Doubao Seedream 5.5 API

# Text-to-image — create returns a taskId, then poll for the result.
curl -X POST https://api.apimodels.app/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-5-5",
    "prompt": "product photo of a matte white ceramic mug on a light oak table by a window, soft morning light",
    "resolution": "1.5K",
    "aspect_ratio": "16:9"
  }'
# → { "code": 200, "data": { "taskId": "...", "state": "pending", "model": "doubao-seedream-5-5" } }

curl "https://api.apimodels.app/v1/images/generations?task_id=TASK_ID" \
  -H "Authorization: Bearer YOUR_API_KEY"
# → { "code": 200, "data": { "state": "completed", "resultUrls": ["https://r2.apimodels.app/..."] } }

# Edit / compose — 1 to 10 reference images (+$0.01 each).
curl -X POST https://api.apimodels.app/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-5-5",
    "prompt": "put the vase from image 2 on the table in image 1; keep the room, furniture and lighting unchanged",
    "images": ["https://example.com/dining-room.jpg", "https://example.com/vase.png"],
    "resolution": "2K"
  }'

# Transparent background — PNG with a real alpha channel.
curl -X POST https://api.apimodels.app/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-5-5",
    "prompt": "a snowy owl with spread wings, isolated, detailed feathers",
    "background": "transparent",
    "resolution": "1K"
  }'

# Layer splitting — exactly one image in, a base plus transparent layers out.
curl -X POST https://api.apimodels.app/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-5-5",
    "image": "https://example.com/poster.png",
    "layer_decomposition": true,
    "max_images": 10,
    "text_recognition": true
  }'
# Completed task:
# { "state": "completed",
#   "resultUrls": ["https://r2.apimodels.app/...base.png", "https://r2.apimodels.app/...layer1.png", ...],
#   "layers": [
#     { "index": 0, "role": "base", "size": "2048x2048", "z_index": 0, "background": "opaque" },
#     { "index": 1, "role": "layer", "size": "800x160", "z_index": 1, "background": "transparent",
#       "bounding_box": { "absolute": [120, 80, 920, 240] },
#       "text_recognition": { "text": "Summer Sale", ... } } ] }