Short captions in German with a focus

What this example returns

The dataset’s “Descriptions” view shows 9 columns: Image, Caption, Alt text, Tags, Visible text, Width, Height, Status, and Error. See every output field.

What each setting does

The input this example runs AI Image Describer: Captions, Alt Text & Tags with. “Try this input” opens it in the console, where you can run it as-is or change any field first.

Image links images

https://images.unsplash.com/photo-1518791841217-8f162f1e1131?w=640, https://images.pexels.com/photos/1108099/pexels-photo-1108099.jpeg?auto=compress&w=640

Images to describe, one per line: links to JPEG, PNG, WebP, GIF, BMP, TIFF, AVIF or HEIC files, or pasted image data (data:image/png;base64,...). Product photos, screenshots, social media pictures, scans. Leave empty when you upload files or read a dataset below.

Detail level detailLevel

Low: one short sentence

How long the caption is. Low: one short sentence. Medium: two or three sentences. High: a detailed paragraph (objects, people, setting, colours, lighting, composition, mood).

Default: High: a detailed paragraph → this example uses Low: one short sentence

Focus (optional) focus

describe the animals and where they are

Point the description at what matters to you, for example "describe the product, its colour and material", "only the background" or "what the people are doing".

Alt text altText

No

A short alt text of at most 125 characters for screen readers and image SEO.

Default: Yes → this example uses No

Visible text visibleText

No

All readable text in the image (signs, labels, logos, screenshots) as written. Empty when the image has no text.

Default: Yes → this example uses No

Output language language

German

The language of the caption, alt text and tags, for example English, German, Spanish or Japanese. Visible text stays as written in the image.

Default: English → this example uses German

{
  "images": [
    "https://images.unsplash.com/photo-1518791841217-8f162f1e1131?w=640",
    "https://images.pexels.com/photos/1108099/pexels-photo-1108099.jpeg?auto=compress&w=640"
  ],
  "detailLevel": "low",
  "language": "German",
  "focus": "describe the animals and where they are",
  "altText": false,
  "visibleText": false
}

What it costs

You pay for the events the actor reports, such as each result or page it produces, plus the platform usage of your runs: compute, proxies and storage. Platform usage is typically about $0.269 per 1,000 results.

• Described image$0.0095One image described and saved: caption at the chosen detail level, plus the alt text, tags and visible text you chose. Images that could not be described are free.

Full pricing

When to use this example

From the AI Image Describer: Captions, Alt Text & Tags readme:

Other ways to run AI Image Describer: Captions, Alt Text & Tags

• Photos, a logo and a sign, detailedTwo photos, a transparent logo image and a pasted sign image: a detailed caption, alt text, tags and the sign's text for each.
• Medium captions, another model, bad linksTwo to three sentences per image with google/gemini-3.1-flash-lite, Max images 5, and examples of links that cannot be described (each gets a free row saying why).

All examples of AI Image Describer: Captions, Alt Text & Tags

About AI Image Describer: Captions, Alt Text & Tags

Describe any image with AI: detailed captions, SEO alt text, keyword tags and the text visible in the picture. Image links, uploads or the images in another run's results, in any language.

Price:

$9.50 / 1,000 results

Developer:

Echofield

Categories:

AI, E-commerce, SEO tools

AI Image Describer: Captions, Alt Text & Tags pageOutput fieldsPricing