GET

/v1/schemas/fal/video/topaz/upscale/video/generative

Accept:

kind inputactivity videohash 27eca1ed…extracted Oct 22, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `b4eb21faf446a562e26c56236ce7b69d7137591910c5733fcd2e38a3bb4ecaf6` { "fetchedAt": 1792645225, "extractorVersion": "1", "verifiedAt": null }

Request body

7 properties · 1 required · 0 $defs

property	type	description	constraints
video_url*	string	URL of the video to upscale
softness	number	How much softening the model applies to the output, from 1 (sharpest) to 5 (softest). Starlight Precise 2.6 only; leave unset for Topaz's default.	1 ≤ n ≤ 5 · nullable
target_fps	integer	Target FPS for the output. Frame interpolation is enabled only when this differs from the source FPS.	16 ≤ n ≤ 60 · nullable
H264_output	boolean	Whether to use H264 codec for output video. Default is H265.	default: false
upscale_factor	number	Factor to upscale the video by (e.g. 2.0 doubles width and height)	1 ≤ n ≤ 4 · default: 2
enable_safety_checker	boolean		default: true
model	enum	Generative diffusion enhancement model. Starlight Precise 2.6 adds realism to AI-generated video; Starlight HQ maximizes quality on high-resolution sources; Starlight Mini restores archival footage; Starlight Sharp is fast restoration with sharper detail; Star…	Starlight Precise 2.6 \| Starlight HQ \| Starlight Mini \| Starlight Sharp \| Starlight Fast 2 · default: "Starlight Precise 2.6"

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"topaz/upscale/video/generative","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}