ByteDanceSeedreamNode - ComfyUI Built-in Node Documentation

The ByteDance Seedream 4.5 & 5.0 node provides unified text-to-image generation and precise single-sentence editing capabilities at up to 4K resolution. It can create new images from text prompts or edit existing images using text instructions. The node supports both single image generation and sequential generation of multiple related images.

Inputs

Parameter	Description	Data Type	Required	Range
`model`	The Seedream model to use for generation.	STRING	Yes	”seedream 5.0 lite" "seedream-4-5-251128" "seedream-4-0-250828”
`prompt`	Text prompt for creating or editing an image. Must be at least 1 character long.	STRING	Yes	-
`image`	Input image(s) for image-to-image generation. Reference image(s) for single or multi-reference generation. Maximum of 14 reference images for seedream-5-0-260128, or 10 for other models.	IMAGE	No	-
`size_preset`	Pick a recommended size. Select Custom to use the width and height below.	STRING	No	Multiple options available
`width`	Custom width for image. Value is working only if `size_preset` is set to `Custom`. Default: 2048.	INT	No	1024 to 6240 (step 2)
`height`	Custom height for image. Value is working only if `size_preset` is set to `Custom`. Default: 2048.	INT	No	1024 to 4992 (step 2)
`sequential_image_generation`	Group image generation mode. “disabled” generates a single image. “auto” lets the model decide whether to generate multiple related images (e.g., story scenes, character variations). Default: “disabled”.	STRING	No	”disabled" "auto”
`max_images`	Maximum number of images to generate when sequential_image_generation=‘auto’. Total images (input + generated) cannot exceed 15. Default: 1.	INT	No	1 to 15 (step 1)
`seed`	Seed to use for generation. Default: 0.	INT	No	0 to 2147483647 (step 1)
`watermark`	Whether to add an “AI generated” watermark to the image. Default: False.	BOOLEAN	No	-
`fail_on_partial`	If enabled, abort execution if any requested images are missing or return an error. Default: True.	BOOLEAN	No	-

Notes on parameter constraints:

The minimum image resolution depends on the selected model: 3.68MP for seedream-4-5 and seedream-5-0 models, 0.92MP for seedream-4-0 models.
The maximum image resolution is 10.4MP for seedream-5-0 models and 16.78MP for other models.
Reference images must have an aspect ratio between 1:3 and 3:1.
When sequential_image_generation is set to “auto”, the total number of input images plus max_images cannot exceed 15.
The width and height parameters are only used when size_preset is set to “Custom”.

Outputs

Output Name	Description	Data Type
`IMAGE`	Generated image(s) based on the input parameters and prompt. Returns a single image tensor or a batch of image tensors if multiple images are generated.	IMAGE

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): 942c75386abd5f2f352b584b51b0f9adbf2ccba2829ee8072173bdc1a407543f

​Inputs

​Outputs

Inputs

Outputs