Notes:

  1. API Key: Saved in your browser local storage. Not sent anywhere except to Google.
  2. Sequential vs. Batch: The default mode processes all images in fast batches. Enable Process Sequentially to analyze each image one-by-one. This is slower and uses more API credits, but is necessary for a per-image delay.
  3. Generation Types: Choose 'Caption' for sentences, 'Tags' for keywords, or 'Weight Brief' for prompts formatted for AI image generation (e.g., `(word:1.2)`).
  4. Kohya_SS Export: When enabled, this creates a ZIP file with a folder structure and text files ready for training LoRA models.
  5. Auto Rename: Automatically renames image files and their corresponding text files to sequential numbers (e.g., 1.png, 1.txt) in the downloaded ZIP.

Options

Usage Instructions:

  1. Get your API key from Google AI Studio and paste it in the options.
  2. Click or drag-and-drop your images into the upload area.
  3. Select your desired Generation Type, Model, and Creativity level.
  4. Add optional Trigger Words or Prompt Enrichments.
  5. Enable any specific processing or export options (like Kohya_SS).
  6. Click "Start" to begin processing.
  7. Once complete, review the results and click "Download as ZIP".