Asset Tap
Generate 3D models from text prompts

Getting Started

Set up your API key, launch Asset Tap, and generate your first 3D model from a text prompt.

Get an API Key

Asset Tap works in two AI-powered steps: first it generates an image from your text prompt (text-to-image), then it converts that image into a 3D model (image-to-3D). You'll need an API key from at least one provider that supports these models.

Included provider:

You can also add your own providers by creating YAML configuration files.

Launch the Application

Open Asset Tap from your Applications folder, Start Menu, or wherever you installed it. On first launch, you'll be prompted to enter your API key.

Generate Your First Model

  1. Enter a text prompt (e.g., "a cowboy ninja with a leather duster, bandana mask, and dual katanas on the back")
  2. Select your text-to-image model and image-to-3D model from the dropdowns
  3. Click Generate
  4. Review the AI-generated image and approve it for 3D conversion
  5. The image-to-3D model creates your 3D model -- preview it in the built-in viewer

That's it! Your generated assets are saved to a timestamped output directory. See Using Asset Tap for the full GUI guide, or Bundle Structure for the output format.

What's Next

  • Using Asset Tap -- Full GUI guide with viewer, library, and settings
  • Installation -- Download and install for your platform
  • CLI Usage -- Automate generation from the command line
  • Providers -- Available models and custom provider configuration
Installation →