infery
← All models

Seedance 2.5 Flash Reference to Video

bytedance/seedance-2.5/flash/reference-to-video

Video generationby ByteDance

Dreamina Seedance 2.5 Flash is the fast tier of Seedance 2.5. It generates, edits and extends video from up to 10 images, 5 videos and 5 audio references at 480p or 720p.

Details

Accepts
text + audio + image + video

Pricing

Input
1750 cr / 1M tokens

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seed—Random seed for reproducibility. Note that results may still vary slightly even with the same seed.
taskstringenum: auto, reference, editing, extensionThe type of video generation task. Reference uses the supplied media as guidance. Editing modifies a reference video and automatically coerces aspect_ratio and duration to auto. Extension continues a reference video and automatically coerces aspect_ratio to auto. Auto leaves the task type unset so t…
codecstringenum: auto, H264, H265'auto' uses the default video codec; US backend output is kept unchanged. 'H264' and 'H265' select H.264 and H.265 respectively.
prompt—The text prompt used to generate the video.
durationstringenum: auto, 4, 5, 6, 7, 8…Duration of the video in seconds. Supports 4 to 30 seconds, or auto to let the model decide based on the prompt.
audio_urlsarrayReference audio to guide video generation. Refer to them in the prompt as @Audio1, @Audio2, etc. Supported formats: MP3, WAV. Up to 5 files. Each file must be 1.8 to 30.2 seconds and no larger than 15 MB; combined duration must not exceed 30.2 seconds.
image_urlsarrayReference images to guide video generation. Refer to them in the prompt as @Image1, @Image2, etc. Supported formats: JPG, PNG, WebP, BMP, TIFF, GIF, HEIC, HEIF. Max 30 MB per image. Up to 10 images.
resolutionstringenum: 480p, 720pVideo resolution - 480p for faster generation, 720p for quality.
video_urlsarrayReference videos to guide video generation. Refer to them in the prompt as @Video1, @Video2, etc. Supported formats: MP4, MOV. Up to 5 videos. Each video must be 1.8 to 30.2 seconds and no larger than 200 MB; combined duration must not exceed 30.2 seconds. An extension with a single video accepts up…
end_user_id—The unique user ID of the end user.
aspect_ratiostringenum: auto, 21:9, 16:9, 4:3, 1:1, 3:4…The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide.
bitrate_modestringenum: standard, highOutput bitrate mode. 'high' requests a higher-quality, larger-file encode from the model; 'standard' uses the default bitrate.
output_formatstringenum: mp4, movOutput video format. 'mp4' is broadly compatible with browsers, mobile devices and media players. 'mov' targets professional post-production such as color grading, keying and compositing, but may not be supported by all players.
generate_audiobooleanWhether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not.

Output

FieldTypeDescription
seedintegerThe seed used for generation.
video—The generated video file.
draft_id—The draft ID, or null when draft mode is disabled. Complete this draft within 14 days using the same account.