The Video Edit Enhanced 2.0 operator (las_video_edit_enhance) provides business-oriented editing templates on top of Seedance's video generation capabilities. Requests use template.id to select a server-maintained processing workflow, enabling direct generation, general keyframe editing, face swapping, complete character replacement, or global style transfer while preserving the original video's actions, shots, composition, and timeline.

Operator ID: las_video_edit_enhance

Core capabilities #

• Template-based routing: The business only specifies the editing target, and the server-side template is responsible for selecting the VLM, keyframe redraw, structural video, and Seedance prompt assembly workflow.
• General keyframe editing: VLM interprets the video and user intent, selects keyframes, and uses Seedream to edit based on the source frame canvas.
• Full character replacement: Uses the original video as the basis for actions and timeline, locking the final character appearance with the target character image and redrawn keyframes.
• Style transfer: By default, uses pure depth structural video to preserve spatial layout, actions, and camera movement, reducing interference from the original video's color, material, subtitles, and cinematographic style.
• Multi-subject mapping: Multiple source subjects in user_prompt can be bound to different target images in image_urls respectively.
• Controllable fallback: When allow_fallback=true, preprocessing failures can fall back to direct generation equivalent to basic; for strong semantic editing, it is recommended to set it to false to avoid returning incomplete editing results.

Supported preset templates #

The supported template types and applicable scenarios are as follows.

Template boundaries:

• To replace only characters, use replace/person_replace.
• Use style_transfer/general only to change global visual media and style; do not use style transfer templates when editing only local subjects.
• general is the general fallback template. When a dedicated template can more clearly constrain person identity, replacement scope, and video structure, the dedicated template should be preferred.

Supported regions #

• Beijing: cn-beijing

Operator performance #

Input requirements #

Output requirements #

• Billing standards

  Breakdown	Billing standards description
  Billing items	Includes video preprocessing and video editing as two billing items. Both billing items are charged based on usage calculated from the input/output video duration. Video preprocessing billing: Depends on the type of video editing task template selected when submitting the task. When submitting an operator task, set the processing template of the task using the template request parameter. The video preprocessing billing unit price of different task templates varies. For video preprocessing billing, usage is calculated based on the output video duration. Video editing billing: Depends on the type of task processing model selected when submitting the task. When submitting an operator task, set the processing model of the task using the model request parameter. The video editing billing unit price of different models varies. For video editing billing, usage is calculated as the sum of the input and output video durations. The final total cost is the sum of the video preprocessing and video editing billing items.
  Billing type	Pay-as-you-go billing, unit: CNY/second, billed hourly based on actual usage. Billing precision: Rounded.
  Unit price	Video preprocessing unit price: 0.16 CNY/second Video editing unit price details: depend on the model type and video resolution you select. See the table below for details.

  warning

  • For each task, the video editing fee depends not only on the unit price, but also on the input/output video duration and the input/output video resolution.
  • Fees are incurred only for tasks that successfully generate videos. No fees are charged for scenarios where video generation fails due to review or other operational reasons.

• Billing details
  Billing estimate: Total cost ≈ video preprocessing fee + video editing fee = video preprocessing unit price * output video duration + video editing unit price * (input video duration + output video duration)

  warning

  The above formula is for cost estimation only; actual billing is based on the calculated amount in the invoice.

  • Video preprocessing unit price: 0.16 CNY/second

  • Video editing unit price details: depend on the model type and video resolution you select. Details are as follows.

    Model	Video resolution	List price
    seedance_2.0_fast	480p	0.442 CNY/second
    	720p	0.95 CNY/second
    seedance_2.0_mini	480p	0.282 CNY/second
    	720p	0.605 CNY/second
    seedance_2.0	480p	0.562 CNY/second
    	720p	1.208 CNY/second
    	1080p	3.014 CNY/second
    	4k	6.22 CNY/second
    seedance_2.5	480p	0.806 CNY/second
    	720p	1.814 CNY/second

• Billing example

  • Example scenario: Using the replace/person_replace task template and the Seedance 2.0 model to perform video face replacement editing, with an input video duration of 10 seconds and a resolution of 1080p.
  • Cost details:
    Total cost ≈ video preprocessing fee + video editing fee = 0.16 CNY/second * 10 seconds + 3.014 CNY/second * (10 seconds + 10 seconds) = 61.88 CNY

API invocation instructions #

• The API for this operator is an asynchronous task interface. You need to submit a task via the submit interface to obtain the task_id, then use the Poll interface to check the status of the corresponding task (task_id) and retrieve the operator processing result. Additionally, this operator supports asynchronous callback capability (Callback). You can set the callback parameter callback.url when initiating an operator task. LAS will send an HTTP POST notification to this URL. For guidance on using asynchronous callbacks, see Asynchronous callback API.
• After the task is submitted, the task_id is valid for 3 days. After 3 days, you will not be able to obtain the operator processing result using this task_id.

Submit #

Interface description #

Invoke the Video Edit Enhanced 2.0 operator (las_video_edit_enhance) to submit an asynchronous task. The operator uses template.id to select a server-maintained business workflow, enabling direct generation, general keyframe editing, face swapping, complete character replacement, or global style transfer while preserving the original video's actions, shots, composition, and timeline.

Request parameters #

Response parameters #

Example #

Request example
basic: Direct generation

curl --location "https://operator.las.cn-beijing.volces.com/api/v1/submit" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $LAS_API_KEY" \
--data '{
  "operator_id": "las_video_edit_enhance",
  "operator_version": "v1",
  "data": {
    "video_url": "tos://bucket/videos/input.mp4",
    "template": {"id": "basic"},
    "user_prompt": "保持镜头和动作不变，提升画面清晰度与色彩层次",
    "image_urls": []
  }
}'

general: General local editing

curl --location "https://operator.las.cn-beijing.volces.com/api/v1/submit" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $LAS_API_KEY" \
--data '{
  "operator_id": "las_video_edit_enhance",
  "operator_version": "v1",
  "data": {
    "video_url": "tos://bucket/videos/input.mp4",
    "template": {"id": "general"},
    "user_prompt": "把桌面上的杯子改成参考图1中的产品，其他人物、物体和背景保持不变",
    "image_urls": ["https://example.com/product.png"]
  }
}'

replace/person_replace: Complete person replacement

curl --location "https://operator.las.cn-beijing.volces.com/api/v1/submit" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $LAS_API_KEY" \
--data '{
  "operator_id": "las_video_edit_enhance",
  "operator_version": "v1",
  "data": {
    "video_url": "tos://bucket/videos/input.mp4",
    "template": {
      "id": "replace/person_replace"
    },
    "user_prompt": "把视频中左侧女性完整替换为参考图1中的人物，把右侧男性完整替换为参考图2中的人物；使用目标人物的脸、发型、体型、服装和配饰，保留原视频动作、位置、互动、镜头和背景",
    "image_urls": [
      "https://example.com/woman.png",
      "https://example.com/man.png"
    ],
    "use_asset_api": true
  }
}'

style_transfer/general: Global style transfer

curl --location "https://operator.las.cn-beijing.volces.com/api/v1/submit" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $LAS_API_KEY" \
--data '{
  "operator_id": "las_video_edit_enhance",
  "operator_version": "v1",
  "data": {
    "video_url": "tos://bucket/videos/input.mp4",
    "template": {
      "id": "style_transfer/general",
      "paras": {
        "style_template": "2d_japanese"
      }
    },
    "user_prompt": "将完整视频转换为高完成度日系二维动画，保持人物身份、数量、动作、口型、镜头、构图和时间线，不要字幕和水印",
    "image_urls": [
      https://example.com/man.png
    ],
    "use_asset_api": true
  }
}'

Response example

{
  "metadata": {
    "task_id": "task-20260427143000-abc123",
    "task_status": "PENDING",
    "business_code": "0",
    "error_msg": ""
  }
}

Error code #

Poll #

Interface description #

Query the execution status and result of the Video Edit Enhanced task.

Request parameters #

Response parameters #

Example #

Request example

curl --location "https://operator.las.cn-beijing.volces.com/api/v1/poll" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $LAS_API_KEY" \
--data '{
    "operator_id": "las_video_edit_enhance",
    "operator_version": "v1",
    "task_id": "task-20260427143000-abc123"
}'

Response example

{
  "metadata": {
    "task_status": "COMPLETED",
    "business_code": "0",
    "operator_id": "las_video_edit_enhance",
    "operator_version": "v1"
  },
  "data": {
    "id": "cgt-xxxxxxxx",
    "model": "doubao-seedance-2-0-260128",
    "status": "succeeded",
    "resolution": "1080p",
    "ratio": "adaptive",
    "duration": 5,
    "framespersecond": 24,
    "usage": { "completion_tokens": 221386, "total_tokens": 221386 },
    "content": {
      "video_url": "https://{bucket}.tos-cn-beijing.volces.com/xxxx/output.mp4?X-Tos-...",
      "last_frame_url": "https://{bucket}.tos-cn-beijing.volces.com/xxxx/last_frame.png?X-Tos-..."
    }
  }
}

Error code #