post-detect-inferences
Detect and extract visual features from images to generate mode maps for AI image processing, supporting modalities like canny, depth, pose, and segmentation.
Instructions
Advanced precision in image generation by transforming visual data from input images into mode maps.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| originalAssets | No | If set to true, returns the original asset without transformation | |
| dryRun | No | ||
| image | Yes | The image to be used to detect. Must reference an existing AssetId or be a data URL. | |
| modality | Yes | Modality to detect | |
| lowThreshold | No | Low threshold for Canny detector | |
| removeBackground | No | Remove background for Grayscale detector | |
| minThreshold | No | Minimum threshold for Grayscale conversion | |
| maxThreshold | No | Maximum threshold for Grayscale conversion | |
| factor | No | Contrast factor for Grayscale detector | |
| highThreshold | No | High threshold for Canny detector | |
| keypointThreshold | No | How polished is the surface? 0 is like a rough surface, 1 is like a mirror |