Bytedance Seedance V1 Lite API

Image To Video
Text To Video
Reference To Video

Endpoint: POST https://fal.run/fal-ai/bytedance/seedance/v1/lite/image-to-video Endpoint ID: fal-ai/bytedance/seedance/v1/lite/image-to-video

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/bytedance/seedance/v1/lite/image-to-video",
    arguments={
        "prompt": "A little dog is running in the sunshine. The camera follows the dog as it plays in a garden.",
        "image_url": "https://fal.media/files/koala/f_xmiodPjhiKjdBkFmTu1.png"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Input Schema

prompt

string

required

The text prompt used to generate the video

aspect_ratio

AspectRatioEnum

default:"auto"

The aspect ratio of the generated video Default value: "auto"Possible values: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto

resolution

ResolutionEnum

default:"720p"

Video resolution - 480p for faster generation, 720p for higher quality Default value: "720p"Possible values: 480p, 720p, 1080p

duration

DurationEnum

default:"5"

Duration of the video in seconds Default value: "5"Possible values: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12

camera_fixed

boolean

default:"false"

Whether to fix the camera position

seed

integer

Random seed to control video generation. Use -1 for random.

enable_safety_checker

boolean

default:"true"

If set to true, the safety checker will be enabled. Default value: true

num_frames

integer

The number of frames to generate. If provided, will override duration.Range: 29 to 289

image_url

string

required

The URL of the image used to generate video

end_image_url

string

The URL of the image the video ends with. Defaults to None.

Output Schema

video

File

required

Generated video file

seed

integer

required

Seed used for generation

Input Example

{
  "prompt": "A little dog is running in the sunshine. The camera follows the dog as it plays in a garden.",
  "aspect_ratio": "auto",
  "resolution": "720p",
  "duration": "5",
  "camera_fixed": false,
  "enable_safety_checker": true,
  "image_url": "https://fal.media/files/koala/f_xmiodPjhiKjdBkFmTu1.png"
}

Output Example

{
  "video": {
    "url": "https://v3.fal.media/files/penguin/qmLZSvOIzTKs6bDFXiEtH_video.mp4"
  },
  "seed": 42
}

Endpoint: POST https://fal.run/fal-ai/bytedance/seedance/v1/lite/text-to-video Endpoint ID: fal-ai/bytedance/seedance/v1/lite/text-to-video

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/bytedance/seedance/v1/lite/text-to-video",
    arguments={
        "prompt": "A little dog is running in the sunshine. The camera follows the dog as it plays in a garden."
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Input Schema

prompt

string

required

The text prompt used to generate the video

aspect_ratio

AspectRatioEnum

default:"16:9"

The aspect ratio of the generated video Default value: "16:9"Possible values: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21

resolution

ResolutionEnum

default:"720p"

Video resolution - 480p for faster generation, 720p for higher quality Default value: "720p"Possible values: 480p, 720p, 1080p

duration

DurationEnum

default:"5"

Duration of the video in seconds Default value: "5"Possible values: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12

camera_fixed

boolean

default:"false"

Whether to fix the camera position

seed

integer

Random seed to control video generation. Use -1 for random.

enable_safety_checker

boolean

default:"true"

If set to true, the safety checker will be enabled. Default value: true

num_frames

integer

The number of frames to generate. If provided, will override duration.Range: 29 to 289

Output Schema

video

File

required

Generated video file

seed

integer

required

Seed used for generation

Input Example

{
  "prompt": "A little dog is running in the sunshine. The camera follows the dog as it plays in a garden.",
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "duration": "5",
  "camera_fixed": false,
  "enable_safety_checker": true
}

Output Example

{
  "video": {
    "url": "https://v3.fal.media/files/penguin/qmLZSvOIzTKs6bDFXiEtH_video.mp4"
  },
  "seed": 42
}

Endpoint: POST https://fal.run/fal-ai/bytedance/seedance/v1/lite/reference-to-video Endpoint ID: fal-ai/bytedance/seedance/v1/lite/reference-to-video

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/bytedance/seedance/v1/lite/reference-to-video",
    arguments={
        "prompt": "The girl catches the puppy and hugs it.",
        "reference_image_urls": [
            "https://storage.googleapis.com/falserverless/example_inputs/seedance_reference.jpeg",
            "https://storage.googleapis.com/falserverless/example_inputs/seedance_reference_2.jpeg"
        ]
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Input Schema

prompt

string

required

The text prompt used to generate the video

aspect_ratio

AspectRatioEnum

default:"auto"

The aspect ratio of the generated video Default value: "auto"Possible values: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto

resolution

ResolutionEnum

default:"720p"

Video resolution - 480p for faster generation, 720p for higher quality Default value: "720p"Possible values: 480p, 720p

duration

DurationEnum

default:"5"

Duration of the video in seconds Default value: "5"Possible values: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12

camera_fixed

boolean

default:"false"

Whether to fix the camera position

seed

integer

Random seed to control video generation. Use -1 for random.

enable_safety_checker

boolean

default:"true"

If set to true, the safety checker will be enabled. Default value: true

num_frames

integer

The number of frames to generate. If provided, will override duration.Range: 29 to 289

reference_image_urls

list<string>

required

Reference images to generate the video with.

Output Schema

video

File

required

Generated video file

seed

integer

required

Seed used for generation

Input Example

{
  "prompt": "The girl catches the puppy and hugs it.",
  "aspect_ratio": "auto",
  "resolution": "720p",
  "duration": "5",
  "camera_fixed": false,
  "enable_safety_checker": true,
  "reference_image_urls": [
    "https://storage.googleapis.com/falserverless/example_inputs/seedance_reference.jpeg",
    "https://storage.googleapis.com/falserverless/example_inputs/seedance_reference_2.jpeg"
  ]
}

Output Example

{
  "video": {
    "url": "https://storage.googleapis.com/falserverless/example_outputs/seedance_reference_output.mp4"
  },
  "seed": 42
}

Seedance 1.0 - High-Quality AI Video Generation by ByteDance

Transform your creative vision into professional videos with Seedance, ByteDance’s advanced video generation model. Available in both Pro and Lite versions, Seedance delivers exceptional text-to-video and image-to-video generation capabilities for content creators, marketers, and developers.

Overview

Seedance 1.0 is a fast and efficient video generation model that creates high-quality videos from text prompts or images. The model supports multiple aspect ratios, resolutions, and durations for versatile video generation.

Available Endpoints

Seedance Lite (Fast & Cost-Effective)

Text-to-Video: fal-ai/bytedance/seedance/v1/lite/text-to-video
Image-to-Video: fal-ai/bytedance/seedance/v1/lite/image-to-video
Resolution: Up to 720p
Duration: 5 or 10 seconds

Seedance Pro (Premium Quality)

Text-to-Video: fal-ai/bytedance/seedance/v1/pro/text-to-video
Image-to-Video: fal-ai/bytedance/seedance/v1/pro/image-to-video
Resolution: Up to 1080p
Duration: 5 or 10 seconds

Getting Started

Setting up Seedance is straightforward. First, install your preferred client: For JavaScript/TypeScript:

npm install --save @fal-ai/client

For Python:

pip install fal-client

Configure your authentication:

import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY_HERE"
});

Creating Your First Video

Text-to-Video Generation

Generate videos directly from text descriptions:

const result = await fal.subscribe("fal-ai/bytedance/seedance/v1/lite/text-to-video", {
  input: {
    prompt: "A little dog is running in the sunshine. The camera follows the dog as it plays in a garden.",
    aspect_ratio: "16:9",
    resolution: "720p",
    duration: "5"
  }
});

console.log(result.video.url);

Image-to-Video Generation

Animate still images with descriptive prompts:

const result = await fal.subscribe("fal-ai/bytedance/seedance/v1/lite/image-to-video", {
  input: {
    image_url: "https://example.com/your-image.jpg",
    prompt: "A skier glides over fresh snow, joyously smiling while kicking up large clouds of snow",
    resolution: "720p",
    duration: "5"
  }
});

API Parameters

Common Parameters

prompt (required): Descriptive text for video generation
aspect_ratio: “16:9”, “9:16”, or “1:1”
resolution: “480p”, “720p”, or “1080p” (Pro only)
duration: “5” or “10” (seconds)
seed: Random seed for reproducible results (use -1 for random)

Image-to-Video Specific

image_url (required): URL of the input image
Supported formats: jpg, jpeg, png, webp, gif, avif

Advanced Features

Camera Movement Instructions (Pro)

Seedance Pro supports camera movement instructions using square brackets:

const result = await fal.subscribe("fal-ai/bytedance/seedance/v1/pro/text-to-video", {
  input: {
    prompt: "A bright blue race car speeds along a snowy racetrack. [Low-angle shot] Captures several cars speeding along the racetrack through a harsh snowstorm. [Overhead shot] The camera gradually pulls upward, revealing the full race scene",
    resolution: "1080p",
    duration: "10"
  }
});

Supported movements include:

Truck left/right, Pan left/right
Push in/Pull out, Pedestal up/down
Tilt up/down, Zoom in/out
Shake, Tracking shot, Static shot

File Upload Support

Upload local files for image-to-video generation:

import { fal } from "@fal-ai/client";

const file = new File([imageData], "image.jpg", { type: "image/jpeg" });
const url = await fal.storage.upload(file);

const result = await fal.subscribe("fal-ai/bytedance/seedance/v1/lite/image-to-video", {
  input: {
    image_url: url,
    prompt: "Animate this scene with gentle movement",
    resolution: "720p",
    duration: "5"
  }
});

Pricing

Seedance Lite

$0.18 per 720p 5-second video
$1.80 per million video tokens
Formula: tokens = (height × width × FPS × duration) / 1024

Seedance Pro

~$0.62 per 1080p 5-second video
$2.50 per million video tokens
Premium quality with advanced features

Best Practices

For Optimal Results

Write Clear, Detailed Prompts
- Begin with the main subject
- Include important visual details
- Specify desired movement or camera actions
- Use camera movement instructions in Pro for cinematic effects
Optimize Performance
- Start with shorter durations (5 seconds) during testing
- Use Lite for rapid prototyping and social media content
- Choose Pro for professional productions requiring highest quality
Image-to-Video Tips
- Use high-quality input images
- Ensure images have clear subjects
- Match prompt descriptions to image content
- Consider aspect ratio compatibility

Use Cases

Seedance Lite - Perfect for:

Social media content (TikTok, Instagram Reels)
Quick creative concepts and prototypes
Educational content and demonstrations
Marketing previews and teasers

Seedance Pro - Ideal for:

Professional marketing campaigns
High-quality brand content
Cinematic storytelling with multi-shot sequences
Premium product demonstrations

Error Handling

Implement robust error handling for production use:

try {
  const result = await fal.subscribe("fal-ai/bytedance/seedance/v1/lite/text-to-video", {
    input: {
      prompt: "Your creative prompt",
      resolution: "720p",
      duration: "5"
    }
  });
  console.log(result.video.url);
} catch (error) {
  console.error("Video generation failed:", error.message);
  // Implement fallback logic
}

Queue Management

For long-running requests, use the queue API:

// Submit request
const { request_id } = await fal.queue.submit("fal-ai/bytedance/seedance/v1/pro/text-to-video", {
  input: {
    prompt: "Complex multi-shot video prompt",
    resolution: "1080p",
    duration: "10"
  },
  webhookUrl: "https://your-webhook.url/results"
});

// Check status
const status = await fal.queue.status("fal-ai/bytedance/seedance/v1/pro/text-to-video", {
  requestId: request_id
});

// Get result
const result = await fal.queue.result("fal-ai/bytedance/seedance/v1/pro/text-to-video", {
  requestId: request_id
});

Technical Details

Inference Speed: ~41 seconds for 5-second 1080p video on L20 GPU
Concurrency: Up to 10 simultaneous renders
API Authentication: Key-based authentication via FAL_KEY
Output Format: MP4 video files
Partner Model: Available through fal.ai’s inference infrastructure

Support

For implementation assistance and additional resources:

Documentation: fal.ai Documentation
API Reference: View model-specific endpoints and parameters
Model Gallery: Explore all Seedance variants at fal.ai/models
Dashboard: Manage API keys at fal.ai/dashboard

Getting Started Today

Ready to transform your ideas into compelling videos? Sign up at fal.ai to get your API key and start creating with Seedance. Both Pro and Lite versions offer unique advantages for different use cases, ensuring you have the right tool for your creative needs.

Seedance 1.0 Pro — Video Generation
Bytedance — Video Generation
Seedance 1.0 Lite — Video Generation

Limitations

aspect_ratio restricted to: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto
resolution restricted to: 480p, 720p, 1080p
num_frames range: 29 to 289
Content moderation via safety checker
aspect_ratio restricted to: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21
resolution restricted to: 480p, 720p

Video Generation

Image Generation

Audio

Vision

3D

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

​Seedance 1.0 - High-Quality AI Video Generation by ByteDance

​Overview

​Available Endpoints

​Getting Started

​Creating Your First Video

​Text-to-Video Generation

​Image-to-Video Generation

​API Parameters

​Common Parameters

​Image-to-Video Specific

​Advanced Features

​Camera Movement Instructions (Pro)

​File Upload Support

​Pricing

​Best Practices

​For Optimal Results

​Use Cases

​Error Handling

​Queue Management

​Technical Details

​Support

​Getting Started Today

​Related

​Limitations

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Seedance 1.0 - High-Quality AI Video Generation by ByteDance

Overview

Available Endpoints

Getting Started

Creating Your First Video

Text-to-Video Generation

Image-to-Video Generation

API Parameters

Common Parameters

Image-to-Video Specific

Advanced Features

Camera Movement Instructions (Pro)

File Upload Support

Pricing

Best Practices

For Optimal Results

Use Cases

Error Handling

Queue Management

Technical Details

Support

Getting Started Today

Related

Limitations