Notes:

  1. API Key: Saved in your browser local storage. Not sent anywhere except to Google.
  2. Sequential Processing: The default mode processes all images in a single, fast API call. Enable Process Sequentially to analyze each image one-by-one. This is slower and uses more API credits, but can sometimes yield more detailed individual analyses.
  3. Positioning: Use the Enable Positional Control checkbox to turn this feature on/off for all Subject and Scene inputs.
  4. Multiple Inputs: Click `+` in any column to add another input for that category (up to 3 each).
  5. Prompt Enrichment: Add extra keywords or instructions that will be appended to the final prompt.
  6. Formatting Options: Format as Single Paragraph is for Caption mode only. Both JSON modes always output a JSON object.

Options

Usage Instructions:

  1. Get your API key from Google AI Studio and paste it below.
  2. Use the main checkboxes to enable/disable entire categories.
  3. Click `+` in a column to add more images for that category.
  4. For Subjects/Scenes, click "Choose Position" to direct placement.
  5. Select your Generation Type, model, and creativity.
  6. Click "Create Scene" to begin.