Skip to main content
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The ByteDance Seedream 4 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

ParameterData TypeInput TypeDefaultRangeDescription
modelMODELCOMBO”seedream-4-0-250828”[“seedream-4-0-250828”]Model name
promptSTRINGSTRING""-Text prompt for creating or editing an image.
imageIMAGEIMAGE--Input image(s) for image-to-image generation. List of 1-10 images for single or multi-reference generation.
size_presetSTRINGCOMBOFirst preset from RECOMMENDED_PRESETS_SEEDREAM_4All labels from RECOMMENDED_PRESETS_SEEDREAM_4Pick a recommended size. Select Custom to use the width and height below.
widthINTINT20481024-4096 (step 64)Custom width for image. Value is working only if size_preset is set to Custom
heightINTINT20481024-4096 (step 64)Custom height for image. Value is working only if size_preset is set to Custom
sequential_image_generationSTRINGCOMBO”disabled”[“disabled”, “auto”]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).
max_imagesINTINT11-15Maximum number of images to generate when sequential_image_generation=‘auto’. Total images (input + generated) cannot exceed 15.
seedINTINT00-2147483647Seed to use for generation.
watermarkBOOLEANBOOLEANTrue-Whether to add an “AI generated” watermark to the image.
fail_on_partialBOOLEANBOOLEANTrue-If enabled, abort execution if any requested images are missing or return an error.

Outputs

Output NameData TypeDescription
IMAGEIMAGEGenerated image(s) based on the input parameters and prompt