Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.comfy.org/llms.txt

Use this file to discover all available pages before exploring further.

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 Image node generates images using ByteDance models through an API based on text prompts. It allows you to select a model, specify image dimensions, and control various generation parameters like seed and guidance scale. The node connects to ByteDance’s image generation service and returns the created image.

Inputs

ParameterData TypeRequiredRangeDescription
modelSTRINGYes"seedream-3-0-t2i-250415"The ByteDance model to use for image generation. Currently only one model option is available.
promptSTRINGYes-The text prompt used to generate the image. Must be at least 1 character long after stripping whitespace.
size_presetSTRINGYesSee descriptionPick a recommended size. Select Custom to use the width and height below. Available presets are defined by the RECOMMENDED_PRESETS list.
widthINTYes512 to 2048 (step 64)Custom width for the image. This value is only used when size_preset is set to Custom. Default: 1024.
heightINTYes512 to 2048 (step 64)Custom height for the image. This value is only used when size_preset is set to Custom. Default: 1024.
seedINTNo0 to 2147483647 (step 1)Seed to use for generation. Default: 0.
guidance_scaleFLOATNo1.0 to 10.0 (step 0.01)Higher value makes the image follow the prompt more closely. Default: 2.5.
watermarkBOOLEANNoTrue / FalseWhether to add an “AI generated” watermark to the image. Default: False. This is an advanced parameter.
Note on size parameters: The width and height parameters are only used when size_preset is set to Custom. If a preset size is selected, the preset’s dimensions override the custom width and height values. Both width and height must be between 512 and 2048 pixels when using custom dimensions.

Outputs

Output NameData TypeDescription
IMAGEIMAGEThe generated image returned from the ByteDance API as a tensor.

Source fingerprint (SHA-256): 69c1f6fd24e6e184b1a1d785b541c8962f3751d2bbd121d6a3b105d66d58d4b1