> ## 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.

# Video models

> The video model families Orisu supports, grouped by what they do: generation, editing, lip sync, and upscaling.

Orisu connects to a range of hosted video models. You pick the model per node in its config panel, so the same node can run on different families depending on what you need. This page covers which models exist and what they're good for. For what each setting does, see [Model settings](/models/settings).

## Generation

These families power the [Generate video](/nodes/ai-video/generate-video) node, turning a text prompt and/or a first-frame image into video. Capabilities vary by family: end frames, reference images and videos, audio input, and subject references appear only on models that support them.

| Family             | Provider  | Good for                                                                                              |
| ------------------ | --------- | ----------------------------------------------------------------------------------------------------- |
| Veo                | Google    | High-fidelity clips with native audio; 720p/1080p, up to 8s                                           |
| Gemini Omni        | Google    | Fast 720p clips with synchronized audio; also edits existing footage from plain-language instructions |
| Sora               | OpenAI    | Coherent multi-shot scenes from text                                                                  |
| Kling              | Kling     | Versatile generation with motion control, elements, and edit variants                                 |
| Hailuo             | MiniMax   | Fast, expressive motion                                                                               |
| Runway             | Runway    | Cinematic look from Gen 4                                                                             |
| Seedance           | ByteDance | Strong text-to-video and image-to-video at flexible aspect ratios                                     |
| Grok Imagine Video | xAI       | Quick generation from text or image                                                                   |
| Hedra              | Hedra     | Character-driven video (Character 3)                                                                  |
| Vidu               | Vidu      | General-purpose generation                                                                            |

Most families now expose their quality tiers directly on the node instead of as separate models: Veo3 and Veo 3.1 offer **Standard / Fast** (Veo 3.1 adds **Lite**), Seedance 2.0 offers **Standard / Fast / Mini**, Kling 3.0 and Kling O3 offer **Standard / Pro / 4K**, and Kling 2.1 offers **Standard / Pro / Master** — the credit estimate updates as you switch. Audio on/off is a setting (`generate_audio`) on models that support it, not a separate model.

<Note>
  Some video models generate audio and some don't. Families like Veo, Kling,
  Seedance, and Gemini Omni support sound; models that do expose a
  generate-audio toggle in the node's settings (audio usually adds to the
  per-second price). Turn it off when you plan to add your own soundtrack.
</Note>

### Available generation variants

<Columns cols={2}>
  <Card title="Veo (Google)">
    Veo 3.1 (Standard / Fast / Lite), Veo3 (Standard / Fast)
  </Card>

  <Card title="Gemini Omni (Google)">
    Gemini Omni Flash — text, image, or reference images to video with audio
  </Card>

  <Card title="Sora (OpenAI)">
    Sora 2
  </Card>

  <Card title="Kling (Kling)">
    Kling 3.0 (Standard / Pro / 4K), O3 (Standard / Pro / 4K), 2.6 Pro,
    2.5 Turbo, 2.1 (Standard / Pro / Master), O1, Elements (Standard / Pro),
    Motion Control
  </Card>

  <Card title="Hailuo (MiniMax)">
    Hailuo 02 Pro, 2.3 Standard, 2.3 Fast
  </Card>

  <Card title="Runway (Runway)">
    Runway Gen 4
  </Card>

  <Card title="Seedance (ByteDance)">
    Seedance Pro, Pro Fast, 1.5 Pro, 2.0 (Standard / Fast / Mini)
  </Card>

  <Card title="Grok Imagine Video (xAI)">
    Grok Imagine Video
  </Card>

  <Card title="Hedra / Vidu">
    Hedra Character 3, Vidu
  </Card>
</Columns>

## Editing

The [Edit video](/nodes/ai-video/edit-video) node rewrites existing footage from text instructions. It runs on:

* Gemini Omni Flash — conversational edits (object replacement, style changes) without regenerating the whole clip
* Kling
* Runway Gen 4 Aleph
* Grok Imagine Edit

## Lip sync

The [Generate lipsync](/nodes/ai-video/generate-lipsync) node drives a face from an audio track. It runs on:

* Sync Lipsync 2.0
* Kling
* Veed Fabric
* Hedra

## Upscale

The [Upscale video](/nodes/ai-video/upscale-video) node increases resolution. It runs on:

* FlashVSR

<Tip>
  Match the model to the inputs you have. Generation models accept prompts and
  first frames; editing models need an existing video; lip sync needs a face
  plus audio; upscaling needs a finished clip.
</Tip>