> ## Documentation Index
> Fetch the complete documentation index at: https://docs.runable.com/llms.txt
> Use this file to discover all available pages before exploring further.

# AI Images

> Generate images from text, edit existing images, remove or replace backgrounds, upscale resolution, and edit text or regions with precision.

AI Images lets you generate images from text prompts and edit them with a suite of AI-powered tools. Generate from scratch, refine existing images, remove or replace backgrounds, upscale resolution up to 4x, detect and edit text inside images, and make precise region-level edits by marking areas on the image.

All images live on the AI Canvas, an infinite workspace where you can arrange, compare, and continue editing.

## What you can do

<CardGroup cols={3}>
  <Card title="Generate from text" icon="sparkles" href="/generate-an-image">
    Describe what you want and the agent creates one or more images.
  </Card>

  <Card title="Remove Background" icon="image" href="/remove-background">
    Strip the background from any image, leaving the subject on transparency.
  </Card>

  <Card title="Replace Background" icon="arrow-right-arrow-left" href="/replace-background">
    Swap the existing background for a new AI-generated scene.
  </Card>

  <Card title="Upscale Resolution" icon="arrow-up-right-dots" href="/upscale-an-image">
    Increase the resolution of any image by up to 4x while keeping detail.
  </Card>

  <Card title="Edit Text in Images" icon="font" href="/edit-text-in-images">
    Detect text in any image and change the wording while preserving style.
  </Card>

  <Card title="Mark & Edit" icon="pen-to-square" href="/mark-and-edit">
    Draw rectangles on specific areas and describe the changes you want.
  </Card>
</CardGroup>

Additional capabilities:

<AccordionGroup>
  <Accordion title="Virtual try-on">
    Upload a garment image and a person image. The AI applies the clothing to the person, creating a realistic virtual try-on. Useful for e-commerce product shots without a photoshoot.
  </Accordion>

  <Accordion title="Sketch to image">
    Draw a rough sketch and the AI turns it into a polished image based on your description.
  </Accordion>

  <Accordion title="Style transfer with references">
    Provide reference images and the agent matches styles, color palettes, and compositions from them.
  </Accordion>
</AccordionGroup>

## Aspect ratios

Select an aspect ratio before generating.

| Ratio    | Description          | Best for                                  |
| -------- | -------------------- | ----------------------------------------- |
| **21:9** | Ultra-wide           | Banners, cinematic scenes                 |
| **16:9** | Widescreen (default) | Presentations, thumbnails, social headers |
| **4:3**  | Standard             | Blog images, general use                  |
| **1:1**  | Square               | Social media posts, profile images        |
| **3:4**  | Portrait             | Posters, product shots                    |
| **9:16** | Tall portrait        | Stories, vertical social content          |
| **9:21** | Ultra-tall           | Vertical banners, phone wallpapers        |

<Note>
  Not all models support all aspect ratios. The agent selects a compatible model automatically based on the ratio you choose.
</Note>

## Two ways to work with images

<Columns cols={2}>
  <div>
    ### Through the chat

    Describe what you want in the input bar. The agent generates or edits images and places them on the canvas. Best for creating new images, complex edits, and multi-step creative work.
  </div>

  <div>
    ### Directly on the canvas

    Select an image on the canvas and use the toolbar (Remove BG, Replace BG, Upscale, Text Edit, Mark Edit, Edit Image) without going through the agent. Best for quick, targeted edits.
  </div>
</Columns>

<Tip>
  Canvas tools use up to 10x fewer credits than sending the same request as a chat prompt. Use canvas edits for fine-tuning and save chat prompts for generating new images or complex multi-step changes.
</Tip>

## Non-destructive editing

Every edit operation (background removal, upscale, text edit, mark edit, refine) creates a new image on the canvas rather than overwriting the original. Your original is always preserved. This gives you a built-in version history of every edit.

## What AI Images does not support

* Vector output (SVG). All images are raster format (PNG).
* Batch editing across multiple images at once from the canvas tools. Each image is edited individually.
* Animated images or GIFs. For motion, see [AI Videos](/overview-what-is-ai-videos).

## Next steps

<CardGroup cols={2}>
  <Card title="Generate an Image" icon="play" href="/generate-an-image">
    Create your first image from a text prompt.
  </Card>

  <Card title="AI Canvas overview" icon="palette" href="/overview-what-is-ai-canvas">
    Explore the full canvas workspace where all image editing happens.
  </Card>
</CardGroup>