> For the complete documentation index, see [llms.txt](https://docs.airops.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.airops.com/actions/playbooks/tools/image-and-video.md).

# Image & Video

Use image and video tools to generate hosted visual assets for Playbook outputs

Image & Video Tools help Playbooks create and retrieve visual assets that downstream systems can reference. Use them when a Playbook needs a generated image, a stock image, or a hosted image URL for a CMS, landing page, social post, or content artifact.

## Tools

### Image Generation

Generate hosted images with GPT Image 2.5 Sunburst, GPT Image 2.5 Flare, GPT Image 2, or Nano Banana 2. Hosted image outputs are useful when a downstream Tool publishes content to a CMS or stores a finished artifact.

Use **Image Generation** when a Playbook needs a new image or an edited source image. Request Sunburst for precision or Flare for faster everyday generation. New image steps prefer Flare when you do not request a model. Existing GPT Image 2 steps keep their configuration.

For GPT Image 2.5, request **Low**, **Medium**, **High**, or **Auto** quality. Custom width and height must be divisible by 16, with no edge above 3840 pixels, an aspect ratio between 1:3 and 3:1, and a total size between 655,360 and 8,294,400 pixels.

### Search Stock Images

Search Getty Images or Unsplash for relevant stock photography. Use **Search Stock Images** when a Playbook needs sourced imagery instead of generated imagery.

### Fetch Stock Image with ID

Fetch a specific stock image from Getty Images or Unsplash by its image ID. Use this after a search step when the Playbook has selected the image that should appear in the final Artifact or downstream publish action.

## How to Configure

1. Open the Playbook editor.
2. Type `/` in the Section where the visual should be created.
3. Select **Image Generation**, **Search Stock Images**, or **Fetch Stock Image with ID**.
4. Describe the image subject, style, source, aspect ratio, dimensions, and usage context.
5. Tell the Playbook where to use the hosted image URL in the final artifact.

## Parameters

| Tool                          | Required context                | Optional guidance                                                                                                      |
| ----------------------------- | ------------------------------- | ---------------------------------------------------------------------------------------------------------------------- |
| **Image Generation**          | Prompt describing the image     | Add model preference, dimensions, image format, quality, number of images, source image, mask, or editing instructions |
| **Search Stock Images**       | Search query and stock provider | Add image style, subject, orientation, usage rights, or result count                                                   |
| **Fetch Stock Image with ID** | Image ID and stock provider     | Add requested size or downstream placement                                                                             |

## Examples

```markdown
Use **Image Generation** with GPT Image 2.5 Flare to create a 1536x864 hero image for the article. Match the Brand Kit visual guidelines and return the hosted image URL.
```

```markdown
Use **Search Stock Images** to find a horizontal Unsplash image for the article hero. Select the image that best matches the Brand Kit visual guidelines, then use **Fetch Stock Image with ID** to return the hosted image URL.
```


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

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

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.airops.com/actions/playbooks/tools/image-and-video.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.