Available now

Seedream 4: text to image

By ByteDance

ByteDance's Seedream 4 creates images from a written prompt and edits the images you upload, with automatic sizes up to 4K.

Model ID
Maker
ByteDance

Input

Fields marked * are required. Review the price before generating.

The text prompt used to generate the image

Example prompt. Edit it or write your own.

Total pixels must be between 960x960 and 4096x4096.

Number of separate model generations to be run with the prompt.

Additional settings

Random seed to control the stochasticity of image generation.

Estimated total$0.05

You sign up first. Your settings are kept.

About this model

Overview

Seedream 4 makes up to six images per run from a prompt. Choose a preset shape or let the model pick the size, including the Auto 2K and Auto 4K options.

Its edit mode takes up to 10 images and a written instruction, so you can change one picture or combine several into a new scene. A prompt enhancement setting trades time for quality: standard aims for higher quality, fast takes less time.

What you can build

  • Product and lifestyle images in several shapes
  • A series of variations from one prompt in a single run
  • Your photos with a new background, outfit or light
  • One scene built from several reference images

Prompting tips

  • Use the standard enhancement setting for final images and fast while you try out ideas.
  • When combining images, say which picture provides which part, for example the person from the first and the room from the second.
  • In edit mode, name what must stay unchanged, such as the face, the logo or the colors.

What to check

Check lettering, object count and source details that should survive an edit.

Inputs

  • Prompt (required): The text prompt used to generate the image.
  • Image Size (optional): The size of the generated image. Total pixels must be between 960x960 and 4096x4096. Options: 2048 × 2048, Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9, Auto, Auto 2K, Auto 4K.
  • Number of Images (optional): Number of separate model generations to be run with the prompt. From 1 to 6.
  • Seed (optional): Random seed to control the stochasticity of image generation.
  • Enhance Prompt Mode (optional): The mode to use for enhancing prompt enhancement. Standard mode provides higher quality results but takes longer to generate. Fast mode provides average quality results but takes less time to generate. Options: standard, fast.

Output and limits

  • Image sizes: 2048 × 2048, Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9, Auto, Auto 2K, Auto 4K.
  • Up to 6 images per run.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • 1 image: $0.05 / image