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

# Seedance 2

<div style={{background: "linear-gradient(135deg, #00080f 0%, #001a3a 55%, #000812 100%)", borderRadius: "20px", padding: "3.5rem 3rem 3rem", marginBottom: "2.5rem", overflow: "hidden", position: "relative"}}>
  <div style={{position: "absolute", inset: "0", background: "radial-gradient(ellipse at 30% 70%, rgba(124,0,251,0.2) 0%, transparent 55%), radial-gradient(ellipse at 85% 10%, rgba(0,100,255,0.12) 0%, transparent 50%)", pointerEvents: "none"}} />

  <div style={{position: "relative"}}>
    <div style={{display: "flex", gap: "0.5rem", marginBottom: "1.5rem", flexWrap: "wrap"}}>
      <span style={{background: "rgba(0,80,200,0.3)", border: "1px solid rgba(0,100,255,0.4)", borderRadius: "100px", padding: "0.3rem 1rem", fontSize: "0.72rem", color: "#7eb8ff", fontWeight: "500", letterSpacing: "0.06em"}}>VIDEO MODEL</span>
      <span style={{background: "rgba(255,255,255,0.06)", border: "1px solid rgba(255,255,255,0.12)", borderRadius: "100px", padding: "0.3rem 1rem", fontSize: "0.72rem", color: "rgba(255,255,255,0.45)", fontWeight: "400"}}>by ByteDance</span>
      <span style={{background: "rgba(255,255,255,0.06)", border: "1px solid rgba(255,255,255,0.12)", borderRadius: "100px", padding: "0.3rem 1rem", fontSize: "0.72rem", color: "rgba(255,255,255,0.45)", fontWeight: "400"}}>Released February 2026</span>
    </div>

    <h1 style={{fontSize: "clamp(2.5rem, 5vw, 3.75rem)", fontWeight: "700", color: "#ffffff", lineHeight: "1.1", letterSpacing: "-0.025em", margin: "0 0 1.1rem 0"}}>Seedance 2</h1>
    <p style={{fontSize: "1.1rem", color: "rgba(255,255,255,0.52)", maxWidth: "580px", lineHeight: "1.7", marginBottom: "2.25rem"}}>ByteDance's most advanced video model — native audio-video joint generation, four generation modes including first-and-last-frame and full references mode, up to 9 reference images, 3 reference videos, and 3 audio clips, with up to 15 seconds of output at 720p–1080p.</p>

    <div style={{display: "flex", gap: "0.75rem", flexWrap: "wrap"}}>
      <div style={{background: "rgba(255,255,255,0.06)", borderRadius: "14px", padding: "0.875rem 1.5rem", border: "1px solid rgba(255,255,255,0.1)"}}>
        <div style={{fontSize: "0.62rem", color: "rgba(255,255,255,0.32)", textTransform: "uppercase", letterSpacing: "0.1em", marginBottom: "0.3rem"}}>References</div>
        <div style={{fontSize: "1rem", color: "#ffffff", fontWeight: "600"}}>9 img + 3 vid + 3 audio</div>
      </div>

      <div style={{background: "rgba(255,255,255,0.06)", borderRadius: "14px", padding: "0.875rem 1.5rem", border: "1px solid rgba(255,255,255,0.1)"}}>
        <div style={{fontSize: "0.62rem", color: "rgba(255,255,255,0.32)", textTransform: "uppercase", letterSpacing: "0.1em", marginBottom: "0.3rem"}}>Duration</div>
        <div style={{fontSize: "1rem", color: "#ffffff", fontWeight: "600"}}>4–15 seconds</div>
      </div>

      <div style={{background: "rgba(255,255,255,0.06)", borderRadius: "14px", padding: "0.875rem 1.5rem", border: "1px solid rgba(255,255,255,0.1)"}}>
        <div style={{fontSize: "0.62rem", color: "rgba(255,255,255,0.32)", textTransform: "uppercase", letterSpacing: "0.1em", marginBottom: "0.3rem"}}>Audio</div>
        <div style={{fontSize: "1rem", color: "#ffffff", fontWeight: "600"}}>Dialogue + SFX + Music</div>
      </div>

      <div style={{background: "rgba(255,255,255,0.06)", borderRadius: "14px", padding: "0.875rem 1.5rem", border: "1px solid rgba(255,255,255,0.1)"}}>
        <div style={{fontSize: "0.62rem", color: "rgba(255,255,255,0.32)", textTransform: "uppercase", letterSpacing: "0.1em", marginBottom: "0.3rem"}}>Modes</div>
        <div style={{fontSize: "1rem", color: "#ffffff", fontWeight: "600"}}>4 generation modes</div>
      </div>
    </div>
  </div>
</div>

<Info>
  Seedance 2 is available in a [Fast variant](/ai-models/video/seedance-2-fast) with the same architecture but lower latency — use Fast for rapid iteration and Seedance 2 for maximum quality final renders.
</Info>

## ByteDance's most capable video model

Seedance 2, released February 10, 2026, is built on the Dual-Branch Diffusion Transformer (DB-DiT) architecture — a significant advancement over the Seedance 1 generation. The model generates audio and video jointly in a single pass, with audio (dialogue, sound effects, music) synchronized at the frame level with the visual output.

The references system is the most expansive in the Seedance lineup: up to 9 reference images, 3 reference video clips, and 3 reference audio clips can be provided simultaneously, giving exhaustive creative control over visual style, character appearance, motion patterns, and audio atmosphere.

## Generation modes

<CardGroup cols={2}>
  <Card title="Text to Video" icon="text">
    Generate video directly from a text prompt. Describe scene, motion, camera behavior, and audio environment — Seedance 2 generates the complete audio-visual output.
  </Card>

  <Card title="Image to Video" icon="image">
    Animate a reference image with described motion. Camera behavior, lighting changes, and audio elements are all added in generation.
  </Card>

  <Card title="First and Last Frame" icon="clapperboard">
    Define both the opening and closing frames — Seedance 2 generates the motion, lighting, and audio between them for precise transition control.
  </Card>

  <Card title="References Mode" icon="images">
    Use up to 9 images, 3 video clips, and 3 audio clips as simultaneous references for maximum creative direction over every aspect of the output.
  </Card>
</CardGroup>

## Capabilities

<CardGroup cols={3}>
  <Card title="Native audio-video joint generation" icon="music">
    Audio and video generated in a single pass — dialogue, sound effects, and music synchronized at the frame level without post-processing.
  </Card>

  <Card title="Multi-shot narrative coherence" icon="film">
    Maintains subject identity, visual style, and scene logic across shots and transitions within a single generation.
  </Card>

  <Card title="Exhaustive reference system" icon="layer-group">
    9 reference images + 3 reference videos + 3 reference audio clips — the most comprehensive reference input system in the lineup.
  </Card>

  <Card title="Advanced camera control" icon="video">
    Complex camera movements including dolly, zoom, pan, tracking, and crane shots with cinematographic accuracy.
  </Card>

  <Card title="Up to 15 seconds" icon="clock">
    Extended generation window at 720p–1080p — suitable for narrative sequences, commercial spots, and music video segments.
  </Card>

  <Card title="DB-DiT architecture" icon="microchip">
    Dual-Branch Diffusion Transformer processes visual and audio branches simultaneously for coherent joint generation.
  </Card>
</CardGroup>

## Specifications

| Feature                  | Details                                    |
| ------------------------ | ------------------------------------------ |
| **Developer**            | ByteDance                                  |
| **Released**             | February 10, 2026                          |
| **Architecture**         | Dual-Branch Diffusion Transformer (DB-DiT) |
| **Resolution**           | 720p–1080p                                 |
| **Duration**             | 4–15 seconds                               |
| **Aspect ratios**        | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16            |
| **Audio**                | Dialogue, SFX, music (native)              |
| **Max reference images** | 9                                          |
| **Max reference videos** | 3                                          |
| **Max reference audio**  | 3                                          |
| **Generation modes**     | 4                                          |

## Availability and requirements

| Requirement            | Details                               |
| ---------------------- | ------------------------------------- |
| **Plan**               | Creator plan or above                 |
| **Email verification** | Business domain verification required |

## How to use

<Steps>
  <Step title="Verify your business email">
    Before accessing Seedance 2, complete business domain email verification in your account settings.
  </Step>

  <Step title="Open the AI Video Generator">
    Log into ImagineArt and go to the **AI Video Generator**.
  </Step>

  <Step title="Select Seedance 2">
    Choose **Seedance 2** from the model dropdown. Confirm your plan is Creator or above.
  </Step>

  <Step title="Choose your generation mode">
    Select **Text to Video**, **Image to Video**, **First and Last Frame**, or **References** depending on your workflow.
  </Step>

  <Step title="Add references (optional)">
    In References mode, upload up to 9 images, 3 video clips, and 3 audio clips to guide the output.
  </Step>

  <Step title="Write your prompt">
    Describe the scene, subject, motion, camera behavior, and audio atmosphere.
  </Step>

  <Step title="Generate">
    Click **Generate** to create your video with synchronized audio.
  </Step>
</Steps>

## Prompting tips

* **Describe audio explicitly** — "With the sound of a violin playing softly in the background" or "city traffic noise in the distance" directly influences the audio generation.
* **Use audio references for music style** — Upload a short audio clip in References mode to anchor the musical style and tempo of the generated audio.
* **First-and-Last-Frame for precise transitions** — Define your opening and closing images; write the prompt around motion style and atmosphere rather than restating what's in the frames.
* **Multi-shot: use transition cues** — "THEN CUT TO:" or "The camera pulls back to reveal..." helps Seedance 2 understand shot structure.

### Example prompts

> A musician plays acoustic guitar on a rooftop at sunset. The camera slowly orbits around them. Warm orange light, city skyline in background. Guitar melody generated naturally with the visuals. 10 seconds.

> FIRST FRAME: woman standing at a window looking out at rain. LAST FRAME: woman smiling, holding a warm mug. Generate the transition — mood shift from pensive to content. Soft piano music.

## Seedance family comparison

| Model                                                 | Audio          | References              | Duration | Speed    | Best for                     |
| ----------------------------------------------------- | -------------- | ----------------------- | -------- | -------- | ---------------------------- |
| **Seedance 2**                                        | Yes            | 9 img + 3 vid + 3 audio | 4–15s    | Standard | Max quality, full multimodal |
| [Seedance 2 Fast](/ai-models/video/seedance-2-fast)   | Yes            | 9 img + 3 vid + 3 audio | 4–15s    | Fast     | Rapid iteration, pipelines   |
| [Seedance 1.5 Pro](/ai-models/video/seedance-1-5-pro) | Yes (lip-sync) | Image input             | 4–12s    | Standard | Multilingual dialogue        |
| [Seedance 1.0 Pro](/ai-models/video/seedance-1-0-pro) | No             | Image input             | 5–10s    | Standard | Cinematic storytelling       |