Generating image descriptions using Claude

Use image description to generate alt text and visual summaries from images.

Common use cases include:

Accessibility workflows for screen readers
Digital asset cataloging
Document enrichment for scanned reports
E-learning content description
Archive and metadata generation

This guide uses Claude as the VLM provider through Nutrient Vision API.

Download sample

How Nutrient helps

Nutrient Java SDK handles provider configuration, request handling, and response parsing.

The SDK handles:

VLM API authentication, endpoint configuration, and request formatting
Image encoding and multimodal API request structures
Model parameters such as temperature, max tokens, and provider-specific settings
Vision service failures and API rate limits

Complete implementation

This example generates an image description using Claude:

package io.nutrient.Sample;

Import the required classes and define the sample class:

import io.nutrient.sdk.Document;
import io.nutrient.sdk.Vision;
import io.nutrient.sdk.enums.VlmProvider;
import io.nutrient.sdk.exceptions.NutrientException;
import io.nutrient.sdk.settings.ClaudeApiSettings;
import io.nutrient.sdk.settings.VisionSettings;

import java.io.FileWriter;
import java.io.IOException;

public class DescribeImageWithClaude {

Configuring the Claude provider

Create the main method, open the image in try-with-resources, and configure Claude.

In this sample:

setProvider(VlmProvider.Claude) selects Claude.
setApiKey("CLAUDE_API_KEY") sets the Anthropic API key.
Input can be PNG, JPEG, GIF, BMP, or TIFF.

    public static void main(String[] args) throws NutrientException, IOException {

Creating a vision instance and generating the description

Create a vision instance and call describe() to generate text.

In this sample:

Vision.set(document) binds processing to the opened image.
vision.describe() returns a description string.
The SDK handles encoding, request construction, and response parsing.

        try (Document document = Document.open("input_photo.png")) {
            // Configure Claude as the VLM provider
            VisionSettings visionSettings = document.getSettings().getVisionSettings();
            visionSettings.setProvider(VlmProvider.Claude);

            // Set the Claude API key
            ClaudeApiSettings claudeSettings = document.getSettings().getClaudeApiSettings();
            claudeSettings.setApiKey("CLAUDE_API_KEY");

Saving the description

Write the description to a text file.

This sample uses try-with-resources for both document and file writer cleanup:

            Vision vision = Vision.set(document);
            String description = vision.describe();

            try (FileWriter writer = new FileWriter("output.txt")) {
                writer.write(description);
            }
        }
    }
}

Understanding the output

describe() returns natural language text for accessibility and content understanding.

Claude descriptions are typically:

Concise — Focused on key subjects and details, often one to three sentences
Accessible — Suitable for users who rely on screen readers
Accurate — Based on visible content only
Contextual — Include relevant relationships and scene context

Use this output for accessibility metadata, image search, and document workflows.

Claude API settings

The Claude provider uses these ClaudeApiSettings properties:

ApiEndpoint — The Claude API endpoint (default: https://api.anthropic.com/v1/).
ApiKey — Your Anthropic API key for authentication.
Model — The model identifier to use (default: claude-sonnet-4-5).
Temperature — Controls response creativity (0.0 = deterministic, 1.0 = creative).
MaxTokens — Maximum tokens in the response (default: 16384).

Error handling

The sample can throw:

NutrientException for vision and API issues
IOException for file I/O operations

Common failure scenarios include:

The input image can’t be read due to path, permission, or format issues
The Claude API key is missing or invalid
The Claude API is unavailable
Rate limits are exceeded
Network requests fail before reaching the API
Image data is too large or corrupted
File writing fails due to path, disk, or permission issues

In production code:

Catch NutrientException and IOException.
Return clear error messages.
Log failure details for debugging.
Add retry logic for transient API failures.

Conclusion

Use this workflow to generate image descriptions with Claude:

Open the image file using try-with-resources for automatic resource cleanup.
The SDK supports multiple image formats, including PNG, JPEG, GIF, BMP, and TIFF.
Retrieve the vision settings with document.getSettings().getVisionSettings() to configure the VLM provider.
Set the provider to Claude with setProvider(VlmProvider.Claude) instead of alternatives like OpenAI or local models.
Retrieve Claude-specific settings with document.getSettings().getClaudeApiSettings() for API configuration.
Set the Anthropic API key with setApiKey() using credentials obtained from the Anthropic Console.
Claude API settings control endpoint URLs, model selection (default: claude-sonnet-4-5), temperature, and max tokens.
Create a vision instance with Vision.set() bound to the document with configured provider settings.
Generate the description with vision.describe(), which sends the image to Claude’s vision endpoint and returns natural language text.
The SDK encodes image data, constructs multimodal API requests, and parses responses automatically.
Generated descriptions are concise (1–3 sentences), accessible (WCAG-compliant alt text), accurate (observable details only), and contextual.
Write the description to a file using try-with-resources with FileWriter for automatic resource cleanup.
Handle NutrientException for vision processing failures, including authentication errors, API failures, and rate limits.
Handle IOException for file operations, including read failures or write errors when saving output.

For related image workflows, refer to the Java SDK guides.

Download this ready-to-use sample package to explore Claude-based image description.