Skip to main content

Vision & Multimodal Capabilities

GoingMerry supports vision capabilities using multimodal models (such as llava, bakllava, or standard vision configurations). You can submit images alongside text prompts to perform OCR, image captioning, and visual QA.

1. Request Format​

Submit image data by encoding your target image as a base64 string and passing it inside the images array parameter of the /api/generate or /api/chat request body.

curl Example​

curl http://localhost:11434/api/generate -d '{
  "model": "llava",
  "prompt": "What is in this image?",
  "stream": false,
  "images": [
    "iVBORw0KGgoAAAANSUhEUgAAAG0AAABmCAYAAADBPx+VAAAACXBIWXMAAAsTAAALEwEAmpwY..."
  ]
}'

2. Supported Image Formats​

GoingMerry automatically decodes standard image formats, including:

  • PNG
  • JPEG
  • WebP

Always ensure that you strip any URI data headers (such as data:image/png;base64,) from your base64 string before submitting the payload.