Available now

Seedream 5 Pro: image editing

By ByteDance

ByteDance's Seedream 5 Pro creates square images from a written brief and edits or combines up to 10 images you upload.

Model ID
Maker
ByteDance

Input

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

The text prompt used to edit the image.

Example prompt. Edit it or write your own.

Total pixels must be between 921600 and 4624220, with aspect ratio between 1/16 and 16.

Number of separate model generations to run with the prompt.

Input reference images. Up to 10 images are supported; if more are sent, only the last 10 are used.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB · 0/10

Additional settings

The file format of the generated image.

Prompt optimization mode. standard prioritizes image quality; fast reduces generation time.

Price$0.32 / run

You sign up first. Your settings are kept.

About this model

Overview

Seedream 5 Pro renders square images at 1024, 1536 or 2048 pixels per side from a text prompt. Your prompt is optimized first: the standard setting favors image quality and the fast setting shortens the wait.

Its edit mode accepts up to 10 reference images and returns up to six results per run, in preset shapes or a size worked out from your images.

What you can build

  • Product and editorial images from a written brief
  • Square visuals for shop listings and social feeds
  • A product from one photo placed into the setting of another
  • Several takes of one edit to choose from

Prompting tips

  • Describe the subject, camera angle, light and background in that order.
  • Explore with the fast optimization setting, then switch to standard for the final image.
  • In the edit mode, say which image supplies what, for example the product from the first and the room from the second.

What to check

Compare the generated image with your brief. Inspect the rim, handle and shadows at full size. Keep the prompt and settings with your selected output so you can repeat the experiment.

Inputs

  • Prompt (required): The text prompt used to edit the image.
  • Image Size (optional): The size of the generated image. Total pixels must be between 921600 and 4624220, with aspect ratio between 1/16 and 16. Options: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9, Auto 1K, Auto 1.5K, Auto 2K.
  • Number of Images (optional): Number of separate model generations to run with the prompt. From 1 to 6.
  • Output Format (optional): The file format of the generated image. Options: jpeg, png.
  • Enhance Prompt Mode (optional): Prompt optimization mode. `standard` prioritizes image quality; `fast` reduces generation time. Options: standard, fast.
  • Images (required): List of URLs of input reference images. Up to 10 images are supported; if more are sent, only the last 10 are used.

Output and limits

  • Image sizes: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9, Auto 1K, Auto 1.5K, Auto 2K.
  • File formats: JPEG, PNG.
  • 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

  • up to, default options: $0.32 / run