Skip to main content
POST
/
api
/
v3
/
images
/
generations
seedream-4-5-251128 (text to image)
curl --request POST \
  --url https://api.example.com/api/v3/images/generations
BytePlus’s official format for the text to image API. 
curl -X POST "https://gptproto.com/api/v3/images/generations" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream-4-5-251128",
  "prompt": "Fisheye lens, a cat'\''s head, the picture shows the cat'\''s facial features are distorted due to the shooting method.",
  "response_format": "url",
  "size": "2k",
  "seed": 12,
  "guidance_scale": 2.5,
  "watermark": true
}'

{
  "error": {
    "message": "Invalid request parameters",
    "type": "invalid_request_error",
    "code": "invalid_parameters"
  }
}

​
Parameters

ParameterTypeRequiredDefaultDescription
modelstring✅ Yesseedream-4-5-251128The model identifier for image generation/editing
promptstring✅ Yes-Description of the desired image transformation or generation
response_formatstring❌ NourlResponse format: “url” (image URL) or “b64_json” (base64 encoded)
sizestring❌ NoadaptiveOutput image resolution. Options: adaptive, 1024x1024, 2K, 4K
seedinteger❌ No-Random seed for reproducible results
guidance_scalenumber❌ No5.5Controls adherence to the prompt. Range: 1.0-10.0, recommended: 3.0-7.0
watermarkboolean❌ NotrueWhether to add watermark to the generated image