AI Image Analyzer

An Apify Actor that analyzes images using NVIDIA NIM's Llama 3.2 90B Vision model for detailed visual understanding and description.

What This Actor Does

This AI Image Analysis Tool leverages NVIDIA NIM (NVIDIA Inference Microservice) and the Llama 3.2 90B Vision model to provide comprehensive image understanding. Provide any image URL and receive detailed, intelligent descriptions.

Key Capabilities

• AI-Powered Image Recognition - Advanced computer vision analysis
• Automated Image Captioning - Generate descriptive text from visuals
• Visual Content Analysis - Understand colors, composition, and subjects
• Technical Image Assessment - Evaluate quality, lighting, and camera settings
• Creative Interpretation - Extract mood, emotions, and artistic elements

How to Use

Input Parameters

Parameter	Type	Required	Default	Description
imageUrl	string	Yes	-	URL of image (JPEG, PNG, GIF, WebP, Google Drive)
analysisType	string	No	general	Analysis mode: general, detailed, technical, creative
customPrompt	string	No	-	Override with custom analysis instructions

Analysis Types

General Analysis

Perfect for quick, balanced descriptions:

{
  "imageUrl": "https://example.com/photo.jpg",
  "analysisType": "general"
}

Detailed Analysis

Comprehensive breakdown of all visual elements:

{
  "imageUrl": "https://example.com/photo.jpg",
  "analysisType": "detailed"
}

Technical Analysis

Professional photography assessment:

{
  "imageUrl": "https://example.com/photo.jpg",
  "analysisType": "technical"
}

Creative Analysis

Artistic interpretation and mood analysis:

{
  "imageUrl": "https://example.com/photo.jpg",
  "analysisType": "creative"
}

Output Format

{
  "imageUrl": "https://example.com/photo.jpg",
  "analysisType": "general",
  "analysisResult": "A woman in a light green formal dress...",
  "modelUsed": "meta/llama-3.2-90b-vision-instruct",
  "processingTime": 10.147,
  "timestamp": "2026-01-28T17:47:13.458Z"
}

Setup

Prerequisites

1. NVIDIA API Key: Get your API key at build.nvidia.com
2. Apify Account: Sign up at apify.com

Configuration

Set your NVIDIA API key as an environment variable:

$NVIDIA_API_KEY=nvapi-your-key-here

Or use the prefill value in the Actor input.

Advanced Features

Google Drive Support

Directly analyze images from Google Drive sharing links - no manual download needed.

Custom Prompts

Override default analysis with your own instructions:

{
  "imageUrl": "https://example.com/photo.jpg",
  "customPrompt": "Describe the architectural style and building materials"
}

Example Results

Input: Fashion photo

Output: The image depicts a woman in a formal, elegant setting. She is dressed in a stunning light green dress with a V-neckline and ruffled high-low hem. The dress features thin straps and a side slit. She accessorizes with a gold necklace and bracelet, complemented by white high-heeled shoes. The background shows a light beige wall with decorative molding and dark wood flooring, suggesting an upscale indoor venue suitable for formal events.

Integration Examples

Python

from apify_client import ApifyClient

client = ApifyClient('YOUR_API_TOKEN')
run = client.actor('akash9078/analyze-image').call(run_input={
    'imageUrl': 'https://example.com/image.jpg',
    'analysisType': 'general'
})

JavaScript

const { ApifyClient } = require('apify-client');

const client = new ApifyClient({ token: 'YOUR_API_TOKEN' });
const run = await client.actor('akash9078/analyze-image').call({
    imageUrl: 'https://example.com/image.jpg',
    analysisType: 'general'
});

cURL

curl -X POST https://api.apify.com/v2/acts/akash9078~analyze-image/runs \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"imageUrl":"https://example.com/image.jpg","analysisType":"general"}'

API Reference

Supported Image Formats

• JPEG/JPG
• PNG
• GIF
• WebP
• Google Drive links (automatic conversion)

Rate Limits

• Processing time: ~10-30 seconds per image
• Concurrent runs: Based on Apify plan limits

License

Apache-2.0 License