Seedance 2.0 Pro 4K - Create video from text or image
Generate 4K video using Seedance 2.0 Pro. Supports text-to-video and image-to-video with optional first and last frame images for transition videos. Also supports reference-to-video: attach up to 9 reference images via reference_images and mention them in the prompt with @Image1..@Image9.
Authorizations
Your Magnific API key. Required for authentication. Learn how to obtain an API key
Body
Text prompt describing the video to generate. Mention references as @Image1, @Image2, ... or @Video1, @Video2, ... matching their 1-indexed array order. Maximum 2000 characters.
2000"A cinematic shot of a cat walking through a neon-lit alley at night"
URL to receive a webhook notification when the video generation task completes. The webhook payload includes the task ID and status.
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.
Optional image to use as the last frame for image-to-video generation. When provided together with image, the model generates a transition video between the first frame and last frame. Accepts a publicly accessible URL or a base64-encoded image.
Up to 9 reference images for reference-to-video generation. Each item is a publicly accessible URL or a base64-encoded image. Reference them in the prompt using @Image1, @Image2, ... @Image9 (1-indexed to the array order). Mutually exclusive with image and image_end.
9Up to 3 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, or @Video3. Each video must be MP4 or MOV, 2 to 15 seconds, 24 to 60 fps, no larger than 50 MB, with 409600 to 2086876 pixels and an aspect ratio from 0.4 to 2.5. Combined duration must not exceed 15 seconds. Mutually exclusive with image and image_end.
3Video duration in seconds. Any integer from 4 to 15.
4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 Output video aspect ratio. Available options:
film_horizontal_21_9: Ultra-wide cinematic (21:9)widescreen_16_9: Standard widescreen (16:9)classic_4_3: Classic TV format (4:3)square_1_1: Square format (1:1)traditional_3_4: Portrait classic (3:4)social_story_9_16: Vertical/social media story (9:16)film_vertical_9_21: Ultra-tall vertical (9:21)
Note: This parameter only applies to text-to-video and reference-to-video requests. When an image (first frame) is provided for image-to-video generation, aspect_ratio is ignored: the output video inherits the aspect ratio of the start frame.
film_horizontal_21_9, widescreen_16_9, classic_4_3, square_1_1, traditional_3_4, social_story_9_16, film_vertical_9_21 When set to true, the camera position stays fixed (tripod shot) throughout the video. When false, the model may apply natural camera movements.
Random seed for reproducible video generation. Use the same seed with the same prompt to get consistent results. Use -1 for a random seed.
-1 <= x <= 4294967295Whether to generate native audio (sound effects and ambience) for the video. Set to false to generate a silent video.
Suppress background music in the generated native audio. Only applies when sound_effects is enabled.
Enable content safety filtering to ensure generated videos comply with safety guidelines. When true, the model filters unsafe content.
Response
OK - The task exists and the status is returned