GET
/v1/schemas/fal/video/openimaginglab/flashvsr-plus
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace5441d4d548c53e371e4608f04b1647b4c715d4e5b3e6f82b6642dd732be0d821{
"fetchedAt": 1794373202,
"extractorVersion": "2",
"verifiedAt": null
} |
Request body
12 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| video_url* | string | The input video to upscale. | |
| preserve_audio | boolean | Copy the input audio track into the output. | default: true |
| upscale_factor | number | Spatial upscaling factor. Output is capped at about 4K. | 1 ≤ n ≤ 4 · default: 2 |
| enable_safety_checker | boolean | Authorized callers may set false to request relaxed screening. | default: true |
| seed | integer | The random seed used for the generation process. | nullable |
| sync_mode | boolean | If `True`, the media will be returned inline and not stored in history. | default: false |
| video_write_mode | enum | Output write mode. | fast | balanced | small · default: "balanced" |
| video_quality | enum | Output encoding quality. | low | medium | high | maximum · default: "high" |
| temporal_compression | enum | Input frames per latent frame. Use 2 or 1 for large motion; inference cost rises about 2x or 4x. | 1 | 2 | 4 · default: 4 |
| video_output_type | enum | Output container/codec. | X264 (.mp4) | VP9 (.webm) | PRORES4444 (.mov) | GIF (.gif) · default: "X264 (.mp4)" |
| model | enum | turbo: fastest (hybrid sliding attention). base: highest quality. v1: FlashVSR v1.1 weights with the base configuration. | turbo | base | v1 · default: "turbo" |
| color_fix | boolean | Apply low-frequency wavelet color correction. | default: false |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"openimaginglab/flashvsr-plus","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}