Image Support

Features

• Image Analysis: Describe, analyze, and extract information from images
• Multiple Formats: PNG, WEBP, JPG, JPEG, GIF, BMP, TIFF, ICO
• Flexible Input: Local files, remote URLs, or data URIs
• Auto-Conversion: Automatic format conversion and resizing
• Drag & Drop: Easy upload in the web UI

Using Images in CLI

# Local image file
llms --image ./screenshot.png "What's in this image?"

# Remote image URL
llms --image https://example.com/photo.jpg "Describe this photo"

# Data URI
llms --image "data:image/png;base64,$(base64 -w 0 image.png)" "Analyze this"

# With specific vision model
llms -m gemini-2.5-flash --image chart.png "Analyze this chart"

# Combined with system prompt
llms -s "You are a data analyst" --image graph.png "What trends do you see?"

Using Images in UI

Simply drag and drop images into the chat or click the attach button to upload.

Vision-Capable Models

Popular models that support image analysis:

• OpenAI: GPT-4o, GPT-4o-mini, GPT-4.1
• Anthropic: Claude Sonnet 4.0, Claude Opus 4.1
• Google: Gemini 2.5 Pro, Gemini Flash
• Qwen: Qwen2.5-VL, Qwen3-VL, QVQ-max
• Ollama: qwen2.5vl, llava

Custom Image Template

Use custom chat templates for image requests:

{
  "model": "qwen2.5vl",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": ""
          }
        },
        {
          "type": "text",
          "text": "Caption this image"
        }
      ]
    }
  ]
}

llms --chat image-request.json --image photo.jpg

Image Limits & Auto-Conversion

Configure image size limits and auto-conversion in llms.json:

{
  "convert": {
    "max_image_size": 2048,
    "max_image_length": 20971520,
    "webp_quality": 90
  }
}

• Images exceeding max_image_size pixels are resized
• Images exceeding max_image_length bytes are converted to WebP
• Quality controlled by webp_quality (0-100)

Use Cases

• Product Analysis: Describe products from images
• Chart Reading: Extract data from charts and graphs
• Document OCR: Extract text from images of documents
• Visual Q&A: Answer questions about image content

Tips for Best Results

• Use high-quality images for better analysis
• Crop to focus on relevant content
• Use appropriate models for the task (e.g., Gemini for diagrams)

Next Steps