Skip to main content
This node uses ByteDance’s Seedance 2.0 model to generate a video from a required first frame image and an optional last frame image. It creates the video based on a text prompt and the provided frames, with the first frame guiding the start and the last frame guiding the end of the video sequence.

​
Inputs

ParameterDescriptionData TypeRequiredRange
modelThe model to use for video generation. Seedance 2.0 is for maximum quality, while Seedance 2.0 Fast is optimized for speed. Selecting a model will reveal additional inputs for prompt, resolution, ratio, duration, and generate_audio.COMBOYes"Seedance 2.0"
"Seedance 2.0 Fast"
first_frameThe image to use as the first frame of the video.IMAGENo-
last_frameThe image to use as the last frame of the video.IMAGENo-
first_frame_asset_idA Seedance asset_id to use as the first frame. This cannot be used at the same time as the first_frame image input. Default is an empty string.STRINGNo-
last_frame_asset_idA Seedance asset_id to use as the last frame. This cannot be used at the same time as the last_frame image input. Default is an empty string.STRINGNo-
seedA seed value. Changing this seed will cause the node to re-run, but the results are non-deterministic regardless of seed value. Default is 0.INTNo0 to 2147483647
watermarkWhether to add a watermark to the generated video. Default is False.BOOLEANNo-
Parameter Constraints:
  • You must provide either a first_frame image or a first_frame_asset_id. Providing both will cause an error.
  • You must provide at least one of first_frame or first_frame_asset_id — at least one is required.
  • You cannot provide both a last_frame image and a last_frame_asset_id for the same frame.
  • The model input is a dynamic combo. After selecting a model, you must also fill in the revealed prompt field (a text description) and configure the other revealed parameters (resolution, ratio, duration, generate_audio).
  • When using local image inputs (not asset IDs), the images must have an aspect ratio between 0.4 and 2.5, and minimum dimensions of 300x300 pixels.

​
Outputs

Output NameDescriptionData Type
outputThe generated video.VIDEO
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
Source fingerprint (SHA-256): 74953cfc8f474a1b5ba7e4765682fd86693e43df87ba59e6d3e615e51293ab07