# Image editing

Image editing allows your worker to modify images, apply filters, and perform similar image manipulation tasks. Toolhouse adds this capability automatically if your worker needs it to complete their task. You can also add it manually.

## How image editing works

You can create a worker that needs to edit images. For example, you can create a social media worker that posts on LinkedIn for you based on a branded banner with your company's logo. You want each post to have a different tagline for every post, but keep the same overall banner template. and a consistent color palette.

In this case, Toolhouse detects the worker will need to edit images and it will add Image Editing to it.

## Setting the style for edited images

To specify how the worker should edit images, open your agent in Agent Editor and tell the editor something like: "I want my worker to always apply a warm vintage filter and add a subtle vignette to every image". You can use natural language and Toolhouse will translate it into proper editing instructions for you.

## Edit an image generated earlier

Your worker can use Image Editing alongside [Image generation](/toolhouse/capabilites/image-generation.md) to modify images it previously created. For example, your worker can generate a hero image and then crop it to multiple aspect ratios for different platforms.

## Adding Image Editing manually

* Go to [Agents](https://toolhouse.app/agents) in your Toolhouse
* Click on your worker to edit it
* Select <i class="fa-wrench">:wrench:</i> **Integrations,** then click **Add Integration**
* Choose **Image Edit**
* Click **Save changes**


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.toolhouse.ai/toolhouse/capabilites/image-editing.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.