seedream-5-0-lite-260128 API

Use the exact model ID seedream-5-0-lite-260128. The model field must match this page exactly.

Sample outputseedream-5-0-lite-260128POST /v1/images/generations

Parameters: size=2Kn=1

Prompt: Editorial fashion portrait of a woman in a sculptural crimson coat against a matching red studio backdrop, hard directional light, confident gaze, magazine cover quality, sharp detail, no text.

Request that produced this sample

{
  "model": "seedream-5-0-lite-260128",
  "prompt": "Editorial fashion portrait of a woman in a sculptural crimson coat against a matching red studio backdrop, hard directional light, confident gaze, magazine cover quality, sharp detail, no text.",
  "n": 1,
  "size": "2K"
}

Authentication and endpoint

Use a Modelflare API key with https://modelflare.dev/v1. The gateway entry point is POST /v1/images/generations.

HTTP

Authorization: Bearer YOUR_MODELFLARE_API_KEY

Generate an image

bash

curl https://modelflare.dev/v1/images/generations \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedream-5-0-lite-260128",
    "prompt": "A white cat runs through a neon-lit street in the rain",
    "size": "2K", "response_format": "url", "output_format": "png", "watermark": false
  }'

Request notes

Seedream Lite uses the Images API; single-image, reference-image, and coherent-group fields are forwarded according to the official page.

Request parameters

Seedream 5.0 Lite uses the Images API for single-image generation, reference-image editing, and coherent image groups. Group generation uses sequential_image_generation and sequential_image_generation_options.max_images; the service determines the actual output count.

Field	Required	Notes
model	Yes	seedream-5-0-lite-260128
prompt	Yes	Generation, editing, or layer-decomposition instruction
image	Conditional	URL, Base64, or up to 14 reference images
size	No	2K / 3K / 4K or a supported explicit pixel size
response_format	No	url / b64_json
output_format	No	png / jpeg
watermark	No	Whether to add a watermark
seed	No	Optional random seed
optimize_prompt_options.mode	No	standard
sequential_image_generation	No	auto enables image groups; disabled generates one image
sequential_image_generation_options.max_images	No	Maximum generated images in a coherent group
background	—	—
layer_decomposition	—	—

Response and input limits

Lite supports 2K/3K/4K and supported explicit pixel sizes. It accepts up to 14 references, each no larger than 30 MB, with a 1:16–16:1 aspect ratio, edges above 14 px, and at most 36,000,000 pixels. response_format: "url" links expire after 24 hours; the service determines the actual output count for coherent groups.

Documented workflow examples

Lite supports single-image generation, reference-image editing, and coherent image groups; the service determines the actual output count.

Coherent image group

bash

curl https://modelflare.dev/v1/images/generations \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedream-5-0-lite-260128",
    "prompt": "生成四张连贯的电影分镜：宇航员维修飞船、遭遇陨石雨、躲避撞击、最终安全返回",
    "size": "2K", "sequential_image_generation": "auto",
    "sequential_image_generation_options": {"max_images": 4},
    "output_format": "png", "watermark": false
  }'

Reference-image editing

bash

curl https://modelflare.dev/v1/images/generations \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedream-5-0-lite-260128",
    "prompt": "将图一人物的服装替换为图二的服装，保留人物身份、姿势和光线",
    "image": ["https://example.com/person.png", "https://example.com/outfit.png"],
    "size": "2K", "output_format": "png", "watermark": false
  }'

Errors and failed tasks

Invalid model parameters return a 4xx with a request ID; use the response fields and error message defined by the selected model contract.

Supported scope

This page covers Modelflare model generation and editing calls. Search or map enrichment, voice management, and element-library management are resource APIs outside this public model-call surface and are not required request fields.

Pricing and billing

This model uses per-image billing. See the model pricing page for the current customer price, reference list price, and complete specification.

Note

This page documents Modelflare’s public interface; the fields and limits shown here are the current contract.