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

# Generation Settings

> Complete guide to image and video generation settings in Open Canva. Learn about model selection, aspect ratios, reference images, and generation controls.

## Overview

Open Canva exposes a focused set of controls so you can generate quickly without tuning low-level parameters. The app automatically handles backend defaults like inference steps and guidance; you only manage the settings below.

## Model selection

* Choose **up to four models per request**. One image (or video) is produced per selected model.
* All selected models share the same prompt and aspect ratio.
* Models that don't support your selected aspect ratio are automatically grayed out.
* Switch between the **Image** and **Video** tabs to access different model categories.

<Tip>
  Start with a single model, then add more to compare results side by side within the same batch.
</Tip>

## Aspect ratio

The aspect ratio picker maps to supported image sizes for each model. Open Canva supports 18 aspect ratios organized by orientation:

### Landscape

| Aspect ratio | Common use                                      |
| ------------ | ----------------------------------------------- |
| 16:9         | Widescreen, presentations, social media banners |
| 4:3          | Standard landscape, product photos              |
| 3:2          | Photography standard, print                     |
| 5:4          | Social media posts                              |
| 21:9         | Ultra-wide, cinematic                           |
| 2:1          | Panoramic                                       |

### Portrait

| Aspect ratio | Common use                     |
| ------------ | ------------------------------ |
| 9:16         | Mobile, Stories, Reels, TikTok |
| 3:4          | Standard portrait              |
| 2:3          | Photography portrait, print    |
| 4:5          | Instagram portrait             |

### Square

| Aspect ratio | Common use                         |
| ------------ | ---------------------------------- |
| 1:1          | Social media posts, profile images |

<Info>
  The default aspect ratio is **16:9 landscape**. The UI maps your selection to the optimal resolution for each selected model -- no manual dimension entry required.
</Info>

### Resolution tiers

Images are generated at resolution tiers (0.5K, 1K, 2K, 4K) depending on the model and your plan's upscale limits:

| Plan       | Max upscale resolution |
| ---------- | ---------------------- |
| Starter    | 2K                     |
| Pro        | 8K                     |
| Max        | 22K                    |
| Enterprise | 22K                    |

## Number of images

Some models support generating multiple images per request. The number selector adjusts based on the selected model's capabilities.

## Reference images

* Upload up to **5 reference images per session** and reuse them across prompts.
* Attach **up to 3 references per generation request** to guide results.
* Uploaded references appear in the References panel; toggle selections before running a prompt.
* References can also be uploaded across sessions for reuse in any project.

<Card title="Reference Images Guide" icon="image" href="/image-generation/reference-images">
  Learn how reference images guide AI output.
</Card>

## Prompt enhancement

* Use the **Enhance** action to expand or refine your prompt before generating.
* Enhanced text can be kept in sync with the editor or discarded at any time.
* For deeper prompt planning, use the [Prompt Assistant](/sessions/prompt-assistant).

## What isn't configurable

Some parameters are handled automatically and are not exposed in the UI:

* Inference steps and guidance scale
* Seed selection
* Negative prompts or style presets

This keeps the interface streamlined while enforcing safe defaults and model-specific requirements.

## Settings reference

| Setting            | Purpose                | Notes                                          |
| ------------------ | ---------------------- | ---------------------------------------------- |
| Models             | Which engines run      | 1-4 models per request; one output per model   |
| Aspect ratio       | Composition and size   | 18 ratios mapped to model-supported dimensions |
| Number of images   | Output count           | Model-dependent availability                   |
| Reference images   | Guide style/content    | Up to 3 per run; reuse uploads across sessions |
| Prompt enhancement | Improve prompt quality | Optional helper before generation              |

## Troubleshooting settings

<AccordionGroup>
  <Accordion title="A model is grayed out">
    The model doesn't support your selected aspect ratio. Change the aspect ratio or select a different model.
  </Accordion>

  <Accordion title="Images look lower quality than expected">
    * Try a higher-quality model (e.g., Flux 2 Max instead of Flux Schnell)
    * Check if your plan supports higher upscale resolutions
    * Make your prompt more detailed and specific
  </Accordion>

  <Accordion title="Generation is slow">
    * Premium models take longer than fast models
    * Video generation is slower than image generation
    * Check your concurrent job limit (varies by plan)
  </Accordion>
</AccordionGroup>

## Related guides

<CardGroup cols={2}>
  <Card title="AI Models" icon="sliders" href="/image-generation/models">
    Browse all available models and their strengths.
  </Card>

  <Card title="Writing Prompts" icon="pen-fancy" href="/image-generation/prompts">
    Combine effective prompts with the right settings.
  </Card>

  <Card title="Reference Images" icon="image" href="/image-generation/reference-images">
    Upload reference images to guide output.
  </Card>

  <Card title="Plans & Pricing" icon="credit-card" href="/billing/plans">
    See resolution limits and features by plan.
  </Card>
</CardGroup>