation Models (Direct Generation)

Interact directly with the raw generative models to create single-modality outputs.

• Image Generation:
  • Gemini Image Generation: Generate high-quality images from text prompts using Gemini (Nano Banana).
  • Edit Images: Edit existing images using powerful inpainting and outpainting tools.
• Video Generation:
  • Veo: Create high-fidelity videos from text or image prompts using Veo 2, Veo 3, and Veo 3.1.
• Audio & Speech Generation:
  • Lyria: Generate complex music tracks and thematic scores from text prompts.
  • Gemini TTS: Synthesize expressive and highly-controllable text-to-speech.
  • Chirp 3 HD: Generate high-definition speech from text.
• Text & Ideation:
  • Gemini (Writer’s Workshop): Collaborate with Gemini to brainstorm, refine, and structure your creative prompts.

3. Creative Workflows

Workflows are opinionated pipelines that chain multiple generative models together to accomplish specific, complex tasks.

• Virtual Try-On: A dedicated interface for virtually trying on clothing items across different generated models.
• Character Consistency: Maintain character identity across multiple video generations and image prompts.
• Shop the Look: Generate shoppable product imagery by combining product extraction and generated lifestyle scenes.
• Starter Pack: Quickly generate a cohesive visual moodboard (a “starter pack”) from a single central concept.
• Interior Design: Re-imagine interior spaces by generating 3D views from basic floor plans.
• Motion Portraits: Create animated, breathing portraits from a single still image.
• Object Rotation: Create 360-degree product videos from a single image.

4. Advanced Tools

• Pixie Compositor: A canvas to help you visually combine and arrange your generative media.
• Labs: A sneak peek at experimental features and odd things currently bubbling up in development.