ByteDance Text to Video - ComfyUI Built-in Node Documentation

The ByteDance Text to Video node generates a video using ByteDance models through an API based on a text prompt.

The ByteDance Text to Video node generates a video using ByteDance models through an API based on a text prompt. You provide a prompt and choose settings such as the model, resolution, aspect ratio, and duration; the node submits the generation request and returns the generated video.

BytePlus shuts the Seedance 1.5 Pro model down on November 11, 2026, so this node no longer offers it and workflows saved with it stop working. Use seedance-1-0-pro-250528, seedance-1-0-pro-fast-251015, or the Seedance 2.5 partner node instead.

​

Inputs

Parameter	Description	Data Type	Required	Range
model	The ByteDance model used to generate the video (default: "seedance-1-0-pro-fast-251015").	COMBO	Yes	"seedance-1-0-pro-250528" "seedance-1-0-pro-fast-251015"
prompt	The text prompt used to generate the video.	STRING	Yes	-
resolution	The resolution of the output video.	COMBO	Yes	"480p" "720p" "1080p"
aspect_ratio	The aspect ratio of the output video.	COMBO	Yes	"16:9" "4:3" "1:1" "3:4" "9:16" "21:9"
duration	The duration of the output video in seconds (default: 5).	INT	Yes	3 to 12
seed	Seed to use for generation (default: 0).	INT	No	0 to 2147483647
camera_fixed	Specifies whether to fix the camera. The platform appends an instruction to fix the camera to your prompt, but does not guarantee the actual effect (default: False).	BOOLEAN	No	-
watermark	Whether to add an “AI generated” watermark to the video (default: False).	BOOLEAN	No	-
generate_audio	Accepted for compatibility; the remaining models ignore this input (default: False).	BOOLEAN	No	-

Parameter Constraints:

• The prompt parameter must contain at least 1 character after whitespace removal.
• The prompt parameter cannot contain the following text parameters: “resolution”, “ratio”, “duration”, “seed”, “camerafixed”, “watermark”.
• The node builds the final prompt by appending the selected resolution, aspect_ratio, duration, seed, camera_fixed, and watermark settings to the prompt text.
• The duration parameter is limited to values between 3 and 12 seconds.
• The seed parameter accepts values from 0 to 2,147,483,647.
• The generate_audio parameter is accepted for compatibility, but the remaining models ignore it.

​

Outputs

Output Name	Description	Data Type
output	The generated video file	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): 83b805b63e59a76cae378b0407b409e1bfe900677ef1e01fc836fede47283eee