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

# Video Generation

> Turn a text prompt or an image into a short video clip.

**Text to Video** makes a clip from a description, and **Image to Video** brings an image to life. Both use the video provider you set in **Settings → Video Generation**, which is separate from image generation and from the model you chat with.

> [!WARNING]
>
> Each clip uses the provider's credits or your Cloud points, and can take a while. Start with a short clip when you try a new provider.

## Before you start

1. Open **Settings → Video Generation** and pick a provider.
2. Set its **Credential Provider** (the key or account it uses) and its **Model Name**.
3. Click **Set as Default**.

The Enconvo Cloud providers, **xAI (Enconvo Cloud)** and **Google Gemini (Enconvo Cloud)**, need no API key of your own.

## Create a clip from text

1. Open SmartBar, type your description, and run **Text to Video**. Describe the subject, the action, how the camera moves, and the scene.
2. Wait while it shows **Generating video...**.
3. Preview the clip in the result, then paste it, copy it, or show it in Finder.

## Animate an image

1. Attach the source image, and describe what moves and what stays the same.
2. Run **Image to Video**. It needs both a description and at least one image.
3. Preview the clip and save it.

If the model accepts only one image or a limited length, write your request within those limits.

## Providers and options

The [video provider catalog](https://docs.enconvo.ai/providers/catalog.md#video-generation) includes xAI, Gemini, OpenRouter, Kie.ai, Topview, and their Enconvo Cloud versions. Models accept different inputs and resolutions. For example, Grok Imagine Video 1.5 adds a 1080p option that the base Grok Imagine Video model doesn't have.

**Text to Video** and **Image to Video** use the model's default length and resolution. To choose them, ask an Agent in chat to make the clip, and ask only for options the model supports.

## Troubleshooting

| Problem | What to do |
| - | - |
| The request fails to submit | Check the provider's access and the options you asked for |
| The clip is still processing | Check its status before you start another paid generation |
| You need help with a failed clip | Keep your input and the error or status it returned, and share them without your credentials |

## Related

> [card] [Image Generation](https://docs.enconvo.ai/ai/image-generation.md)
>
> Create or edit an image in chat.

> [card] [Media Utilities](https://docs.enconvo.ai/features/media-tools.md)
>
> Download, compress, or pull the audio from a clip.

> [card] [Provider Catalog](https://docs.enconvo.ai/providers/catalog.md#video-generation)
>
> Every video provider and its settings.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.