Nodes/ComfyUI/ByteDance Seedream 4.5 & 5.0
ComfyUI Node Runs on cloud

ByteDance Seedream 4.5 & 5.0

Unified text-to-image generation and precise single-sentence editing at up to 4K resolution.

By Comfy-Org·Created 4 years ago·Updated 19 days ago· 121,575
ByteDance Seedream 4.5 & 5.0
  • image
  • IMAGE
model
prompt
size_preset
width2048
height2048
sequential_image_generation
max_images1
seed0
watermarkfalse
fail_on_partialtrue
Categorypartner/image/ByteDance

Inputs (11)

NameTypeDefaultDescription
modelCOMBO3 options: seedream 5.0 lite, seedream-4-5-251128, seedream-4-0-250828
promptSTRINGText prompt for creating or editing an image.
size_presetCOMBOPick a recommended size. Select Custom to use the width and height below.
imageoptIMAGEInput image(s) for image-to-image generation. Reference image(s) for single or multi-reference generation.
widthoptINT20481024–6240Custom width for image. Value is working only if `size_preset` is set to `Custom`
heightoptINT20481024–4992Custom height for image. Value is working only if `size_preset` is set to `Custom`
sequential_image_generationoptCOMBOGroup 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_imagesoptINT11–15Maximum number of images to generate when sequential_image_generation='auto'. Total images (input + generated) cannot exceed 15.
seedoptINT00–2147483647Seed to use for generation.
watermarkoptBOOLEANfalseWhether to add an "AI generated" watermark to the image.
fail_on_partialoptBOOLEANtrueIf enabled, abort execution if any requested images are missing or return an error.

Outputs (1)

NameTypeDescription
IMAGEIMAGE