Use the pre-process task when the source image may contain more than one valid target, or when your integration needs to explicitly choose which detected target receives the effect. For single-target images, pre-process can be skipped when the feature supports a default index value and your application does not need manual target selection.
The pre-process task detects candidate targets in the source image and returns their coordinates in data.results.result. Each item in the result array represents one detected target. Review the returned coordinates, map them to the intended face or region in the source image, and use that item's zero-based array index as the index value when creating the effect task.
For images with multiple detected faces or regions, do not rely on the default index value without checking the pre-process result. The effect is applied only to the target selected by index, so the integration must confirm the result item that corresponds to the intended target before running the effect task.
This task is asynchronous. After creating the task, handle completion with webhook if the feature supports it, or poll the corresponding pre-process status endpoint until data.task_status is success or error.
- Run task with src file url
- Run task with src file ID
curl -i -X POST \
https://yce-api-01.makeupar.com/s2s/v2.0/task/teeth-whiten/pre-process \
-H 'Authorization: Bearer <YOUR_TOKEN_HERE>' \
-H 'Content-Type: application/json' \
-d '{
"src_file_url": "https://example.com/selfie.jpg"
}'{ "status": 200, "data": { "task_id": "grH0CvsgXuAIHLUzD0V1Ol34hoet3R1tvdbtiVHrDb6_UqCLKIejAIajwxrhOAfe" } }