> For the complete documentation index, see [llms.txt](https://help.vectary.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.vectary.com/canvas/overview.md).

# Canvas overview

Vectary Canvas is an infinite canvas where you collect references, generate images, video and 3D with AI presets, and turn ideas into concepts, all in one place.

{% hint style="info" icon="rectangle-beta" %}
Vectary Canvas is currently in **Beta**. We're actively improving it, and some features may change.
{% endhint %}

{% embed url="<https://screen.studio/share/8dJUasny>" %}

### What you can do with Canvas

{% columns %}
{% column width="16.666666666666664%" %}

<div align="left"><figure><img src="https://2973737105-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FAXNLyKVZ2tvtyDr8sVES%2Fuploads%2FViTDbGT8dVrPruDfzcJ5%2Fimage.png?alt=media&amp;token=32b302e1-a3cd-49d2-9263-91dd65bcd28b" alt="" width="65"><figcaption></figcaption></figure></div>
{% endcolumn %}

{% column width="83.33333333333334%" %}
**Collect and organize** - bring images, 3D models, PDFs, links, and Studio scenes onto one canvas and arrange them freely.
{% endcolumn %}
{% endcolumns %}

{% columns %}
{% column width="16.666666666666664%" %}

<div align="left"><figure><img src="https://2973737105-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FAXNLyKVZ2tvtyDr8sVES%2Fuploads%2Fk0e1nNG9r2mJ9v49VE0I%2Fimage.png?alt=media&amp;token=195c32c2-c2c8-4118-b378-9403d165e227" alt="" width="65"><figcaption></figcaption></figure></div>
{% endcolumn %}

{% column width="83.33333333333334%" %}
**Generate with presets** - apply a preset to your content to generate new images or 3D models. You don't pick an AI model or write a prompt: each preset is already tuned for a specific task.
{% endcolumn %}
{% endcolumns %}

{% columns %}
{% column width="16.666666666666664%" %}

<div align="left"><figure><img src="https://2973737105-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FAXNLyKVZ2tvtyDr8sVES%2Fuploads%2FJMOS8GkCIGjfV658sFq0%2Fimage.png?alt=media&amp;token=8555a747-dbb0-430b-911a-3e0f912ef3f0" alt="" width="65"><figcaption></figcaption></figure></div>
{% endcolumn %}

{% column width="83.33333333333334%" %}
**Work with 3D directly on the canvas** - import a 3D model, open it in full-screen mode to adjust the transformation and edit materials and textures, or create a **Material** element on the canvas and apply it to a model or to a specific part of it.&#x20;
{% endcolumn %}
{% endcolumns %}

{% columns %}
{% column width="16.666666666666664%" %}

<div align="left"><figure><img src="https://2973737105-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FAXNLyKVZ2tvtyDr8sVES%2Fuploads%2FTBYngK9uLMok9eh00dD1%2Fimage.png?alt=media&amp;token=2ac4148b-377e-459f-9180-32532b713cb7" alt="" width="65"><figcaption></figcaption></figure></div>
{% endcolumn %}

{% column width="83.33333333333334%" %}
**Collaborate** - leave comments, annotations, and sticky notes, and work on the same canvas with your team.
{% endcolumn %}
{% endcolumns %}

### How Canvas works

Every Canvas project is a single infinite canvas. Work on it follows a simple loop: **bring in content, apply a preset, and continue with the result.**

{% stepper %}
{% step %}

#### Bring in your content

Most work starts with something you already have. Import an image, a 3D model, a PDF, or a link, or add a Studio scene, either by pasting its link or by choosing it from your library.&#x20;

{% endstep %}

{% step %}

#### Apply a preset

A preset is a ready-made AI tool for one specific job, such as creating a photorealistic render from a sketch, extracting materials from a photo, or generating a 3D model from an image. Presets are designed to work with the content you've brought in, so you start from your own reference rather than from a blank page.

You don't choose an AI model or write a prompt. Each preset is crafted by Vectary for its task.<br>
{% endstep %}

{% step %}

#### Continue with the result

The result of a generation (an image, a video, or a 3D model) appears on the canvas as a new element. You can apply another preset to it, compare it with other variations, or keep refining.&#x20;
{% endstep %}
{% endstepper %}

### Canvas elements

Everything on the canvas is an element. Besides imported content and generation results, you can add elements from the **+** menu to organize and annotate your work: **Prompt**, **Text**, **Frame**, **Material**, **Gallery**, **Sticky Note**, and **Annotation**.&#x20;

<div align="left"><figure><img src="https://2973737105-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FAXNLyKVZ2tvtyDr8sVES%2Fuploads%2F5VYIxtoPHtryAiDr2Wf1%2Fimage.png?alt=media&amp;token=1db513e7-208c-41fb-a9c0-b6f3c5edfc25" alt="" width="347"><figcaption></figcaption></figure></div>

### Presets

A preset is a ready-made AI tool for one specific job, for example creating a photorealistic render, changing a material, or generating a 3D model from an image. Presets are designed and tested by Vectary, so you get consistent results without adjusting settings.

<div align="left"><figure><img src="https://2973737105-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FAXNLyKVZ2tvtyDr8sVES%2Fuploads%2FXnofuztMbzZadchyMwZ2%2Fimage.png?alt=media&amp;token=fcd02199-8d55-484c-9826-ef1144b174db" alt="" width="375"><figcaption></figcaption></figure></div>

### A typical workflow

1. **Research** - collect references, sketches, photos, documents, and 3D models
2. **Explore** - generate and compare forms, finishes, and variations with presets
3. **Refine** - develop the strongest idea into a 3D concept: geometry, materials, lighting
4. **Validate** - compare options and gather team feedback

### Canvas and Studio

Vectary offers two editors, and each project you create uses one of them:

<table data-header-hidden><thead><tr><th width="126.19140625"></th><th></th><th></th></tr></thead><tbody><tr><td></td><td><strong>Canvas</strong></td><td><strong>Studio</strong></td></tr><tr><td><strong>Best for</strong></td><td>Research, ideation, and AI-assisted concepting</td><td>Detailed 3D scenes, configurators, and interactive 3D/AR experiences</td></tr><tr><td><strong>Works as</strong></td><td>An infinite canvas with AI presets</td><td>A full 3D editor</td></tr></tbody></table>

Both live in your [Workspace](/documentation/getting-started/workspace.md), where Canvas and Studio projects are organized together in folders.

<figure><img src="https://2973737105-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FAXNLyKVZ2tvtyDr8sVES%2Fuploads%2F6YTF3w4QrVkIMgq7MxBj%2Fimage.png?alt=media&amp;token=c8e1e463-bd06-4464-aee8-ba7e6b92856a" alt=""><figcaption></figcaption></figure>

### Getting started

Open [canvas.vectary.com](https://canvas.vectary.com) to explore a sample project, or create a **Canvas Project** from your Workspace. See [Workspace](/documentation/getting-started/workspace.md) for details.

### Usage and credits

AI generations use credits. You can track usage in [Workspace](/documentation/getting-started/workspace.md) settings → **Limit History**.&#x20;


---

# 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://help.vectary.com/canvas/overview.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.
