# Fal AI Video Generator

Blocks for generating AI videos using FAL.ai models.

## AI Video Generator

### What it is

Generate videos using FAL AI models.

### How it works

This block generates videos from text prompts using FAL.ai's video generation models including Mochi, Luma Dream Machine, and Veo3. Describe the video you want to create, and the AI generates it.

The generated video URL is returned along with progress logs for monitoring longer generation jobs.

### Inputs

| Input  | Description                                | Type                                                              | Required |
| ------ | ------------------------------------------ | ----------------------------------------------------------------- | -------- |
| prompt | Description of the video to generate.      | str                                                               | Yes      |
| model  | The FAL model to use for video generation. | "fal-ai/mochi-v1" \| "fal-ai/luma-dream-machine" \| "fal-ai/veo3" | No       |

### Outputs

| Output     | Description                               | Type       |
| ---------- | ----------------------------------------- | ---------- |
| error      | Error message if video generation failed. | str        |
| video\_url | The URL of the generated video.           | str        |
| logs       | Generation progress logs.                 | List\[str] |

### Possible use case

**Content Creation**: Generate video clips for social media, ads, or creative projects.

**Visualization**: Create visual representations of concepts, products, or stories.

**Prototyping**: Generate video mockups for creative ideation and storyboarding.

***


---

# 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://agpt.co/docs/integrations/block-integrations/ai_video_generator.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.