Przejdź do głównej treści

​
Endpointy

MetodaEndpointOpis
POST/api/v1/generateTask/seedance-1-5-proUtwórz zadanie generowania
GET/api/v1/statusTask/seedance-1-5-proSprawdź status zadania

​
Uwierzytelnianie

Wszystkie żądania wymagają klucza API w nagłówku: 
Authorization: Bearer YOUR_API_KEY

​
Treść żądania

{
  "request_type": "async",
  "callback_url": "https://...",
  "provider": "auto",
  "input": {
    "mode": "text-to-video",
    "prompt": "...",
    "resolution": "720p",
    "duration": 8,
    "sound": true,
    "aspect_ratio": "16:9",
    "fixed_lens": false,
    "image_urls": ["..."]
  }
}

​
Parametry

​
request_type
string
domyślnie:"async"
async (polling) or callback (webhook)
​
callback_url
string
Callback URL, required when request_type=callback (conditional)
​
provider
string
domyślnie:"auto"
Routing strategy: auto, value, or official
​
input
object
wymagane
Model input parameters
Mode Options:
  • text-to-video — Generate video from text
  • image-to-video — Generate video from image (supports 1-2 images for end frame control)

​
Przykład

Text-to-Video 
curl -X POST "https://api.apixo.ai/api/v1/generateTask/seedance-1-5-pro" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "provider": "value",
    "input": {
      "mode": "text-to-video",
      "prompt": "a calm seaside sunrise with gentle camera dolly movement",
      "resolution": "720p",
      "duration": 8,
      "sound": true,
      "aspect_ratio": "16:9",
      "fixed_lens": false
    }
  }'
Image-to-Video (with End Frame Control) 
curl -X POST "https://api.apixo.ai/api/v1/generateTask/seedance-1-5-pro" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "callback",
    "callback_url": "https://your-server.com/callback",
    "provider": "official",
    "input": {
      "mode": "image-to-video",
      "prompt": "animate this landscape with moving clouds and wind",
      "resolution": "480p",
      "duration": 4,
      "sound": false,
      "image_urls": [
        "https://example.com/head.jpg",
        "https://example.com/tail.jpg"
      ],
      "aspect_ratio": "1:1"
    }
  }'

​
Odpowiedź

​
POST /api/v1/generateTask/seedance-1-5-pro

Returns taskId on success for subsequent status queries. Success: 
{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678"
  }
}
Error: 
{
  "code": 400,
  "message": "Insufficient credits",
  "data": null
}

​
GET /api/v1/statusTask/seedance-1-5-pro

Query task execution status and results via taskId. 
curl -X GET "https://api.apixo.ai/api/v1/statusTask/seedance-1-5-pro?taskId=task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"
Success: 
{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://r2.apixo.ai/video.mp4\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965652317,
    "costTime": 41388
  }
}
Failed: 
{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "CONTENT_VIOLATION",
    "failMsg": "Content does not meet safety guidelines"
  }
}

​
Pola odpowiedzi statusu

​
taskId
string
Unique task identifier.
​
state
string
Current task state: pending, processing, success, or failed.
​
resultJson
string
JSON string containing resultUrls array. Only present on success. Parse with JSON.parse().
​
failCode
string
Error code. Only present when state is failed. See Kody błędów.
​
failMsg
string
Human-readable error message. Only present when state is failed.
​
createTime
integer
Task creation timestamp (Unix milliseconds).
​
completeTime
integer
Task completion timestamp (Unix milliseconds).
​
costTime
integer
Processing duration in milliseconds.

​
Kody błędów

CodeDescription
400Invalid parameters or request error
401Invalid or missing API Key
429Rate limit exceeded
Fail CodeDescription
CONTENT_VIOLATIONContent violates safety guidelines
INVALID_IMAGE_URLCannot access provided image URL

​
Limity rate

LimitValue
Requests10000 / minute
Concurrent tasks1000
Exceeding limits returns 429 error. Wait and retry.

​
Wskazówki

  • Generation time:
    • 4-second video: ~40-60 seconds
    • 8-second video: ~60-90 seconds
    • 12-second video: ~90-120 seconds
    • Submit task, wait 50 seconds, then poll every 5 seconds
  • Callback mode: Video generation takes time, strongly recommend using callback mode.
  • Video expiration: Result URLs are valid for 15 days. Download promptly.
  • Content moderation: Prompts must comply with content safety guidelines.
  • Audio generation: Seedance 1.5 Pro supports audio generation:
    • sound: true: Auto-generates matching ambient sounds and background music
    • sound: false: Generates silent video
    • Describe sound effects in prompt for better audio (e.g., “ocean waves”, “bird sounds”)
  • End frame control: image-to-video mode supports 2 images:
    • 1st image: Video start frame
    • 2nd image: Video end frame
    • Enables precise start/end control, ideal for transitions and scene changes
  • Fixed lens:
    • fixed_lens: true: Camera stays still, ideal for product showcases, close-ups
    • fixed_lens: false: Allows dynamic camera movement (dolly, pan, etc.)
  • Resolution selection:
    • 480p: Fast generation, for previews and social media
    • 720p: High quality, for most publishing scenarios
  • Duration: Supports 4/8/12 second options, billed per second.
  • Aspect ratio suggestions:
    • 1:1: Square, for social media (default)
    • 16:9: Landscape, for traditional video platforms
    • 9:16: Portrait, for short video platforms
    • 21:9: Ultra-wide, for cinematic feel
  • Prompt tips:
    • Describe both visual and audio effects for better synchronization
    • Specify camera movement (e.g., “slow dolly in”, “orbiting shot”)
    • Describe dynamic elements (e.g., “drifting clouds”, “swaying leaves”)
  • Image formats: image_urls supports JPG, PNG, WebP, max 10MB per image.
Video generation takes longer than images — use callback mode for production workloads. Result URLs expire after 15 days; download important outputs promptly.

​
Powiązane