GET
/v1/schemas/fal/image/fal-ai%2Fevf-sam
Accept:
Request body
10 properties · 2 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| image_url* | string | URL of the input image | |
| prompt* | string | The prompt to generate segmentation from. | |
| blur_mask | integer | Apply Gaussian blur to the mask. Value determines kernel size (must be odd number) | 0 ≤ n ≤ 50 · default: 0 |
| mask_only | boolean | Output only the binary mask instead of masked image | default: true |
| use_grounding_dino | boolean | Use GroundingDINO instead of SAM for segmentation | default: false |
| revert_mask | boolean | Invert the mask (background becomes foreground and vice versa) | default: false |
| expand_mask | integer | Expand/dilate the mask by specified pixels | 0 ≤ n ≤ 20 · default: 0 |
| negative_prompt | string | Areas to exclude from segmentation (will be subtracted from prompt results) | nullable |
| semantic_type | boolean | Enable semantic level segmentation for body parts, background or multi objects | default: false |
| fill_holes | boolean | Fill holes in the mask using morphological operations | default: false |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/evf-sam","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}