Skip to main content
POST
/
v1
/
videos
Seedance 2.0 Image-to-Video
curl --request POST \
  --url https://api.powertokens.ai/v1/videos \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "dreamina-seedance-2-0-260128",
  "media": [
    {
      "type": "text",
      "text": "The camera moves slowly inward, the girl smiles"
    },
    {
      "type": "first_frame",
      "url": "https://example.com/first-frame.jpg"
    }
  ],
  "seconds": "5",
  "size": "720p",
  "ratio": "adaptive"
}
'

Authorizations

​
Authorization
string
header
required

Pass Authorization: Bearer <token> in the request header.

Body

application/json
​
model
enum<string>
required

Video generation model name.

Available options:
dreamina-seedance-2-0-260128
​
media
object[]
required

Multimodal input array. First frame image-to-video must contain inputs with type: "first_frame" and type: "text".

Minimum array length: 2
​
seconds
enum<string>
default:5

Video generation duration (seconds) in string format. Supports "-1" (smart selection) or "4" to "15".

Available options:
4,
5,
6,
7,
8,
9,
10,
11,
12,
15,
-1
Example:

"5"

​
size
enum<string>
default:720p

Video output resolution specification. Defaults to 720p.

Available options:
480p,
720p,
1080p
​
ratio
enum<string>
default:adaptive

Video aspect ratio. First frame image-to-video defaults to adaptive.

Available options:
16:9,
4:3,
1:1,
3:4,
9:16,
21:9,
adaptive
​
seed
integer
default:-1

Random seed, range [-1, 4294967295].

Required range: -1 <= x <= 4294967295
​
watermark
boolean
default:false

Whether to add a watermark.

​
generate_audio
boolean
default:true

Whether to generate sound synchronized with the visuals. Supported by the 2.0 series.

​
return_last_frame
boolean
default:false

Whether to return the last frame image.

​
safety_identifier
string

Unique identifier for the end user, used for compliance checks. Supported only by the 2.0 series, length not exceeding 64 characters.

Response

200

Submission successful, returns a video task object.