ReplicateText to videoComing soon

black-forest-labs/flux-video-upscale

Name: black-forest-labs/flux-video-upscale
Brand: Replicate

black-forest-labs/flux-video-upscale is a text to video tool from Replicate that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs: In the background
Returns: video
Longest queue wait: 3600s
Run deadline: 3600s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`input_video` required	text	—	The video to upscale. Must be an mp4, at most 50MB, 20 seconds, and 2560x1440 (2K) of source footage.
`prompt`	text		Optional description of the clip's content to steer the enhanced detail. Leave empty for a neutral upscale.
`creativity`	JSON	1	How the upscaler treats your footage. 0 (precise) preserves the source exactly and sharpens it — use it for faces, products, and real people. 1 (creative) restores and invents fine detail more aggressively — use it for generated footage, textures, and scenery, but it doesn't preserve identity as strictly.
`upscale_factor`	number 1.5 to 3	2	How much to scale the output relative to the source resolution. The output keeps the source aspect ratio. Output frames are capped at about 14.4 megapixels (4K), so very large sources are upscaled by less than the requested factor.
`safety_tolerance`	number (whole) 0 to 4	2	Moderation strictness for the prompt and the delivered frames, 0 (strictest) to 4 (most permissive).

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "replicate",
    "model": "black-forest-labs/flux-video-upscale",
    "input": {
      "input_video": "<input_video>"
    }
  }'