Seedream 5.0 Lite

Seedream 5.0 Lite is ByteDance’s image generation and editing model for single images, multi-image references, and coherent image sets. Use model ID seedream-5-0-lite-260128.

For specific content requests, select the Special-Ns resource group.

Key capabilities

Text to image — Generate single images or coherent image sets from natural-language prompts
Image to image — Add, remove, replace, or restyle content while preserving requested source details
Multi-image reference — Combine subjects, products, styles, or layouts from multiple references
Visual-instruction editing — Use arrows, boxes, masks, and doodles to identify the edit region
Coherent image sets — Create storyboards, comics, and branded image sets
Knowledge-rich visuals — Create diagrams, formulas, educational images, and information graphics

Text to image
Image to image

Single image

cURL

curl https://www.anyfast.ai/v1/images/generations \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedream-5-0-lite-260128",
    "prompt": "A clean editorial poster explaining the water cycle, accurate labels and clear hierarchy",
    "size": "2K",
    "response_format": "url",
    "output_format": "png",
    "watermark": false
  }'

Coherent image set

cURL

curl https://www.anyfast.ai/v1/images/generations \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedream-5-0-lite-260128",
    "prompt": "Generate four coherent cinematic storyboard frames of an astronaut repairing a spacecraft",
    "size": "2K",
    "sequential_image_generation": "auto",
    "sequential_image_generation_options": { "max_images": 4 },
    "output_format": "png",
    "watermark": false
  }'

Parameter	Type	Required	Description
`model`	string	Yes	Must be `seedream-5-0-lite-260128`
`prompt`	string	Yes	Image generation prompt
`size`	string	No	`2K`, `3K`, `4K`, or supported explicit pixels
`seed`	integer	No	Random seed
`sequential_image_generation`	string	No	`auto` for an image set; `disabled` for one image
`sequential_image_generation_options.max_images`	integer	No	Maximum generated images
`response_format`	string	No	`url` or `b64_json`
`output_format`	string	No	`png` or `jpeg`
`watermark`	boolean	No	Whether to add an AI-generated watermark
`optimize_prompt_options.mode`	string	No	Prompt optimization mode. Use `standard`.

cURL

curl https://www.anyfast.ai/v1/images/generations \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedream-5-0-lite-260128",
    "prompt": "Replace the clothing in image 1 with the outfit from image 2 while preserving identity and lighting",
    "image": [
      "https://example.com/person.png",
      "https://example.com/outfit.png"
    ],
    "size": "2K",
    "output_format": "png",
    "watermark": false
  }'

Coherent image set from references

{
  "model": "seedream-5-0-lite-260128",
  "prompt": "Create four coherent cinematic storyboard frames using the reference character",
  "image": ["https://example.com/character.png"],
  "size": "2K",
  "sequential_image_generation": "auto",
  "sequential_image_generation_options": {
    "max_images": 4
  },
  "response_format": "url",
  "output_format": "png",
  "watermark": false
}

Parameter	Type	Required	Description
`model`	string	Yes	Must be `seedream-5-0-lite-260128`
`prompt`	string	Yes	Image editing or reference-generation instruction
`image`	string or array	Yes	URL, Base64 data URI, or up to 14 references
`size`	string	No	`2K`, `3K`, `4K`, or supported explicit pixels
`seed`	integer	No	Random seed
`sequential_image_generation`	string	No	`auto` or `disabled`
`sequential_image_generation_options.max_images`	integer	No	Maximum images to return; references plus generated images must not exceed 15.
`response_format`	string	No	`url` or `b64_json`
`output_format`	string	No	`png` or `jpeg`
`watermark`	boolean	No	Whether to add an AI-generated watermark
`optimize_prompt_options.mode`	string	No	Prompt optimization mode. Use `standard`.

Input limits

Supported formats are jpeg, png, webp, bmp, tiff, gif, heic, and heif. Each image must be no larger than 30 MB, have an aspect ratio in [1/16, 16], have width and height greater than 14 px, and contain no more than 36,000,000 pixels. Up to 14 references are supported, and the number of references plus generated images must not exceed 15.

URLs returned with response_format: "url" expire after 24 hours.

API Reference

View both Seedream 5.0 Lite workflows.

Getting started

Model Introduction

Resources

Seedream 5.0 Lite

Key capabilities

Single image

Coherent image set

Coherent image set from references

Input limits

API Reference

​Key capabilities

​Single image

​Coherent image set

​Coherent image set from references

​Input limits

API Reference

Key capabilities

Single image

Coherent image set

Coherent image set from references

Input limits