ReplicateText to videoComing soon

bytedance/video-upscaler

Name: bytedance/video-upscaler
Brand: Replicate

bytedance/video-upscaler 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
`video` required	text	—	Video to upscale and enhance. Typically a Seedance 2.0 output (1080p/24fps), but any AIGC video works.
`scene`	JSON	aigc	Scene-based enhancement preset. 'aigc' is recommended for Seedance / other model outputs. 'short_series' is tuned for short-form drama, 'ugc' for user-generated content, 'old_film' for film restoration, 'common' for everything else.
`target_fps`	JSON	60	Target output frame rate. Frame interpolation is applied if higher than the source. Valid range: 1–120.
`processing_type`	JSON	standard	Processing tier. 'standard' is self-serve and works for any BytePlus VOD account. 'pro' uses a higher-quality enhancement model — better skin textures and fine detail for real-people footage — but requires your BytePlus account to be whitelisted first (file a support ticket).
`target_resolution`	JSON	4k	Target output resolution. BytePlus VOD uses lowercase suffixes (`2k`/`4k` not `2K`/`4K`). 4k is the native maximum.

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": "bytedance/video-upscaler",
    "input": {
      "video": "<video>"
    }
  }'