ByteDance Video Upscaler | AI Video Upscaler API

Seedance Video Upscaler

BytePlus VOD's enhancement feature provides an intelligent and efficient solution for improving video quality through AI algorithms. This feature integrate atomic capabilities like face enhancement, color enhancement, text enhancement, compression distortion removal, noise reduction, deblurring, dark scene optimization, and brightness equalization. It adaptively matches the optimal processing strategy to ensure that videos present a clearer and more vivid visual effect at the same bitrate.

Powered by a high-quality, large-scale training dataset covering both OGC (Professionally Produced Content) and PUGC (Professional User-Generated Content).

What Seedance does

Super-resolution upscaling to 1080p / 2K / 4K with detail recovery and de-ringing
Temporal consistency to reduce flicker and ghosting between frames
Works well on live-action, animation, game captures, product reels, and vertical shorts

Inputs

video – The source clip you want to enhance.
target_resolution – One of:
1080p
2k
4k

How to use

Upload or paste the URL of your video.
Choose the desired target_resolution (1080p, 2k, or 4k).
Click Run to upscale; then compare the result with your original in your editor or viewer.

Notes

Very short clips are billed with a 5-second minimum.
Jobs longer than 600 seconds (10 minutes) only bill the first 600 seconds.

Pricing

Resolution	Price per second
1080p	$0.0072
2k	$0.0144
4k	$0.0288

Minimum charge: 5 seconds at the chosen resolution
Maximum billed duration: 600 seconds per job

Tips

Feed the highest-quality source you have; upscalers can’t fully restore detail from heavy blur.
If the source is very noisy, denoise first, then upscale.
Match your export’s aspect ratio to the target platform to avoid letterboxing after upscaling.

Video Upscaler API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/video-upscaler with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Video Upscaler below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/bytedance/video-upscaler" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "video": "https://example.com/your-input.mp4",
    "target_resolution": "1080p"
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("bytedance/video-upscaler", {
        "video": "https://example.com/your-input.mp4",
        "target_resolution": "1080p"
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "bytedance/video-upscaler",
    {
    "video": "https://example.com/your-input.mp4",
    "target_resolution": "1080p"
}
)

print(output["outputs"][0])  # → URL of the generated output

Video Upscaler API — Frequently asked questions

What is the Video Upscaler API?

Video Upscaler is a ByteDance model for upscaling, exposed as a REST API on WaveSpeedAI. Video Upscaler uses AI super-resolution to upscale videos to 4K and recover fine detail in a secure cloud environment. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Video Upscaler API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-video-upscaler.

How much does Video Upscaler cost per run?

Video Upscaler starts at $0.007 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Video Upscaler accept?

Key inputs: `video`, `target_resolution`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-video-upscaler.

How long does Video Upscaler take to generate?

Average end-to-end generation time on WaveSpeedAI is around 366 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Video Upscaler outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (ByteDance). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

ExamplesView all

Related Models

README