Seedance 2.0 API Documentation — Uncensored AI Video Generation

Overview

The Seedance 2.0 API provides programmatic access to uncensored AI video generation. Through this API, you can:

Upload media — Upload images or videos to cloud storage as reference material
Generate videos — Create AI videos from text descriptions, reference images, or reference videos
Track progress — Poll task status and retrieve generated video URLs

Typical Workflow

1Upload media (optional)→2Submit generation task→3Poll task status→4Get video URL

Authentication

All API requests must include an API key in the HTTP header for authentication.

Header Format

http

X-API-Key: <your_api_key>

API Key Rules

Format	String provided by admin
How to get	Contact admin to activate and receive your key

Request Example

bash

curl https://api.seedance2.movie/api/v1/video/balance \
  -H "X-API-Key: <your_api_key>"

Keep your API key secure. Do not expose it in frontend code or public repositories.

Common Info

Base URL

url

https://api.seedance2.movie

Request Format

• Content-Type: application/json
• Encoding: UTF-8
• HTTP methods: specified per endpoint

Response Format

All endpoints return a unified JSON structure:

Success Response

json

{
  "code": "200",
  "message": "Success",
  "result": {
    "...": "..."
  }
}

Error Response

json

{
  "code": "INVALID_PARAMETER",
  "message": "Invalid parameter: duration must be 4-15"
}

Response Fields

Field	Type	Description
code	string	Status code. "200" means success, other values indicate specific errors
message	string	Status description. "Success" when successful
result	object \| null	Business data. May be null on error

File Upload

Before submitting a generation task, if you need to use reference images or videos, you must first obtain a presigned upload URL, then upload the file via HTTP PUT.

Get Presigned Upload URL

POST/api/v1/video/upload/presign

Query Parameters

Field	Type	Required	Default	Description
filename	string	Yes	—	File name (max 128 characters)
content_type	string	Yes	—	File MIME type

Allowed Content Types

image/png — .png

image/jpeg — .jpg, .jpeg

image/webp — .webp

video/mp4 — .mp4

video/quicktime — .mov

video/webm — .webm

Success Response

json

{
  "code": "200",
  "message": "Success",
  "result": {
    "presigned_url": "https://s3.amazonaws.com/bucket/api/uploads/1/uuid_scene.png?X-Amz-...",
    "file_path": "api/uploads/1/uuid_scene.png",
    "expires_in": 3600
  }
}

Field	Description
presigned_url	Presigned upload URL (time-limited, use promptly)
file_path	Unique file identifier in cloud storage — use this when referencing the file in tasks
expires_in	URL expiration time in seconds

Upload File

After obtaining the presigned URL, upload the file directly via HTTP PUT:

bash

curl -X PUT "<presigned_url>" \
  -H "Content-Type: image/png" \
  --data-binary @./scene.png

• The Content-Type during upload must match the content_type used when getting the presigned URL
• Presigned URLs have a limited validity period — upload promptly after obtaining one
• After uploading, use the returned file_path to reference the file in generation tasks

Submit Video Generation Task

POST/api/v1/video/task

Request Body (JSON)

Field	Type	Required	Default	Description
model	string	No	seedance-2.0	Model selection
content	array	Yes	—	Input content array (at least 1 item)
resolution	string	No	720p	Video resolution
ratio	string	No	16:9	Aspect ratio
duration	integer	No	5	Video duration in seconds (4–15)
generate_audio	boolean	No	false	Whether to generate audio
seed	integer	No	—	Random seed (-1 or above, optional)
watermark	boolean	No	false	Whether to add watermark
callback_url	string	No	—	Callback URL for task completion notification (max 512 chars)
return_last_frame	boolean	No	false	Whether to return the last frame image

Model Options

• seedance-2.0 — Standard model (default)
• seedance-2.0-fast — Fast model

Resolution Options

• 480p
• 720p (default)
• 1080p

Aspect Ratio Options

16:99:164:33:41:121:9

Content Types

Each item in the content array must have a type field:

• text — Text prompt describing the video
• image_url — Reference image (use file_path from upload)
• video_url — Reference video (use file_path from upload)
• audio_url — Reference audio
• sample_id — Sample ID for reference

bash

curl -X POST https://api.seedance2.movie/api/v1/video/task \
  -H "X-API-Key: <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0",
    "content": [
      { "type": "text", "text": "A cat running under cherry blossoms, warm sunlight" }
    ],
    "resolution": "720p",
    "ratio": "16:9",
    "duration": 8,
    "generate_audio": false
  }'

Success Response

json

{
  "code": "200",
  "message": "Success",
  "result": {
    "task_id": "a1b2c3d4e5f6...",
    "status": "pending",
    "credit_cost": 14.4
  }
}

Query Task Status

GET/api/v1/video/task/{task_id}

Path Parameters

task_id

Task ID returned from submit

bash

curl https://api.seedance2.movie/api/v1/video/task/a1b2c3d4e5f6 \
  -H "X-API-Key: <your_api_key>"

Success Response

json

{
  "code": "200",
  "message": "Success",
  "result": {
    "task_id": "a1b2c3d4e5f6...",
    "model": "seedance-2.0",
    "status": "completed",
    "resolution": "720p",
    "ratio": "16:9",
    "duration": 8,
    "generate_audio": false,
    "seed": null,
    "video_url": "https://cdn.example.com/video.mp4?token=...",
    "last_frame_url": null,
    "error_code": null,
    "error_message": null,
    "credit_cost": 14.4,
    "created_at": "2025-01-15T10:30:00Z",
    "updated_at": "2025-01-15T10:33:45Z"
  }
}

Field	Description
task_id	Task ID
model	Model used
status	Task status (see status table below)
resolution	Video resolution
ratio	Aspect ratio
duration	Video duration in seconds
generate_audio	Whether audio was generated
seed	Random seed used
video_url	Generated video download URL (available on success, signed URL valid for 7 days)
last_frame_url	Last frame image URL (if requested)
error_code	Error code (on failure)
error_message	Error description (on failure)
credit_cost	Credits consumed
created_at	Task creation time (ISO 8601)
updated_at	Last update time (ISO 8601)

Task Status

pending — Waiting to be processed (not terminal)

queued — Queued for generation (not terminal)

processing — Video is being generated (not terminal)

completed — Generation successful (terminal)

failed — Generation failed (terminal)

cancelled — Task was cancelled (terminal)

expired — Task expired (terminal)

Polling Advice

• Recommended polling interval: 5–10 seconds
• Stop polling when status is completed, failed, cancelled, or expired
• Generation typically takes 1–5 minutes depending on duration and resolution

Task List

GET/api/v1/video/tasks

Paginated query of all tasks for the authenticated API key.

Query Parameters

Field	Type	Required	Default	Description
page	integer	No	1	Page number (starts from 1, default: 1)
page_size	integer	No	20	Items per page (1–100, default: 20)
status	string	No	—	Filter by task status (optional)

bash

curl "https://api.seedance2.movie/api/v1/video/tasks?page=1&page_size=10" \
  -H "X-API-Key: <your_api_key>"

Success Response

json

{
  "code": "200",
  "message": "Success",
  "result": {
    "data": [
      "{ ... task objects ... }"
    ],
    "total": 42,
    "page": 1,
    "page_size": 10
  }
}

Cancel Task

POST/api/v1/video/task/{task_id}/cancel

Cancel a task that is in a non-terminal state. Tasks in pending status can be cancelled immediately. Tasks in queued or processing status will attempt cancellation with the provider.

bash

curl -X POST https://api.seedance2.movie/api/v1/video/task/a1b2c3d4e5f6/cancel \
  -H "X-API-Key: <your_api_key>"

Success Response

json

{
  "code": "200",
  "message": "Success",
  "result": {
    "task_id": "a1b2c3d4e5f6...",
    "status": "cancelled"
  }
}

Tasks in terminal states (completed, failed, cancelled, expired) cannot be cancelled and will return a TASK_CANCEL_NOT_ALLOWED error.

Balance Query

GET/api/v1/video/balance

Query the credit balance associated with the current API key.

bash

curl https://api.seedance2.movie/api/v1/video/balance \
  -H "X-API-Key: <your_api_key>"

Success Response

json

{
  "code": "200",
  "message": "Success",
  "result": {
    "total_credits": 10000,
    "used_credits": 3250.5,
    "remain_credits": 6749.5
  }
}

Field	Description
total_credits	Total credits in account
used_credits	Credits consumed
remain_credits	Remaining available credits

Pricing

Billing Model

The API uses a post-pay model: credits are deducted only after a task completes successfully. Failed tasks are not charged.

text

Cost = price_per_second × duration

Price Per Second (Credits)

Model	Resolution	Price / Second	Example (8s)
seedance-2.0	1080p	4.5	36.0
seedance-2.0	720p	1.8	14.4
seedance-2.0	480p	0.9	7.2
seedance-2.0-fast	1080p	3.312	26.50
seedance-2.0-fast	720p	1.44	11.52
seedance-2.0-fast	480p	0.72	5.76

The example column shows the cost for an 8-second video: price_per_second × 8.

For credit recharges, please contact the administrator.

Error Codes

Business Error Codes

Code	Description
INVALID_API_KEY	Invalid or disabled API key
INVALID_PARAMETER	Invalid parameter value or format
MISSING_PARAMETER	Required parameter is missing
INSUFFICIENT_CREDIT	Insufficient credit balance
CREDIT_DEDUCT_FAILED	Credit deduction failed — please retry
TASK_NOT_FOUND	Task not found or does not belong to your API key
TASK_SUBMIT_FAILED	Task submission failed — please retry
TASK_CANCEL_NOT_ALLOWED	Task cannot be cancelled in its current status
CONCURRENCY_LIMIT_REACHED	Max concurrent tasks reached — task is queued
FILE_UPLOAD_FAILED	Failed to generate upload URL
VIDEO_DOWNLOAD_FAILED	Video processing failed
CONTENT_MODERATION_FAILED	Content moderation failed — input or output contains sensitive content
COPYRIGHT_VIOLATION	Content may violate copyright restrictions
PRIVACY_VIOLATION	Input contains real person imagery which is not allowed
SERVICE_BUSY	Service is temporarily busy — please retry later
RATE_LIMIT_EXCEEDED	Rate limit exceeded — please slow down
INTERNAL_ERROR	Internal server error

HTTP Status Mapping

While most responses use HTTP 200 with error details in the body, the following HTTP status codes may also be returned:

• 401 — Invalid API key
• 400 — Invalid parameter, missing parameter, content moderation, or cancel not allowed
• 402 — Insufficient credits
• 404 — Task not found
• 429 — Rate limit or concurrency limit reached
• 500 — Internal server error or submission failure
• 503 — Service busy

Code Examples

Image-to-Video (Python)

Upload an image and generate a video from it:

python

import requests
import time

API_BASE = "https://api.seedance2.movie"
API_KEY = "<your_api_key>"
HEADERS = {
    "X-API-Key": API_KEY,
    "Content-Type": "application/json",
}


def upload_file(file_path, file_name, content_type):
    """Step 1: Get presigned URL and upload file"""
    resp = requests.post(
        f"{API_BASE}/api/v1/video/upload/presign",
        headers=HEADERS,
        params={"filename": file_name, "content_type": content_type},
    )
    resp.raise_for_status()
    data = resp.json()["result"]

    # Upload file to presigned URL
    with open(file_path, "rb") as f:
        requests.put(
            data["presigned_url"],
            headers={"Content-Type": content_type},
            data=f,
        ).raise_for_status()

    print(f"Uploaded: {data['file_path']}")
    return data["file_path"]


def submit_task(file_path):
    """Step 2: Submit image-to-video task"""
    resp = requests.post(
        f"{API_BASE}/api/v1/video/task",
        headers=HEADERS,
        json={
            "model": "seedance-2.0",
            "content": [
                {"type": "image_url", "image_url": file_path},
                {"type": "text", "text": "The character slowly turns around, wind blowing through hair"},
            ],
            "resolution": "720p",
            "ratio": "16:9",
            "duration": 8,
        },
    )
    resp.raise_for_status()
    result = resp.json()["result"]
    print(f"Task submitted: {result['task_id']}")
    return result["task_id"]


def poll_task(task_id, interval=5, timeout=600):
    """Step 3: Poll task status"""
    elapsed = 0
    while elapsed < timeout:
        resp = requests.get(
            f"{API_BASE}/api/v1/video/task/{task_id}",
            headers=HEADERS,
        )
        task = resp.json()["result"]
        print(f"[{elapsed}s] Status: {task['status']}")

        if task["status"] == "completed":
            print(f"Video URL: {task['video_url']}")
            return task
        if task["status"] in ("failed", "cancelled", "expired"):
            print(f"Failed: {task.get('error_message', 'Unknown error')}")
            return task

        time.sleep(interval)
        elapsed += interval

    print("Polling timeout")
    return None


if __name__ == "__main__":
    path = upload_file("./character.png", "character.png", "image/png")
    task_id = submit_task(path)
    poll_task(task_id)

Text-to-Video (Python)

Generate a video from a text prompt without uploading media:

python

import requests
import time

API_BASE = "https://api.seedance2.movie"
HEADERS = {
    "X-API-Key": "<your_api_key>",
    "Content-Type": "application/json",
}

# Submit text-to-video task
resp = requests.post(
    f"{API_BASE}/api/v1/video/task",
    headers=HEADERS,
    json={
        "model": "seedance-2.0",
        "content": [
            {"type": "text", "text": "A spaceship gliding past Saturn's rings, epic cinematic shot"}
        ],
        "resolution": "720p",
        "ratio": "21:9",
        "duration": 10,
        "generate_audio": True,
    },
)
task_id = resp.json()["result"]["task_id"]
print(f"Task submitted: {task_id}")

# Poll until complete
while True:
    resp = requests.get(
        f"{API_BASE}/api/v1/video/task/{task_id}",
        headers=HEADERS,
    )
    task = resp.json()["result"]
    print(f"Status: {task['status']}")

    if task["status"] == "completed":
        print(f"Video URL: {task['video_url']}")
        break
    elif task["status"] in ("failed", "cancelled", "expired"):
        print(f"Error: {task.get('error_message')}")
        break

    time.sleep(8)

Complete Flow (cURL)

Step-by-step API usage with cURL:

bash

# Step 1: Get presigned upload URL
curl -X POST "https://api.seedance2.movie/api/v1/video/upload/presign?filename=scene.png&content_type=image/png" \
  -H "X-API-Key: <your_api_key>"

# Step 2: Upload file (use presigned_url from step 1)
curl -X PUT "<presigned_url>" \
  -H "Content-Type: image/png" \
  --data-binary @./scene.png

# Step 3: Submit generation task (use file_path from step 1)
curl -X POST "https://api.seedance2.movie/api/v1/video/task" \
  -H "X-API-Key: <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "content": [
      {"type": "image_url", "image_url": "<file_path>"},
      {"type": "text", "text": "The scene comes alive, flowers blooming"}
    ],
    "duration": 8,
    "ratio": "16:9"
  }'

# Step 4: Query task status (use task_id from step 3)
curl "https://api.seedance2.movie/api/v1/video/task/<task_id>" \
  -H "X-API-Key: <your_api_key>"

Overview

The Seedance 2.0 API provides programmatic access to uncensored AI video generation. Through this API, you can:

Upload media — Upload images or videos to cloud storage as reference material
Generate videos — Create AI videos from text descriptions, reference images, or reference videos
Track progress — Poll task status and retrieve generated video URLs

Typical Workflow

1Upload media (optional)→2Submit generation task→3Poll task status→4Get video URL

Authentication

All API requests must include an API key in the HTTP header for authentication.

Header Format

http

X-API-Key: <your_api_key>

API Key Rules

Format	String provided by admin
How to get	Contact admin to activate and receive your key

Request Example

bash

curl https://api.seedance2.movie/api/v1/video/balance \
  -H "X-API-Key: <your_api_key>"

Keep your API key secure. Do not expose it in frontend code or public repositories.

Common Info

Base URL

url

https://api.seedance2.movie

Request Format

• Content-Type: application/json
• Encoding: UTF-8
• HTTP methods: specified per endpoint

Response Format

All endpoints return a unified JSON structure:

Success Response

json

{
  "code": "200",
  "message": "Success",
  "result": {
    "...": "..."
  }
}

Error Response

json

{
  "code": "INVALID_PARAMETER",
  "message": "Invalid parameter: duration must be 4-15"
}

Response Fields

Field	Type	Description
code	string	Status code. "200" means success, other values indicate specific errors
message	string	Status description. "Success" when successful
result	object \| null	Business data. May be null on error

File Upload

Before submitting a generation task, if you need to use reference images or videos, you must first obtain a presigned upload URL, then upload the file via HTTP PUT.

Get Presigned Upload URL

POST/api/v1/video/upload/presign

Query Parameters

Field	Type	Required	Default	Description
filename	string	Yes	—	File name (max 128 characters)
content_type	string	Yes	—	File MIME type

Allowed Content Types

image/png — .png

image/jpeg — .jpg, .jpeg

image/webp — .webp

video/mp4 — .mp4

video/quicktime — .mov

video/webm — .webm

Success Response

json

{
  "code": "200",
  "message": "Success",
  "result": {
    "presigned_url": "https://s3.amazonaws.com/bucket/api/uploads/1/uuid_scene.png?X-Amz-...",
    "file_path": "api/uploads/1/uuid_scene.png",
    "expires_in": 3600
  }
}

Field	Description
presigned_url	Presigned upload URL (time-limited, use promptly)
file_path	Unique file identifier in cloud storage — use this when referencing the file in tasks
expires_in	URL expiration time in seconds

Upload File

After obtaining the presigned URL, upload the file directly via HTTP PUT:

bash

curl -X PUT "<presigned_url>" \
  -H "Content-Type: image/png" \
  --data-binary @./scene.png

• The Content-Type during upload must match the content_type used when getting the presigned URL
• Presigned URLs have a limited validity period — upload promptly after obtaining one
• After uploading, use the returned file_path to reference the file in generation tasks

Submit Video Generation Task

POST/api/v1/video/task

Request Body (JSON)

Field	Type	Required	Default	Description
model	string	No	seedance-2.0	Model selection
content	array	Yes	—	Input content array (at least 1 item)
resolution	string	No	720p	Video resolution
ratio	string	No	16:9	Aspect ratio
duration	integer	No	5	Video duration in seconds (4–15)
generate_audio	boolean	No	false	Whether to generate audio
seed	integer	No	—	Random seed (-1 or above, optional)
watermark	boolean	No	false	Whether to add watermark
callback_url	string	No	—	Callback URL for task completion notification (max 512 chars)
return_last_frame	boolean	No	false	Whether to return the last frame image

Model Options

• seedance-2.0 — Standard model (default)
• seedance-2.0-fast — Fast model

Resolution Options

• 480p
• 720p (default)
• 1080p

Aspect Ratio Options

16:99:164:33:41:121:9

Content Types

Each item in the content array must have a type field:

• text — Text prompt describing the video
• image_url — Reference image (use file_path from upload)
• video_url — Reference video (use file_path from upload)
• audio_url — Reference audio
• sample_id — Sample ID for reference

bash

curl -X POST https://api.seedance2.movie/api/v1/video/task \
  -H "X-API-Key: <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0",
    "content": [
      { "type": "text", "text": "A cat running under cherry blossoms, warm sunlight" }
    ],
    "resolution": "720p",
    "ratio": "16:9",
    "duration": 8,
    "generate_audio": false
  }'

Success Response

json

{
  "code": "200",
  "message": "Success",
  "result": {
    "task_id": "a1b2c3d4e5f6...",
    "status": "pending",
    "credit_cost": 14.4
  }
}

Query Task Status

GET/api/v1/video/task/{task_id}

Path Parameters

task_id

Task ID returned from submit

bash

curl https://api.seedance2.movie/api/v1/video/task/a1b2c3d4e5f6 \
  -H "X-API-Key: <your_api_key>"

Success Response

json

{
  "code": "200",
  "message": "Success",
  "result": {
    "task_id": "a1b2c3d4e5f6...",
    "model": "seedance-2.0",
    "status": "completed",
    "resolution": "720p",
    "ratio": "16:9",
    "duration": 8,
    "generate_audio": false,
    "seed": null,
    "video_url": "https://cdn.example.com/video.mp4?token=...",
    "last_frame_url": null,
    "error_code": null,
    "error_message": null,
    "credit_cost": 14.4,
    "created_at": "2025-01-15T10:30:00Z",
    "updated_at": "2025-01-15T10:33:45Z"
  }
}

Field	Description
task_id	Task ID
model	Model used
status	Task status (see status table below)
resolution	Video resolution
ratio	Aspect ratio
duration	Video duration in seconds
generate_audio	Whether audio was generated
seed	Random seed used
video_url	Generated video download URL (available on success, signed URL valid for 7 days)
last_frame_url	Last frame image URL (if requested)
error_code	Error code (on failure)
error_message	Error description (on failure)
credit_cost	Credits consumed
created_at	Task creation time (ISO 8601)
updated_at	Last update time (ISO 8601)

Task Status

pending — Waiting to be processed (not terminal)

queued — Queued for generation (not terminal)

processing — Video is being generated (not terminal)

completed — Generation successful (terminal)

failed — Generation failed (terminal)

cancelled — Task was cancelled (terminal)

expired — Task expired (terminal)

Polling Advice

• Recommended polling interval: 5–10 seconds
• Stop polling when status is completed, failed, cancelled, or expired
• Generation typically takes 1–5 minutes depending on duration and resolution

Task List

GET/api/v1/video/tasks

Paginated query of all tasks for the authenticated API key.

Query Parameters

Field	Type	Required	Default	Description
page	integer	No	1	Page number (starts from 1, default: 1)
page_size	integer	No	20	Items per page (1–100, default: 20)
status	string	No	—	Filter by task status (optional)

bash

curl "https://api.seedance2.movie/api/v1/video/tasks?page=1&page_size=10" \
  -H "X-API-Key: <your_api_key>"

Success Response

json

{
  "code": "200",
  "message": "Success",
  "result": {
    "data": [
      "{ ... task objects ... }"
    ],
    "total": 42,
    "page": 1,
    "page_size": 10
  }
}

Cancel Task

POST/api/v1/video/task/{task_id}/cancel

Cancel a task that is in a non-terminal state. Tasks in pending status can be cancelled immediately. Tasks in queued or processing status will attempt cancellation with the provider.

bash

curl -X POST https://api.seedance2.movie/api/v1/video/task/a1b2c3d4e5f6/cancel \
  -H "X-API-Key: <your_api_key>"

Success Response

json

{
  "code": "200",
  "message": "Success",
  "result": {
    "task_id": "a1b2c3d4e5f6...",
    "status": "cancelled"
  }
}

Tasks in terminal states (completed, failed, cancelled, expired) cannot be cancelled and will return a TASK_CANCEL_NOT_ALLOWED error.

Balance Query

GET/api/v1/video/balance

Query the credit balance associated with the current API key.

bash

curl https://api.seedance2.movie/api/v1/video/balance \
  -H "X-API-Key: <your_api_key>"

Success Response

json

{
  "code": "200",
  "message": "Success",
  "result": {
    "total_credits": 10000,
    "used_credits": 3250.5,
    "remain_credits": 6749.5
  }
}

Field	Description
total_credits	Total credits in account
used_credits	Credits consumed
remain_credits	Remaining available credits

Pricing

Billing Model

The API uses a post-pay model: credits are deducted only after a task completes successfully. Failed tasks are not charged.

text

Cost = price_per_second × duration

Price Per Second (Credits)

Model	Resolution	Price / Second	Example (8s)
seedance-2.0	1080p	4.5	36.0
seedance-2.0	720p	1.8	14.4
seedance-2.0	480p	0.9	7.2
seedance-2.0-fast	1080p	3.312	26.50
seedance-2.0-fast	720p	1.44	11.52
seedance-2.0-fast	480p	0.72	5.76

The example column shows the cost for an 8-second video: price_per_second × 8.

For credit recharges, please contact the administrator.

Error Codes

Business Error Codes

Code	Description
INVALID_API_KEY	Invalid or disabled API key
INVALID_PARAMETER	Invalid parameter value or format
MISSING_PARAMETER	Required parameter is missing
INSUFFICIENT_CREDIT	Insufficient credit balance
CREDIT_DEDUCT_FAILED	Credit deduction failed — please retry
TASK_NOT_FOUND	Task not found or does not belong to your API key
TASK_SUBMIT_FAILED	Task submission failed — please retry
TASK_CANCEL_NOT_ALLOWED	Task cannot be cancelled in its current status
CONCURRENCY_LIMIT_REACHED	Max concurrent tasks reached — task is queued
FILE_UPLOAD_FAILED	Failed to generate upload URL
VIDEO_DOWNLOAD_FAILED	Video processing failed
CONTENT_MODERATION_FAILED	Content moderation failed — input or output contains sensitive content
COPYRIGHT_VIOLATION	Content may violate copyright restrictions
PRIVACY_VIOLATION	Input contains real person imagery which is not allowed
SERVICE_BUSY	Service is temporarily busy — please retry later
RATE_LIMIT_EXCEEDED	Rate limit exceeded — please slow down
INTERNAL_ERROR	Internal server error

HTTP Status Mapping

While most responses use HTTP 200 with error details in the body, the following HTTP status codes may also be returned:

• 401 — Invalid API key
• 400 — Invalid parameter, missing parameter, content moderation, or cancel not allowed
• 402 — Insufficient credits
• 404 — Task not found
• 429 — Rate limit or concurrency limit reached
• 500 — Internal server error or submission failure
• 503 — Service busy

Code Examples

Image-to-Video (Python)

Upload an image and generate a video from it:

python

import requests
import time

API_BASE = "https://api.seedance2.movie"
API_KEY = "<your_api_key>"
HEADERS = {
    "X-API-Key": API_KEY,
    "Content-Type": "application/json",
}


def upload_file(file_path, file_name, content_type):
    """Step 1: Get presigned URL and upload file"""
    resp = requests.post(
        f"{API_BASE}/api/v1/video/upload/presign",
        headers=HEADERS,
        params={"filename": file_name, "content_type": content_type},
    )
    resp.raise_for_status()
    data = resp.json()["result"]

    # Upload file to presigned URL
    with open(file_path, "rb") as f:
        requests.put(
            data["presigned_url"],
            headers={"Content-Type": content_type},
            data=f,
        ).raise_for_status()

    print(f"Uploaded: {data['file_path']}")
    return data["file_path"]


def submit_task(file_path):
    """Step 2: Submit image-to-video task"""
    resp = requests.post(
        f"{API_BASE}/api/v1/video/task",
        headers=HEADERS,
        json={
            "model": "seedance-2.0",
            "content": [
                {"type": "image_url", "image_url": file_path},
                {"type": "text", "text": "The character slowly turns around, wind blowing through hair"},
            ],
            "resolution": "720p",
            "ratio": "16:9",
            "duration": 8,
        },
    )
    resp.raise_for_status()
    result = resp.json()["result"]
    print(f"Task submitted: {result['task_id']}")
    return result["task_id"]


def poll_task(task_id, interval=5, timeout=600):
    """Step 3: Poll task status"""
    elapsed = 0
    while elapsed < timeout:
        resp = requests.get(
            f"{API_BASE}/api/v1/video/task/{task_id}",
            headers=HEADERS,
        )
        task = resp.json()["result"]
        print(f"[{elapsed}s] Status: {task['status']}")

        if task["status"] == "completed":
            print(f"Video URL: {task['video_url']}")
            return task
        if task["status"] in ("failed", "cancelled", "expired"):
            print(f"Failed: {task.get('error_message', 'Unknown error')}")
            return task

        time.sleep(interval)
        elapsed += interval

    print("Polling timeout")
    return None


if __name__ == "__main__":
    path = upload_file("./character.png", "character.png", "image/png")
    task_id = submit_task(path)
    poll_task(task_id)

Text-to-Video (Python)

Generate a video from a text prompt without uploading media:

python

import requests
import time

API_BASE = "https://api.seedance2.movie"
HEADERS = {
    "X-API-Key": "<your_api_key>",
    "Content-Type": "application/json",
}

# Submit text-to-video task
resp = requests.post(
    f"{API_BASE}/api/v1/video/task",
    headers=HEADERS,
    json={
        "model": "seedance-2.0",
        "content": [
            {"type": "text", "text": "A spaceship gliding past Saturn's rings, epic cinematic shot"}
        ],
        "resolution": "720p",
        "ratio": "21:9",
        "duration": 10,
        "generate_audio": True,
    },
)
task_id = resp.json()["result"]["task_id"]
print(f"Task submitted: {task_id}")

# Poll until complete
while True:
    resp = requests.get(
        f"{API_BASE}/api/v1/video/task/{task_id}",
        headers=HEADERS,
    )
    task = resp.json()["result"]
    print(f"Status: {task['status']}")

    if task["status"] == "completed":
        print(f"Video URL: {task['video_url']}")
        break
    elif task["status"] in ("failed", "cancelled", "expired"):
        print(f"Error: {task.get('error_message')}")
        break

    time.sleep(8)

Complete Flow (cURL)

Step-by-step API usage with cURL:

bash

# Step 1: Get presigned upload URL
curl -X POST "https://api.seedance2.movie/api/v1/video/upload/presign?filename=scene.png&content_type=image/png" \
  -H "X-API-Key: <your_api_key>"

# Step 2: Upload file (use presigned_url from step 1)
curl -X PUT "<presigned_url>" \
  -H "Content-Type: image/png" \
  --data-binary @./scene.png

# Step 3: Submit generation task (use file_path from step 1)
curl -X POST "https://api.seedance2.movie/api/v1/video/task" \
  -H "X-API-Key: <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "content": [
      {"type": "image_url", "image_url": "<file_path>"},
      {"type": "text", "text": "The scene comes alive, flowers blooming"}
    ],
    "duration": 8,
    "ratio": "16:9"
  }'

# Step 4: Query task status (use task_id from step 3)
curl "https://api.seedance2.movie/api/v1/video/task/<task_id>" \
  -H "X-API-Key: <your_api_key>"