# Image to Environment Map

## Overview

The **Image to Environment Map** tool generates HDR environment maps by using a reference image and a text-based description. It allows users to create detailed 3D environments based on image inputs and text prompts. The tool offers control over the inclusion or exclusion of specific elements and can produce varied results using a random seed value.

## Tool Inputs

<figure><img src="https://3763251240-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F9BAa74uZVvvtnO0Rq9Vh%2Fuploads%2Fgit-blob-15a359a8e8b00f99a0c4d3451076b62cb4561ea2%2Fimage-to-environment-map.png?alt=media" alt=""><figcaption><p>Image to Environment Map tab</p></figcaption></figure>

Inputs :

* **Reference Image:** The image used as reference to create HDR environment.
* **Text Prompt:** Text description of the desired HDR environment.
* **Negative Prompt:** The elements to exclude from the HDR environment.
* **Seed:** A random number used for generating varied outputs with identical inputs. For instance, two HDR environments with different seeds, might differ even with the same reference image, text prompt and negative prompt.

{% hint style="info" %}
For optimal results, ensure the reference image has the horizon positioned around the **middle**, a field of view (FoV) close to **60** degrees, and a **1:1** aspect ratio. If a different aspect ratio is used, make sure the key point of interest is centrally located to prevent any loss of important information and ensure the accuracy of the generated HDR environment map.
{% endhint %}


---

# 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.realtwin.org/virtual-productions-cloud/vpc-plugin/toolkits/environment-toolkit/tools/image-to-environment-map.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.