Design briefs and visual communication

Free Image Caption Generator.

Accurate caption distinguishing observation from inference.

Write a caption grounded in the image and the story details you provide, without inventing identities or events.

Chrome extension + account required.
25 free automation tasks/month across tools. Browser-provider limits apply.

WHAT TO HAVE READY

User-provided image and publication context.

YOUR STARTING POINT

A task you can make yours.

Copy it here. Paste it into WebAct when you are ready.

This page prepares your prompt. The task runs in WebAct.

01

Make the task yours.

Review the prompt above. Add your goal and any requirements that matter.

02

Bring it to WebAct.

Open WebAct with your browser ChatGPT connection, supply the image and paste the task. Include the context in which the description or review will be used.

03

Check the useful part.

Supply the image through an available browser ChatGPT connection. Review descriptions against the image, especially small text and details that are difficult to see.

A PRACTICAL GUIDE

How to use the Image Caption Generator.

An image caption should connect visible content to the surrounding story. Add names, dates or locations only when supplied, and avoid treating an interpretation as an observed fact.

Make the workflow fit your task.

Describe the visible subject or action and connect it to supplied story context. Add names, place or date only when verified. Keep interpretation distinct from observation and choose a length appropriate to the publication.

What you provide
User-provided image and publication context.
What you get
Accurate caption distinguishing observation from inference.

See the input and the result.

Illustrative input and output · a teaching example, not a live WebAct run

Example input

Photo shows three people planting a sapling; no names or location are provided.

Completed example

Three people plant a sapling together.
If the caption needs an event name or location, request those details rather than inferring them from the image.
Download this example

Load this input into the prompt, then copy it to WebAct to try the task. Your result may differ from the illustration.

Decisions and troubleshooting.

Should a caption infer a person's identity or location from appearance?

Use supplied, verified context rather than guessing those details from the image.

Why does the caption repeat the adjacent headline without adding information?

It may ignore the image's specific contribution. Describe the relevant visible detail or verified context the reader would otherwise miss.

Try it with your own source.

Replace the example with your material in the task prompt. Keep the requirements you need, then copy the task into WebAct.

Customize and copy the task ↑
BEFORE YOU BEGIN

Using WebAct.

The prompt and example are available here. Run your task in the WebAct Chrome extension.

Is this tool free?

You can copy and edit the prompt here for free. To use it with WebAct, install the Chrome extension, create and verify your account, and connect an available browser ChatGPT session. The Free plan includes 25 user-started automation tasks per calendar month, shared across tools. Ordinary browser Chat is separate; provider limits apply.

Learn about shared context in our privacy policy and choosing Chat or Task.

FROM A PROMPT TO YOUR OWN WORK

Bring the task to your page.

Install WebAct, add your source material and make the result yours.

Install WebAct