GET
/v1/schemas/fal/image/fal-ai/flux-vision-upscaler
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source tracee522601c7fcd6fda4789da74fc5d0918cdc80d572943793e95e0633fb9dbda02{
"fetchedAt": 1792818001,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
8 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| image_url* | string | The URL of the image to upscale. | |
| seed | integer | The seed to use for the upscale. If not provided, a random seed will be used. | nullable |
| steps | integer | Number of inference steps (4-50). | 4 ≤ n ≤ 50 · default: 20 |
| sync_mode | boolean | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. | default: false |
| creativity | number | The creativity of the model. The higher the creativity, the more the model will deviate from the original. Refers to the denoise strength of the sampling. | 0 ≤ n ≤ 1 · default: 0.3 |
| guidance | number | CFG/guidance scale (1-4). Controls how closely the model follows the prompt. | 1 ≤ n ≤ 4 · default: 1 |
| upscale_factor | number | The upscale factor (1-4x). | 1 ≤ n ≤ 4 · default: 2 |
| enable_safety_checker | boolean | Whether to enable the safety checker. | default: true |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/flux-vision-upscaler","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}