Omni

Input type:

• prompt: Text prompt
• first_frame: First-frame image
• last_frame: Last-frame image
• refer_image: Element / scene reference image
• feature_video: Feature reference video
• base_video: Base video to edit
• element: Element

{
  "type": "prompt",
  "text": "string"
}

• text: Prompt content, max 3072 characters (recommended ≤ 2500)
• Multi-shot format: "shot n, m, words; shot n, m, words;" (separated by standard semicolons), where:
  • n: shot sequence number (1–6 shots supported)
  • m: shot duration in seconds (each shot ≥ 1s; sum must equal total video duration)
  • words: shot prompt (max 512 characters)
• Reference an image, Element, or video in the prompt with @xxx, e.g. @image_1, @Zhang, @video_1
• Avoid Element names that are substrings of each other (e.g. @Zhang and @ZhangSan)
• Avoid Element names that overlap with prompt content (e.g. do not use @gmail if the prompt contains xxx@gmail.com)

{
  "type": "first_frame",
  "url": "string",
  "id": "string"
}

Images can be used as scene/style references, or as first/last frames.

• url: Image URL or Base64
• id: Optional input index ID for use in the prompt; must be unique within the same task
• Formats: .jpg, .jpeg, .png
• Size: max 50MB
• Dimensions: width and height ≥ 300px; aspect ratio between 1:2.5 and 2.5:1
• Supports first-frame and first-and-last-frame generation; last-frame-only is not supported
• Quantity limits (depend on reference video and Element types):
  • No reference video + only multi-image Elements: total of reference images and multi-image Elements ≤ 7
  • No reference video + both video-character Elements and multi-image Elements: total of reference images and multi-image Elements ≤ 4
  • With a reference video + only multi-image Elements: total of reference images and multi-image Elements ≤ 4
  • With a reference video: video-character Elements and reference images cannot be used together

{
  "type": "feature_video",
  "url": "string",
  "id": "string"
}

• url: Video URL
• id: Optional input index ID for use in the prompt; must be unique within the same task
• Formats: .mp4, .mov
• Size: max 200MB
• Duration: 3s–15.5s (inclusive)
• Dimensions: width and height between 700px and 4553px; total pixels ≤ 8294400; aspect ratio between 0.4 and 2
• Frame rate: 24fps–60fps (output is 24fps)
• Maximum 1 reference video. After adding a reference video, add at most one video-character Element

When using feature_video:

• Multi-shot is supported; multi_shot must be true
• Native audio is not supported; audio must be off

When using base_video (video to edit):

• First/last frames are not supported
• Multi-shot is not supported
• Native audio is not supported; audio cannot be native

{
  "type": "element",
  "element_id": "string",
  "id": "string"
}

• element_id: Element ID returned by the Element-related API
• id: Input index ID used in the prompt (e.g. @element_1); must be unique within the same task
• Elements are either video-character Elements (from video) or multi-image Elements (from images); limits differ by type
• Count limits:
  • First frame or first-and-last frames: at most 3 Elements
  • No reference video + only multi-image Elements: reference images + multi-image Elements ≤ 7
  • No reference video + only video-character Elements: ≤ 3 video-character Elements
  • No reference video + both types: ≤ 3 video-character Elements; reference images + multi-image Elements ≤ 4
  • With reference video + only multi-image Elements: reference images + multi-image Elements ≤ 4
  • With reference video + only video-character Elements: ≤ 1 video-character Element
  • With a reference video: video-character Elements and multi-image Elements cannot be used together

Whether to generate multi-shot video. Default true.

When set to false, multi-shot prompts will not produce multi-shot output.

Whether to generate audio for the video. Default off.

• native: Include native audio matching the visuals
• original: Retain the original sound of the reference video
• off: No audio

Output video resolution. Default 720p.

• 720p: 720P output
• 1080p: 1080P output
• 4k: 4K output

Aspect ratio of generated video frames. Default 16:9.

Options: 16:9, 9:16, 1:1

Required when there is no first frame or reference video.

Video duration in seconds. Default 5.

Options: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15

Callback URL for task result notifications. If set, the server sends a notification when the task status changes.

Custom task ID. Does not overwrite the system-generated task ID and can be used for querying. Must be unique within the account.

Whether to also generate a watermarked result, controlled by enabled:

{
  "enabled": false
}

• true: Include watermarked result
• false (default): No watermark

Custom watermarks are not supported.

Account charge type:

• cash: Balance deduction
• unit: Resource package deduction

Balance type; only present when charge_type=cash:

• balance: Official quota
• test_balance: Test quota

Deduction amount. When charge_type=cash, the discounted balance price; when charge_type=unit, the resource package units deducted (decimal string).

Resource package type; only present when charge_type=unit. Enum: video, image, audio.

List price for balance deduction; only present when charge_type=cash.