Seedance 2.0 Fast I2V

curl --request POST \ --url https://api.modellix.ai/api/v1/bytedance/seedance-2.0-fast-i2v \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data ' { "first_frame_image": "https://example.com/first.jpg" } '

{ "code": 0, "message": "success", "data": { "status": "pending", "task_id": "task-abc123", "model_id": "model-123", "get_result": { "method": "GET", "url": "https://api.modellix.ai/api/v1/tasks/task-abc123" } } }

Authorizations

Authorization

string

header

required

API Key authentication. Format: Bearer YOUR_API_KEY.

Body

application/json

Option 1 — Frame mode
Option 2 — Reference mode

Seedance 2.0 Fast image-to-video. Same options as standard 2.0 I2V; resolution is limited to 480p/720p. Note: images containing real human faces are not supported per BytePlus Seedance 2.0 API.

first_frame_image

string

required

Required. Starting frame URL or Base64.

Minimum string length: 1

Example:

"https://example.com/first.jpg"

prompt

string

Optional. Video description. Maximum 10000 characters. Recommended prompt length: under 1000 words. Frame animation description.

Required string length: 1 - 10000

Example:

"The person smiles and waves at the camera"

last_frame_image

string

Optional. Ending frame URL or Base64. Requires first_frame_image.

Minimum string length: 1

Example:

"https://example.com/last.jpg"

audio_urls

string[]

Optional. Up to 3 reference audio URLs. Use [Audio n] placeholders in prompt.

Required array length: 1 - 3 elements

Audio URL.

Minimum string length: 1

ratio

enum<string>

default:16:9

Aspect ratio of the generated video.

Available options:

21:9,

16:9,

4:3,

1:1,

3:4,

9:16

duration

enum<integer>

default:5

Video duration in seconds (4-15 seconds).

Available options:

4,

5,

6,

7,

8,

9,

10,

11,

12,

13,

14,

15

seed

integer

default:-1

Random seed for reproducible generation. Use -1 for random.

Required range: -1 <= x <= 4294967295

camera_fixed

boolean

default:false

Whether to keep the camera fixed during generation.

generate_audio

boolean

default:true

Whether to generate audio.

execution_expires_after

integer

default:172800

Task expiration time in seconds.

Required range: 3600 <= x <= 259200

return_last_frame

boolean

default:false

Whether to return the last frame of the generated video.

resolution

enum<string>

default:720p

Output resolution of the video.

Available options:

480p,

720p

Response

200 - application/json

Task submitted successfully

code

integer

required

Response code, 0 indicates success

Example:

0

message

string

required

Response message

Example:

"success"

data

object

required

Detailed data about the submitted asynchronous task.

Show child attributes