video

Seedance 2.5 Pro 720p - Create video from text or image

Generate 720p video using Seedance 2.5 Pro. Supports text-to-video, image-to-video (first/last frame), and reference-to-video with up to 30 reference images (@Image1..@Image30), 10 reference videos (@Video1..@Video10) and 10 reference audios (@Audio1..@Audio10). Also supports camera motion, multishot sequences (up to 6 shots) and native audio (sound effects).

post/v1/ai/video/seedance-2-5-pro-720p

Request

  • Base URL: https://api.magnific.com
  • URL: https://api.magnific.com/v1/ai/video/seedance-2-5-pro-720p
  • Auth: API key in header x-magnific-api-key

Request body

webhook_urlstring uri

URL to receive a webhook notification when the video generation task completes. The webhook payload includes the task ID and status.

imagestring byte

Optional image to use as the first frame for image-to-video generation. Accepts a publicly accessible URL or a base64-encoded image. Mutually exclusive with reference_images and reference_videos.

image_endstring byte

Optional image to use as the last frame for image-to-video generation. Requires image. When provided together with image, the model generates a transition video between the first and last frame. Mutually exclusive with reference_images and reference_videos.

reference_imagesstring[]

Up to 30 reference images (subjects, characters, products or style references). Each item is a publicly accessible URL or a base64-encoded image. Reference them in the prompt using @Image1, @Image2, ... @Image30 (1-indexed to the array order). Mutually exclusive with image and image_end.

reference_videosstring[]

Up to 10 reference videos. Each item must be a publicly accessible HTTPS URL or a video upload file_id (upl_vid_...). Reference them in the prompt using @Video1, @Video2, ... @Video10 (1-indexed to the array order). Each video must be MP4 or MOV, 2 to 30 seconds, 24 to 60 fps, no larger than 200 MB, with 409600 to 8295044 pixels and an aspect ratio from 0.4 to 2.5. Combined duration must not exceed 30 seconds. Mutually exclusive with image and image_end.

reference_audiosstring[]

Up to 10 reference audios (2-60s each, mp3 or wav). Each item is a publicly accessible URL: unlike reference_images, this field does not take upload file_ids. Reference them in the prompt using @Audio1, @Audio2, ... @Audio10 (1-indexed to the array order).

The audio is not copied into the video. The model composes its own soundtrack, guided by the rhythm and character of what you send: a 120 BPM reference produces a soundtrack at that tempo, but it is a new recording, not your file muxed into the result. A reference with a clear beat, music or speech gives the model something to follow; a flat tone or near-silence does not.

promptstring required

Text prompt describing the video to generate. To use references, mention them as @Image1, @Video1, @Audio1, ... matching the 1-indexed order of each reference array. Maximum 40000 characters. Prompts longer than 5,000 characters are accepted, but results may become less predictable.

durationinteger

Video duration in seconds. Any integer from 4 to 30.

aspect_ratio'film_horizontal_21_9' | 'widescreen_16_9' | 'classic_4_3' | 'square_1_1' | 'traditional_3_4' | 'social_story_9_16' | 'film_vertical_9_21'

Output video aspect ratio. Only applies to text-to-video and reference-to-video; ignored when image (first frame) is provided (the output inherits the start frame ratio).

camera_fixedboolean

When true, the camera position stays fixed (tripod shot). When false, the model may apply natural camera movements.

camera_motion'static' | 'moveLeft' | 'moveRight' | 'moveUp' | 'moveDown' | 'pushIn' | 'pullOut' | 'zoomIn' | 'zoomOut' | 'panLeft' | 'panRight' | 'tiltUp' | 'tiltDown' | 'truckLeft' | 'truckRight' | 'pedestalUp' | 'pedestalDown' | 'superDollyIn' | 'superDollyOut' | 'crashZoomIn' | 'crashZoomOut' | 'doubleDolly' | 'jibUp' | 'jibDown' | 'craneUp' | 'craneDown' | 'craneOverTheHead' | 'orbitLeft' | 'orbitRight' | '360Orbit' | 'leftCircling' | 'rightCircling' | 'leftWalking' | 'rightWalking' | 'upwardTilt' | 'downwardTilt' | 'fisheye' | 'overhead' | 'objectPov' | 'whipPan' | 'dutchAngle' | 'dirtyLens' | 'lensCrack' | 'lensFlare' | 'focusChange' | 'lowShutter' | 'fpvDrone' | 'handheld' | 'headTracking' | 'snorricam' | 'stageLeft' | 'stageRight' | 'scenicShot' | 'carChasing' | 'throughObjectIn' | 'timelapseHuman' | 'timelapseLandscape'

Optional camera movement to guide the shot. Each value is expanded into a descriptive instruction appended to the prompt.

seedinteger

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

sound_effectsboolean

Whether to generate native audio (sound effects and ambience) for the video.

no_musicboolean

Suppress background music in the generated native audio. Only applies when sound_effects is enabled.

output_format'mp4' | 'mov'

Container format of the generated video. mov trades file size for colour fidelity; mp4 is the default.

enable_safety_checkerboolean

Enable content safety filtering to ensure generated videos comply with safety guidelines.

Example request

{
  "reference_videos": [
    "https://example.com/reference-1.mp4"
  ],
  "prompt": "A cinematic shot of a cat walking through a neon-lit alley at night"
}

Response

OK - The task exists and the status is returned

Example response

{
  "data": {
    "generated": [
      "https://openapi-generator.tech",
      "https://openapi-generator.tech"
    ],
    "task_id": "046b6c7f-0b8a-43b9-b35d-6489e6daee91",
    "status": "CREATED"
  }
}

Changes

No recorded changes to this operation across all 1 revision of this API.