GET
/v1/schemas/fal/video/fal-ai%2Fflashvsr%2Fupscale%2Fvideo
Accept:
Request body
12 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| video_url* | string | The input video to be upscaled | |
| output_quality | enum | The quality of the output video. | low | medium | high | maximum · default: "high" |
| quality | integer | Quality level for tile blending (0-100). Controls overlap between tiles to prevent grid artifacts. Higher values provide better quality with more overlap. Recommended: 70-85 for high-res videos, 50-70 for faster processing. | 0 ≤ n ≤ 100 · default: 70 |
| preserve_audio | boolean | Copy the original audio tracks into the upscaled video using FFmpeg when possible. | default: false |
| seed | integer | The random seed used for the generation process. | nullable |
| enable_safety_checker | boolean | Authorized callers may set false to request relaxed screening. | default: true |
| upscale_factor | number | Upscaling factor to be used. | 1 ≤ n ≤ 4 · default: 2 |
| output_write_mode | enum | The write mode of the output video. | fast | balanced | small · default: "balanced" |
| output_format | enum | The format of the output video. | X264 (.mp4) | VP9 (.webm) | PRORES4444 (.mov) | GIF (.gif) · default: "X264 (.mp4)" |
| color_fix | boolean | Color correction enabled. | default: true |
| acceleration | enum | Acceleration mode for VAE decoding. Options: regular (best quality), high (balanced), full (fastest). More accerleation means longer duration videos can be processed too. | regular | high | full · default: "regular" |
| sync_mode | boolean | If `True`, the media will be returned inline and not stored in history. | default: false |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/flashvsr/upscale/video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}