Quick Start

# Install dependencies in your project directory
# pip install moondream

import moondream as md
from PIL import Image

# Initialize with API key
model = md.vl(api_key="your-api-key")

# Load an image
image = Image.open("./path/to/image.jpg")
encoded_image = model.encode_image(image)  # Encode image (recommended for multiple operations)


# Generate a caption (length options: "short" or "normal" (default))
caption = model.caption(encoded_image)["caption"]
print("Caption:", caption)

# Stream the caption
for chunk in model.caption(encoded_image, stream=True)["caption"]:
    print(chunk, end="", flush=True)

# Ask a question
answer = model.query(encoded_image, "What's in this image?")["answer"]
print("Answer:", answer)

# Stream the answer
for chunk in model.query(encoded_image, "What's in this image?", stream=True)["answer"]:
    print(chunk, end="", flush=True)

# Detect objects
detect_result = model.detect(image, 'subject')  # change 'subject' to what you want to detect
print("Detected objects:", detect_result["objects"])

# Point at an object
point_result = model.point(image, 'subject')  # change 'subject' to what you want to point at
print("Points:", point_result["points"])

// Install dependencies in your project directory
// npm install moondream
const { vl } = require('moondream');
const fs = require('fs');

async function main() {
const model = new vl({
	apiKey: "your-api-key"
});

// Load an image
const encodedImage = Buffer.from(fs.readFileSync("./path/to/image.jpg"))  // Load and encode image

// Generate caption (length options: "short" or "normal" (default))
const caption = await model.caption({ image: encodedImage })
console.log("Caption:", caption)

// Stream the caption
process.stdout.write("Streaming caption: ")
const captionStream = await model.caption({ image: encodedImage, stream: true })
for await (const chunk of captionStream.caption) process.stdout.write(chunk)

// Ask questions about the image
const answer = await model.query({ image: encodedImage, question: "What's in this image?" })
console.log("\nAnswer:", answer)

// Stream the answer
process.stdout.write("Streaming answer: ")
const answerStream = await model.query({ image: encodedImage, question: "What's in this image?", stream: true })
for await (const chunk of answerStream.answer) process.stdout.write(chunk)

// Detect objects
const detectResult = await model.detect({ image: encodedImage, object: "subject" })  // change 'subject' to what you want to detect
console.log("Detected objects:", detectResult.objects)

// Point at an object
const pointResult = await model.point({ image: encodedImage, object: "subject" })  // change 'subject' to what you want to point at
console.log("Points:", pointResult.points)

}

main().catch(console.error);