# Seedance 2.0

> ByteDance's flagship video model with text-to-video, image-to-video, and reference-to-video (multi-image/video/audio) generation, cinematic output, native synchronized audio, multi-shot editing, and director-level camera control.

## Quick Reference

- Model ID: seedance-2.0
- Creator: ByteDance
- Status: active
- Family: seedance
- Base URL: https://api.lumenfall.ai/v1

## Specifications

- Max Input Images: 9
- Max Video Duration: 15 seconds
- Input Modalities: text, image, video, audio
- Output Modalities: video, audio
- Supported Modes: Text to Video, Image to Video, Video to Video

## API Parameters

The compiled parameter schema for this model is available via the API: `GET /v1/models/seedance-2.0?schema=true`.

### Core Parameters

- `prompt` (string) — REQUIRED: Text prompt for video generation. Modes: Text to Video, Image to Video, Video to Video
- `seed` (integer): Random seed for reproducibility. Modes: Text to Video, Image to Video, Video to Video
- `duration` (number): Video duration in seconds. Values: 10, 11, 12, 13, 14, 15, 4, 5, 6, 7, 8, 9. Modes: Text to Video, Image to Video, Video to Video

### Size & Layout

- `size` (string): Video dimensions as WxH pixels (e.g. "1920x1080") or aspect ratio (e.g. "16:9"). Values: auto, 1563x670, 1365x768, 768x1365, 887x1182, 1024x1024, 1183x887. Modes: Text to Video, Image to Video, Video to Video
- `aspect_ratio` (string): Aspect ratio of the output video (e.g. "16:9", "1:1"). Values: auto, 9:16, 3:4, 1:1, 4:3, 16:9, 21:9. Modes: Text to Video, Image to Video, Video to Video
- `resolution` (string): Output resolution tier (e.g. "1K", "4K"). Values: auto, 1K. Modes: Text to Video, Image to Video, Video to Video

### Media Inputs

- `input_reference` (array) — REQUIRED: Input image(s) to animate into video. Modes: Image to Video, Video to Video
- `input_video` (string) — REQUIRED: Input video URL to transform. Modes: Video to Video

### Audio

- `generate_audio` (boolean): Whether to generate audio alongside video. Modes: Text to Video, Image to Video, Video to Video

### Output & Format

- `n` (integer): Number of videos to generate. Default: 1. Modes: Text to Video, Image to Video, Video to Video

### Additional Parameters

- `end_image` (string): End frame image URL for video interpolation. Modes: Image to Video
- `audio_urls` (array): Reference audio clips (up to 3) for lip-sync or scoring.. Modes: Video to Video. Only available via fal
- `end_user_id` (string): Optional end user identifier.. Modes: Text to Video, Image to Video, Video to Video. Only available via fal


## Model Identifiers

- Primary Slug: seedance-2.0
- Aliases: seedance-2-0, seedance-2


## Tags

video-generation, text-to-video, image-to-video, video-to-video, audio-generation

## Available Providers

### fal.ai

- Config Key: fal/seedance-2.0
- Provider Model ID: bytedance/seedance-2.0/text-to-video
- Pricing: $0.303/second
  - Source: https://fal.ai/models/bytedance/seedance-2.0/text-to-video

### fal.ai

- Config Key: fal/seedance-2.0-i2v
- Provider Model ID: bytedance/seedance-2.0/image-to-video
- Pricing: $0.302/second
  - Source: https://fal.ai/models/bytedance/seedance-2.0/image-to-video

### fal.ai

- Config Key: fal/seedance-2.0-r2v
- Provider Model ID: bytedance/seedance-2.0/reference-to-video
- Pricing: $0.181/second
  - Source: https://fal.ai/models/bytedance/seedance-2.0/reference-to-video


## Performance Metrics

Provider performance over the last 30 days.

### fal

- Median Generation Time (p50): 244ms
- 95th Percentile Generation Time (p95): 2014ms
- Average Generation Time: 925ms
- Success Rate: 100.0%
- Total Requests: 28


## Image Gallery

4 images available for this model. Browse all at https://lumenfall.ai/models/bytedance/seedance-2.0/gallery

### Arena Video Results

- : Elo . Prompt: "Cinematic 4k drone shot gliding over a vibrant futuristic greenhouse city. In the foreground, a s..."
- Celebrity Arrival: Elo 1117. Prompt: "Ultra-realistic celebrity arrival scene in New York City, filmed as one continuous handheld shot ..."
- The Rubik's Gauntlet: Elo 1047. Prompt: "Hyper-realistic cinematic close-up of a professional speedcuber solving a 3x3 Rubik's Cube at wor..."
- Neon Rain Reverie: Elo 1000. Prompt: "Hyper-realistic cinematic video of an elegant young woman in a flowing white silk dress dancing g..."

## Example Prompt

The following prompt was used to generate an example video in our playground:

Cinematic 4k drone shot gliding over a vibrant futuristic greenhouse city. In the foreground, a sleek metallic drone hovers, scanning luminescent exotic plants. The name "Seedance 2.0" is holographically projected in the air. In the blurry mid-ground, a calm capybara sits peacefully on a stone bench next to a robotic gardener, unbothered by the high-tech surroundings. Smooth camera movement, natural light filtering through glass panels, hyper-realistic textures, and atmospheric synth foley.

## Code Examples

### Text to Video (/v1/videos/generations) — Async

#### cURL

# Step 1: Submit video generation request
VIDEO_ID=$(curl -s -X POST \
  https://api.lumenfall.ai/v1/videos \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0",
    "prompt": "",
    "size": "1024x1024"
  }' | jq -r '.id')

echo "Video ID: $VIDEO_ID"

# Step 2: Poll for completion
while true; do
  RESULT=$(curl -s \
    https://api.lumenfall.ai/v1/videos/$VIDEO_ID \
    -H "Authorization: Bearer $LUMENFALL_API_KEY")

  STATUS=$(echo $RESULT | jq -r '.status')
  echo "Status: $STATUS"

  if [ "$STATUS" = "completed" ]; then
    echo $RESULT | jq -r '.output.url'
    break
  elif [ "$STATUS" = "failed" ]; then
    echo $RESULT | jq -r '.error.message'
    break
  fi

  sleep 5
done

#### JavaScript

const BASE_URL = 'https://api.lumenfall.ai/v1';
const API_KEY = 'YOUR_API_KEY';

// Step 1: Submit video generation request
const submitRes = await fetch(`${BASE_URL}/videos`, {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${API_KEY}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'seedance-2.0',
    prompt: '',
    size: '1024x1024'
  })
});

const { id: videoId } = await submitRes.json();
console.log('Video ID:', videoId);

// Step 2: Poll for completion
while (true) {
  const pollRes = await fetch(`${BASE_URL}/videos/${videoId}`, {
    headers: { 'Authorization': `Bearer ${API_KEY}` }
  });
  const result = await pollRes.json();

  if (result.status === 'completed') {
    console.log('Video URL:', result.output.url);
    break;
  } else if (result.status === 'failed') {
    console.error('Error:', result.error.message);
    break;
  }

  await new Promise(r => setTimeout(r, 5000));
}

#### Python

import requests
import time

BASE_URL = "https://api.lumenfall.ai/v1"
API_KEY = "YOUR_API_KEY"
HEADERS = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json"
}

# Step 1: Submit video generation request
response = requests.post(
    f"{BASE_URL}/videos",
    headers=HEADERS,
    json={
        "model": "seedance-2.0",
        "prompt": "",
        "size": "1024x1024"
    }
)

video_id = response.json()["id"]
print(f"Video ID: {video_id}")

# Step 2: Poll for completion
while True:
    result = requests.get(
        f"{BASE_URL}/videos/{video_id}",
        headers=HEADERS
    ).json()

    if result["status"] == "completed":
        print(f"Video URL: {result['output']['url']}")
        break
    elif result["status"] == "failed":
        print(f"Error: {result['error']['message']}")
        break

    time.sleep(5)

### Image to Video (/v1/videos/generations) — Async

#### cURL

# Step 1: Submit image-to-video request
VIDEO_ID=$(curl -s -X POST \
  https://api.lumenfall.ai/v1/videos \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0",
    "prompt": "",
    "image_url": "https://example.com/start-frame.jpg",
    "duration": "10",
    "aspect_ratio": "16:9"
  }' | jq -r '.id')

echo "Video ID: $VIDEO_ID"

# Step 2: Poll for completion
while true; do
  RESULT=$(curl -s \
    https://api.lumenfall.ai/v1/videos/$VIDEO_ID \
    -H "Authorization: Bearer $LUMENFALL_API_KEY")

  STATUS=$(echo $RESULT | jq -r '.status')
  echo "Status: $STATUS"

  if [ "$STATUS" = "completed" ]; then
    echo $RESULT | jq -r '.output.url'
    break
  elif [ "$STATUS" = "failed" ]; then
    echo $RESULT | jq -r '.error.message'
    break
  fi

  sleep 5
done

#### JavaScript

const BASE_URL = 'https://api.lumenfall.ai/v1';
const API_KEY = 'YOUR_API_KEY';

// Step 1: Submit image-to-video request
const submitRes = await fetch(`${BASE_URL}/videos`, {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${API_KEY}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'seedance-2.0',
    prompt: '',
    image_url: 'https://example.com/start-frame.jpg',
    duration: '10',
    aspect_ratio: '16:9'
  })
});

const { id: videoId } = await submitRes.json();
console.log('Video ID:', videoId);

// Step 2: Poll for completion
while (true) {
  const pollRes = await fetch(`${BASE_URL}/videos/${videoId}`, {
    headers: { 'Authorization': `Bearer ${API_KEY}` }
  });
  const result = await pollRes.json();

  if (result.status === 'completed') {
    console.log('Video URL:', result.output.url);
    break;
  } else if (result.status === 'failed') {
    console.error('Error:', result.error.message);
    break;
  }

  await new Promise(r => setTimeout(r, 5000));
}

#### Python

import requests
import time

BASE_URL = "https://api.lumenfall.ai/v1"
API_KEY = "YOUR_API_KEY"
HEADERS = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json"
}

# Step 1: Submit image-to-video request
response = requests.post(
    f"{BASE_URL}/videos",
    headers=HEADERS,
    json={
        "model": "seedance-2.0",
        "prompt": "",
        "image_url": "https://example.com/start-frame.jpg",
        "duration": "10",
        "aspect_ratio": "16:9"
    }
)

video_id = response.json()["id"]
print(f"Video ID: {video_id}")

# Step 2: Poll for completion
while True:
    result = requests.get(
        f"{BASE_URL}/videos/{video_id}",
        headers=HEADERS
    ).json()

    if result["status"] == "completed":
        print(f"Video URL: {result['output']['url']}")
        break
    elif result["status"] == "failed":
        print(f"Error: {result['error']['message']}")
        break

    time.sleep(5)

### Video to Video (/v1/videos/generations) — Async

#### cURL

# Step 1: Submit video-to-video request
VIDEO_ID=$(curl -s -X POST \
  https://api.lumenfall.ai/v1/videos \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0",
    "prompt": "Apply cinematic color grading to @Video1",
    "video_url": "https://example.com/source.mp4",
    "keep_audio": true,
    "aspect_ratio": "16:9"
  }' | jq -r '.id')

echo "Video ID: $VIDEO_ID"

# Step 2: Poll for completion
while true; do
  RESULT=$(curl -s \
    https://api.lumenfall.ai/v1/videos/$VIDEO_ID \
    -H "Authorization: Bearer $LUMENFALL_API_KEY")

  STATUS=$(echo $RESULT | jq -r '.status')
  echo "Status: $STATUS"

  if [ "$STATUS" = "completed" ]; then
    echo $RESULT | jq -r '.output.url'
    break
  elif [ "$STATUS" = "failed" ]; then
    echo $RESULT | jq -r '.error.message'
    break
  fi

  sleep 5
done

#### JavaScript

const BASE_URL = 'https://api.lumenfall.ai/v1';
const API_KEY = 'YOUR_API_KEY';

// Step 1: Submit video-to-video request
const submitRes = await fetch(`${BASE_URL}/videos`, {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${API_KEY}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'seedance-2.0',
    prompt: 'Apply cinematic color grading to @Video1',
    video_url: 'https://example.com/source.mp4',
    keep_audio: true,
    aspect_ratio: '16:9'
  })
});

const { id: videoId } = await submitRes.json();
console.log('Video ID:', videoId);

// Step 2: Poll for completion
while (true) {
  const pollRes = await fetch(`${BASE_URL}/videos/${videoId}`, {
    headers: { 'Authorization': `Bearer ${API_KEY}` }
  });
  const result = await pollRes.json();

  if (result.status === 'completed') {
    console.log('Video URL:', result.output.url);
    break;
  } else if (result.status === 'failed') {
    console.error('Error:', result.error.message);
    break;
  }

  await new Promise(r => setTimeout(r, 5000));
}

#### Python

import requests
import time

BASE_URL = "https://api.lumenfall.ai/v1"
API_KEY = "YOUR_API_KEY"
HEADERS = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json"
}

# Step 1: Submit video-to-video request
response = requests.post(
    f"{BASE_URL}/videos",
    headers=HEADERS,
    json={
        "model": "seedance-2.0",
        "prompt": "Apply cinematic color grading to @Video1",
        "video_url": "https://example.com/source.mp4",
        "keep_audio": True,
        "aspect_ratio": "16:9"
    }
)

video_id = response.json()["id"]
print(f"Video ID: {video_id}")

# Step 2: Poll for completion
while True:
    result = requests.get(
        f"{BASE_URL}/videos/{video_id}",
        headers=HEADERS
    ).json()

    if result["status"] == "completed":
        print(f"Video URL: {result['output']['url']}")
        break
    elif result["status"] == "failed":
        print(f"Error: {result['error']['message']}")
        break

    time.sleep(5)


## Frequently Asked Questions

### How much does Seedance 2.0 cost?

Seedance 2.0 starts at $0.1814 per video through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

### How do I use Seedance 2.0 via API?

You can use Seedance 2.0 through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "seedance-2.0". Code examples are available in Python, JavaScript, and cURL.

### Which providers offer Seedance 2.0?

Seedance 2.0 is available through fal.ai on Lumenfall. Lumenfall automatically routes requests to the best available provider.

## Links

- Model Page: https://lumenfall.ai/models/bytedance/seedance-2.0
- About: https://lumenfall.ai/models/bytedance/seedance-2.0/about
- Providers, Pricing & Performance: https://lumenfall.ai/models/bytedance/seedance-2.0/providers
- API Reference: https://lumenfall.ai/models/bytedance/seedance-2.0/api
- Benchmarks: https://lumenfall.ai/models/bytedance/seedance-2.0/benchmarks
- Use Cases: https://lumenfall.ai/models/bytedance/seedance-2.0/use-cases
- Gallery: https://lumenfall.ai/models/bytedance/seedance-2.0/gallery
- Playground: https://lumenfall.ai/playground?model=seedance-2.0
- API Documentation: https://docs.lumenfall.ai