ByteDance2FirstLastFrameNode - ComfyUI Built-in Node Documentation

This node generates a video from a required first frame image and an optional last frame image using ByteDance Seedance models.

This node generates a video from a required first frame image and an optional last frame image using ByteDance Seedance models. You describe the video with a text prompt; the first frame guides the start of the video and the last frame guides the end. It supports Seedance 2.5 and the Seedance 2.0 family (Seedance 2.0, Seedance 2.0 Fast, and Seedance 2.0 Mini).

Inputs

Common Inputs

Parameter	Description	Data Type	Required	Range
model	Seedance 2.5 for the newest model, videos up to 30 seconds and mp4/mov output; Seedance 2.0 for maximum quality and 4k; Fast for speed optimization; Mini for the fastest, lowest-cost generation. Selecting a model reveals model-specific inputs below.	DYNAMIC_COMBO	Yes	"Seedance 2.5" "Seedance 2.0" "Seedance 2.0 Fast" "Seedance 2.0 Mini"
first_frame	First frame image for the video.	IMAGE	No	-
last_frame	Last frame image for the video.	IMAGE	No	-
first_frame_asset_id	Seedance asset_id to use as the first frame. Mutually exclusive with the first_frame image input. Default is an empty string.	STRING	No	-
last_frame_asset_id	Seedance asset_id to use as the last frame. Mutually exclusive with the last_frame image input. Default is an empty string.	STRING	No	-
seed	Seed controls whether the node should re-run; results are non-deterministic regardless of seed. Default is 0.	INT	Yes	0 to 2147483647
watermark	Whether to add a watermark to the video. Default is False.	BOOLEAN	Yes	False True

Seedance 2.5 Inputs

These inputs appear when Seedance 2.5 is selected.

Parameter	Description	Data Type	Required	Range
prompt	Text prompt for video generation. Put spoken lines in double quotes to steer the generated dialogue.	STRING	Yes	-
resolution	Resolution of the output video. Default is 720p.	COMBO	Yes	"480p" "720p" "1080p"
duration	Duration of the output video in seconds (4-30). Default is 5.	INT	Yes	4 to 30
generate_audio	Enable audio generation for the output video. Default is True.	BOOLEAN	Yes	False True
output_format	Container format of the output video. Default is mp4.	COMBO	Yes	"mp4"

Seedance 2.0 Inputs

These inputs appear when Seedance 2.0 is selected.

Parameter	Description	Data Type	Required	Range
prompt	Text prompt for video generation.	STRING	Yes	-
resolution	Resolution of the output video.	COMBO	Yes	"480p" "720p" "1080p" "4k"
ratio	Aspect ratio of the output video. Default is adaptive, which uses the nearest supported ratio to the input frame’s aspect ratio.	COMBO	Yes	"16:9" "4:3" "1:1" "3:4" "9:16" "21:9" "adaptive"
duration	Duration of the output video in seconds (4-15). Default is 7.	INT	Yes	4 to 15
generate_audio	Enable audio generation for the output video. Default is True.	BOOLEAN	Yes	False True

Seedance 2.0 Fast and Seedance 2.0 Mini Inputs

Shared by Seedance 2.0 Fast and Seedance 2.0 Mini.

Parameter	Description	Data Type	Required	Range
prompt	Text prompt for video generation.	STRING	Yes	-
resolution	Resolution of the output video.	COMBO	Yes	"480p" "720p"
ratio	Aspect ratio of the output video. Default is adaptive, which uses the nearest supported ratio to the input frame’s aspect ratio.	COMBO	Yes	"16:9" "4:3" "1:1" "3:4" "9:16" "21:9" "adaptive"
duration	Duration of the output video in seconds (4-15). Default is 7.	INT	Yes	4 to 15
generate_audio	Enable audio generation for the output video. Default is True.	BOOLEAN	Yes	False True

Parameter Constraints

• You must provide the first frame either as a first_frame image or as a first_frame_asset_id. Providing both raises an error; providing neither also raises an error.
• The last_frame and last_frame_asset_id inputs are optional, but you cannot provide both for the same frame.
• Asset IDs must reference existing, active Seedance Image assets.
• The prompt input is required and cannot be empty.
• With Seedance 2.5, the output aspect ratio is always adaptive and follows the first frame’s own aspect ratio, so no ratio input is shown.
• With Seedance 2.0 family models and local frame images, the images are center-cropped and resized to the target output resolution and ratio before generation. When ratio is adaptive, the nearest supported ratio to the input image is used.
• Local frame images are validated for supported aspect ratio and dimensions; oversized images are downscaled.

Outputs

Output Name	Description	Data Type
output	The 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): bc2eb5f43c935986ad870703cfbc92dd99a53d6f0ac91cf0cad46bee33ff2cc0