Video¶

Seedance 2.0¶

Create Video Generation Task¶

Submit a video generation task. Supports text-to-video and image-to-video.

curl -X POST "https://www.chnllm.com/v1/video/generations" \
  -H "Authorization: Bearer $WS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedance-2-0-260128",
    "prompt": "First-person POV throughout, using the composition of video 1 and audio 1 as background music. A first-person fruit-tea promo for AVG \"WSAI\" Apple Fruit Tea limited edition; first frame is image 1, your hand picks a dew-covered Aksu red apple with a crisp snap; 2-4s: quick cut, your hand drops apple chunks into a shaker with ice and tea base, shakes vigorously, ice and shaking sounds sync to upbeat drums, voiceover: \"Freshly cut, freshly shaken\"; 4-6s: first-person close-up of the finished product, layered fruit tea poured into a clear cup, your hand spreads cream cap on top, applies a pink label, camera moves in on the layered texture; 6-8s: first-person hold-up, you raise the fruit tea from image 2 to the camera (as if handing it to the viewer), label clearly visible, voiceover: \"Take a fresh sip\", final frame freezes on image 2. All background voice unified as female timbre.",
    "images": [
      "https://ark-project.tos-cn-beijing.volces.com/doc_image/r2v_tea_pic1.jpg",
      "https://ark-project.tos-cn-beijing.volces.com/doc_image/r2v_tea_pic2.jpg"
    ],
    "videos" :["https://ark-project.tos-cn-beijing.volces.com/doc_video/r2v_tea_video1.mp4"],

    "audios": [
      "https://ark-project.tos-cn-beijing.volces.com/doc_audio/r2v_tea_audio1.mp3"
    ],
    "metadata": {
      "generate_audio": true,
      "resolution" : "480p",
      "ratio": "4:3",
      "duration": 5,
      "watermark": false
    }
  }'

Returns a task ID. Use the GET endpoint to query task status.

{"task_id":"task_id"}

Get Video Generation Task Status¶

Query the status and result of a video generation task.

curl https://www.chnllm.com/v1/video/generations/task_id \
  -H "Authorization: Bearer $WS_API_KEY"

Task status:

href="index.html#__codelineno-3-1">{ "code": "success", "message": "", "data": { "task_id": "task_id", "action": "generate", "status": "SUCCESS", "fail_reason": "", "submit_time": 1775188030, "start_time": 1775188043, "finish_time": 1775188329, "progress": "100%", "data": { "id": "task_id", "draft": false, "model": "volcengine/doubao-seedance-2-0-260128", "ratio": "4:3", "frames": 0, "result": { "id": "cgt-20260403114650-qgcb2", "seed": 40141, "draft": false, "model": "doubao-seedance-2-0-260128", "ratio": "4:3", "usage": { "total_tokens": 99111, "completion_tokens": 99111 }, "status": "succeeded", "content": { "video_url": "video download URL" }, "duration": 5, "created_at": 1775188030, "resolution": "480p", "updated_at": 1775188324, "service_tier": "default", "generate_audio": true, "framespersecond": 24, "execution_expires_after": 172800 }, "status": "succeed", "duration": 5, "created_at": "2026-04-03T03:47:10Z", "resolution": "480p", "updated_at": "2026-04-03T03:52:04Z" } } }

queued: queued
in_progress: in progress
completed: completed
failed: failed

Kling¶

Text-to-Video - Create Task¶

Submit a text-to-video task. Returns a task ID. Use the GET endpoint to query task status.

curl -X POST "https://www.chnllm.com/kling/v1/videos/text2video" \
  -H "Authorization: Bearer $WS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-v3",
    "prompt": "A cat playing piano in the garden",
    "negative_prompt": "blurry, low quality",
    "cfg_scale": 0.7,
    "mode": "pro",
    "aspect_ratio": "16:9",
    "duration": "4",
    "metadata": {
      "sound": "on"
    }
  }'

Request parameters:

Parameter	Type	Required	Description
`model`	string	Yes	Model name, e.g. `kling-v3`
`prompt`	string	Yes	Positive prompt describing the desired video content
`negative_prompt`	string	No	Negative prompt describing content to avoid
`cfg_scale`	float	No	Prompt adherence, range `0`–`1`; higher values follow the prompt more closely
`mode`	string	No	Generation mode, `std` (standard) or `pro` (high quality)
`aspect_ratio`	string	No	Aspect ratio, e.g. `16:9`, `9:16`, `1:1`
`duration`	string	No	Video duration in seconds, e.g. `4`, `5`, `10`
`metadata.sound`	string	No	Whether to generate audio, `on` to enable, `off` to disable

Response example:

{
  "code": 0,
  "message": "SUCCEED",
  "request_id": "request_id",
  "data": {
    "task_id": "task_id",
    "task_status": "submitted",
    "created_at": 1775188030000,
    "updated_at": 1775188030000
  }
}

Text-to-Video - Query Task¶

Query the status and result of a text-to-video task.

curl "https://www.chnllm.com/kling/v1/videos/text2video/task_id" \
  -H "Authorization: Bearer $WS_API_KEY"

Task status:

{
  "code": 0,
  "message": "SUCCEED",
  "request_id": "request_id",
  "data": {
    "task_id": "task_id",
    "task_status": "succeed",
    "task_status_msg": "",
    "created_at": 1775188030000,
    "updated_at": 1775188329000,
    "task_result": {
      "videos": [
        {
          "id": "video_id",
          "url": "video download URL",
          "duration": "4"
        }
      ]
    }
  }
}

Image-to-Video - Create Task¶

Submit an image-to-video task using an image as the first frame (optional last frame). Returns a task ID.

curl -X POST "https://www.chnllm.com/kling/v1/videos/image2video" \
  -H "Authorization: Bearer $WS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-v3",
    "image": "https://example.com/first-frame.jpg",
    "image_tail": "https://example.com/last-frame.jpg",
    "prompt": "A cat playing piano in the garden",
    "negative_prompt": "blurry, low quality",
    "cfg_scale": 0.7,
    "mode": "pro",
    "duration": "4",
    "metadata": {
      "sound": "on"
    }
  }'

Request parameters:

Parameter	Type	Required	Description
`model`	string	Yes	Model name, e.g. `kling-v3`
`image`	string	Yes	First frame image, supports image URL or Base64 encoding
`image_tail`	string	No	Last frame image, supports image URL or Base64 encoding
`prompt`	string	No	Positive prompt describing the desired video content
`negative_prompt`	string	No	Negative prompt describing content to avoid
`cfg_scale`	float	No	Prompt adherence, range `0`–`1`; higher values follow the prompt more closely
`mode`	string	No	Generation mode, `std` (standard) or `pro` (high quality)
`duration`	string	No	Video duration in seconds, e.g. `4`, `5`, `10`
`metadata.sound`	string	No	Whether to generate audio, `on` to enable, `off` to disable

Response example:

{
  "code": 0,
  "message": "SUCCEED",
  "request_id": "request_id",
  "data": {
    "task_id": "task_id",
    "task_status": "submitted",
    "created_at": 1775188030000,
    "updated_at": 1775188030000
  }
}

Image-to-Video - Query Task¶

Query the status and result of an image-to-video task.

curl "https://www.chnllm.com/kling/v1/videos/image2video/task_id" \
  -H "Authorization: Bearer $WS_API_KEY"

Task status:

{
  "code": 0,
  "message": "SUCCEED",
  "request_id": "request_id",
  "data": {
    "task_id": "task_id",
    "task_status": "succeed",
    "task_status_msg": "",
    "created_at": 1775188030000,
    "updated_at": 1775188329000,
    "task_result": {
      "videos": [
        {
          "id": "video_id",
          "url": "video download URL",
          "duration": "4"
        }
      ]
    }
  }
}

Kling task status:

submitted: submitted
processing: in progress
succeed: completed
failed: failed