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

# Video nodes

> Generate and transform video clips in Creative Studio — text-to-video, image-to-video, lip sync, motion control, and utilities like upscale and join.

Video nodes generate and transform clips directly on the Creative Studio canvas. Chain them with image nodes, audio nodes, and utilities to build complete video production pipelines.

<Warning>
  This page covers **Studio video nodes**. For product-URL pipelines use [URL to Video](/docs/url-to-video/overview). For wizard-driven campaign video use [Campaign modes](/docs/campaigns/modes).
</Warning>

## What generation modes are available?

<Tabs>
  <Tab title="Text to video">
    Generate a video clip from a text prompt. No source media required — describe the scene, motion, and style.

    **Best for:** backgrounds, B-roll, concept visualizations, abstract motion.
  </Tab>

  <Tab title="Image to video">
    Animate a still image using a prompt that describes the desired motion. The image anchors the scene; the prompt drives movement.

    **Best for:** product animations, character motion, bringing photography to life.
  </Tab>

  <Tab title="Reference to video">
    Provide one or more reference images to guide style, subject identity, or scene composition during generation.

    **Best for:** brand-consistent clips, character consistency across scenes.
  </Tab>

  <Tab title="First / last frame">
    Define the exact starting and ending frames as keyframe images. The model interpolates the motion between them.

    **Best for:** controlled transitions, reveal animations, precise narrative beats.
  </Tab>

  <Tab title="Motion control">
    Apply camera or subject motion guidance — pans, zooms, orbits, or custom trajectories — on top of a generated or provided clip.

    **Best for:** cinematic camera moves, dynamic product spins, directional storytelling.
  </Tab>

  <Tab title="Lip sync">
    Align mouth movements in a face video to an audio track. Feed an audio node output directly into the lip sync node.

    **Best for:** AI spokesperson content, dubbed dialogue, voiceover synchronization.
  </Tab>
</Tabs>

## What utility modes are available?

<CardGroup cols={2}>
  <Card title="Remove objects / background" icon="eraser">
    Clean up a clip by removing unwanted objects or replacing the background scene.
  </Card>

  <Card title="Upscale" icon="zoom-in">
    Increase video resolution and enhance detail for final delivery or display at larger sizes.
  </Card>

  <Card title="Join videos" icon="git-merge">
    Concatenate multiple clips into a single output — useful for assembling a sequence from separate generation runs.
  </Card>

  <Card title="Hyperframes (animated video)" icon="film" href="/docs/studio/hyperframes">
    Structured multi-stage pipeline: plan, storyboard, script, voiceover, and render a cohesive short film.
  </Card>
</CardGroup>

## Which models are available for video nodes?

| Model        | Notable capabilities                                 |
| ------------ | ---------------------------------------------------- |
| **Veo**      | High-quality cinematic generation, strong motion     |
| **Kling**    | Long clips, strong subject consistency               |
| **Sora**     | Creative and stylized outputs, good at scene variety |
| **LTX**      | Fast, efficient, good for iteration                  |
| **Seedance** | Portrait and character-focused video                 |

Capability matrices — including max duration, audio support, and resolution — vary by model. See [Video models](/docs/models/video) for the full comparison.

<Note>
  Video generation is among the most credit-intensive operations. Check the credit estimate in the node panel before running, especially for longer clips or higher resolutions.
</Note>

## How do you build a video pipeline?

<Steps>
  <Step title="Generate or upload source media">
    Start with a text-to-image node (or upload an image) to create your anchor visual.
  </Step>

  <Step title="Add a video node">
    Choose a generation mode — image-to-video is a common first step when you have a strong hero image.
  </Step>

  <Step title="Add audio (optional)">
    Connect an [audio node](/docs/studio/audio-nodes) output to a lip sync node or as a reference track for the Hyperframes renderer.
  </Step>

  <Step title="Apply utilities">
    Chain upscale, remove-background, or join nodes as needed.
  </Step>

  <Step title="Export or schedule">
    Send the final clip to export or connect to the [Scheduler](/docs/scheduler/overview) for publishing.
  </Step>
</Steps>

## What's next?

<CardGroup cols={3}>
  <Card title="Hyperframes" icon="film" href="/docs/studio/hyperframes">
    Full animated video pipeline with storyboarding
  </Card>

  <Card title="Audio nodes" icon="mic" href="/docs/studio/audio-nodes">
    Add voiceover and dialogue to your clips
  </Card>

  <Card title="Video models reference" icon="cpu" href="/docs/models/video">
    Full model capability matrix
  </Card>
</CardGroup>