Seedream V4

Seedream V4 generates images from text or edits an input image using your prompt.

Try Seedream V4 in the playground

Last updated View as MarkdownAgent setup

Seedream V4

Node type: generate:bytedance_seedream_v4_text_to_image
Category: edit

Description

Seedream V4 generates images from text or edits an input image using your prompt: connect your text to the Prompt port, which is required, connect an image to the Image 1 port if you have one, and the results come out of Generated Images. In the config panel you pick an Image Size from options such as match_input_image, square_hd and portrait_4_3, choose standard or fast for Enhance Prompt Mode, and set Num Images and Max Images, each from 1 to 6. It costs about 10 credits per image. The node's family also includes an edit variant, edit:bytedance_seedream_v4_edit.

Pricing

  • Cost: ~10 credits per image

Variant family

  • Family: bytedance_seedream_v4
  • Is primary: yes
  • All variants: edit:bytedance_seedream_v4_edit, generate:bytedance_seedream_v4_text_to_image

Canvas ports

These appear as port handles on the left side of the node.

ID Label Details
prompt Prompt TEXT (required)
image1 Image 1 IMAGE

These render as form fields in the right-side config panel when the node is selected.

ID Label Details
enable_safety_checker Enable Safety Checker BOOLEAN
enhance_prompt_mode Enhance Prompt Mode TEXT · options: standard, fast
image_size Image Size IMAGE_SIZE · options: match_input_image, custom, square_hd, square, portrait_4_3, +6
max_images Max Images NUMBER · 1…6
num_images Num Images NUMBER · 1…6
seed Seed NUMBER
sync_mode Sync Mode BOOLEAN

Outputs

ID Label Type
images Generated Images IMAGE

Auto-generated from the Wireflow node registry.

For AI agents: the full documentation index is at /llms.txt, and most docs pages are available as Markdown by adding .md to the URL.

© 2026 Wireflow. All rights reserved.