start_batch
Process files, folders, or globs through a background image pipeline. Returns a job ID for status polling, isolates per-file failures, and writes a JSON report to the output directory.
Instructions
Process files/folders/globs with one pipeline in the background. Returns job_id immediately; poll job_status. normalize equalises exposure/WB per image for consistent series; match_reference adds a per-image style match. Failures are isolated per file; a JSON report is written to output_dir.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"inputs": "<inputs>",
"output_dir": "<output_dir>"
},
"name": "start_batch"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| steps | No | ||
| format | No | ||
| inputs | Yes | ||
| naming | No | {stem}{ext} | |
| preset | No | ||
| dry_run | No | ||
| quality | No | ||
| metadata | No | keep | |
| normalize | No | none | |
| overwrite | No | ||
| recursive | No | ||
| output_dir | Yes | ||
| project_id | No | ||
| skip_existing | No | ||
| match_reference | No |