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

# Generate video

> Generate video from an optional text prompt and/or first-frame image, with brand context.

Generate Video creates video from a text prompt and/or a first-frame image. Depending on the selected model, you can supply end frames, reference images and videos, audio, and brand context.

## When to use

* Marketing clips
* Product showcases
* Social vertical video

Common patterns: `text_prompt → generate_video`, or `upload_image → generate_video`.

## Inputs

Connect a text prompt and/or a first-frame image to generate video. Several inputs appear only when the selected model supports them.

<ParamField body="Text Prompt" type="text">
  The prompt describing the video. Optional. Accepts an array and supports loop mode.
</ParamField>

<Note>
  **Inline prompt.** You don't need a separate Text Prompt node for a fixed prompt —
  type it directly on the node. The inline field appears whenever the prompt input is
  unconnected and disappears once you wire a text input in. Connect a Text Prompt node
  only when you want to drive the prompt from upstream or expose it as an app input.
  Type `@` to mention a connected input by name — text inputs insert their content into
  the prompt, media inputs insert their name.
</Note>

<ParamField body="First Frame" type="image">
  An image used as the opening frame. Optional. Accepts an array and supports loop mode.
</ParamField>

<ParamField body="Brand" type="brand">
  Brand context applied to the output. Optional, accepts multiple.
</ParamField>

<ParamField body="Product" type="product">
  Product context from a [Product from Website](/nodes/integrations/extract-product) node. Product facts are injected into the prompt, and the product's photos and logo are used as reference images. Optional, accepts multiple.
</ParamField>

<ParamField body="Audio" type="audio">
  An audio track. Available only when the selected model supports audio sources.
</ParamField>

<ParamField body="End Frame" type="image">
  An image used as the closing frame. Available only when the selected model supports end frames.
</ParamField>

<ParamField body="Reference Videos" type="video">
  Videos used as references. Available only when the selected model supports video sources. Accepts multiple.
</ParamField>

<ParamField body="Reference Images" type="image">
  Images used as references. Available only when the selected model supports image sources. Accepts multiple.
</ParamField>

<ParamField body="Context" type="any">
  Anything to include as additional context: scraper Results, text descriptions, or mixed bundles. Contents are described to the model in the prompt. Images in the bundle are passed as reference images where the selected model supports them. Optional, accepts multiple.
</ParamField>

<ParamField body="Element" type="element">
  Subject reference slots. Available only when the selected model supports subject references and you set element slots above zero.
</ParamField>

## Outputs

<ParamField body="Video" type="video">
  The generated video.
</ParamField>

## Configuration

<ParamField body="numberOfRuns" type="number" default="1">
  How many video variations to generate (1 to 10).
</ParamField>

<ParamField body="motionIntensity" type="string" default="medium">
  Amount of motion in the video. One of `low`, `medium`, or `high`.
</ParamField>

<ParamField body="elementSlotCount" type="number" default="0">
  Number of subject-reference element slots to expose. Synced to the selected model's capability.
</ParamField>

<ParamField body="duration" type="number | &#x22;auto&#x22;">
  Clip length in seconds. The slider snaps to the lengths the selected model supports. Seedance 2.0 adds an **Auto** notch (its default): the model chooses the best length between 4 and 15 seconds from your prompt. With Auto, credits are held at the 15-second ceiling when the run starts and then settle to the delivered clip's real length.
</ParamField>

<Note>
  This node runs on a selectable model and consumes credits. Additional model-specific options (such as duration, aspect ratio, resolution, and audio generation) are available depending on the model you choose. Pick the model in the node's config panel. See [Video models](/models/video) for the options, and [Model settings](/models/settings) for what each setting does.
</Note>