videoseg

Video human segmentation tool: invokes Aliyun's async SegmentVideoBody and returns a same-length black/white mask video, suitable for downstream compositing or matting.

Overview

Field	Value
Model ID	`videoseg`
CLI	`dlazy videoseg`
MCP	`videoseg` (Claude Code surfaces this as `mcp__dlazy__videoseg`)
Type	`video`
Execution	Returns synchronously
Batch	Supports `--batch <n>` parallel fan-out

Parameters

Arg	Type	Required	Notes
`video`	url	Yes	Video (URL); video (accepts URL, local path, or data: URL)

--input @file.json or --input '{...}' can supply all args at once; flags take precedence over --input keys.

CLI Examples

dlazy videoseg --help
dlazy videoseg --video "https://example.com/source.mp4"
dlazy videoseg --video "./local-video.mp4"
dlazy videoseg --video "https://example.com/source.mp4" --dry-run
dlazy videoseg --video "https://example.com/source.mp4" --batch 4

Compose with a pipeline

dlazy seedance-2.0-fast --prompt "reference clip" \
  | dlazy videoseg --video -

MCP is consumed by AI clients, not handwritten. Once dLazy is registered as an MCP server the tool appears in the client's tool list — Claude Code surfaces it as mcp__dlazy__videoseg; generic clients (e.g. OpenClaw) call it as videoseg.

See MCP setup for how to add the server.

Output

{
  "outputs": [
    { "type": "video", "id": "o_...", "url": "https://files.dlazy.com/result.mp4", "mimeType": "video/mp4" }
  ]
}

Media tools emit image / video / audio / file outputs. Use --output url to print only the URLs on stdout.