Video Upscaler Collection API
Eight video super-resolution endpoints from five providers — WaveSpeedAI (Standard, Pro, Ultimate, SeedVR2, LTX-2 19B), ByteDance, Bria, and Clarity AI — all reachable through one WaveSpeedAI API key. Pick by target resolution (up to 8K), source length, motion characteristics, and per-call cost.
Eight endpoints covering everything from fast 2x post-processing on AI-generated clips to 8K archival restoration. Frame-consistency is the common differentiator vs frame-by-frame image upscalers — each model maintains temporal coherence across motion. Same request shape across the lineup; one billing account, one rate-limit envelope.
About the Video Upscaler Collection API
What Video Upscaler Collection does, how it fits in the WaveSpeedAI model lineup, and why teams reach for it.
Video Upscaler Collection is a AI upscaling model from WaveSpeedAI, available through the WaveSpeedAI REST API. Eight video super-resolution endpoints from five providers — WaveSpeedAI (Standard, Pro, Ultimate, SeedVR2, LTX-2 19B), ByteDance, Bria, and Clarity AI — all reachable through one WaveSpeedAI API key. Pick by target resolution (up to 8K), source length, motion characteristics, and per-call cost.
Eight endpoints covering everything from fast 2x post-processing on AI-generated clips to 8K archival restoration. Frame-consistency is the common differentiator vs frame-by-frame image upscalers — each model maintains temporal coherence across motion. Same request shape across the lineup; one billing account, one rate-limit envelope.
The Video Upscaler Collection family on WaveSpeedAI ships 8 REST endpoints covering Upscaler workflow. Each variant carries its own pricing, parameter knobs, and example outputs — pick the one that matches your input modality and production constraints, or call several from the same API key to compose multi-step pipelines.
Run Video Upscaler Collection through the same API key, billing account, and rate-limit envelope you use for the other 1,000+ AI models on WaveSpeedAI. No separate vendor setup, no per-provider SDKs, no per-vendor rate-limit envelopes — one integration covers everything from text-to-image and text-to-video through audio synthesis, 3D generation, upscaling, and editing.
All Video Upscaler Collection API endpoints
8 endpoints available now on WaveSpeedAI — pick the variant that matches your workflow.

Video Upscaler
Bria Video Upscaler increases video resolution up to 8K with 2x or 4x upscaling. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Video Upscaler
LTX-2 19B Video Upscaler converts low-resolution videos into crisp 4K footage with seamless motion dynamics and frame consistency. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Video Upscaler
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.

Video
SeedVR2 Video Upscaler turns low-resolution videos into high-fidelity 4K with seamless motion and consistent frames. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Crystal Video Upscaler
Clarity AI Crystal Video Upscaler is a fast AI video super-resolution model that increases video resolution with target megapixel control and Clarity AI crystal-video processing. Ready-to-use REST inference API for enhancing low-resolution videos, restoring details, improving visual clarity, upscaling creative clips, product videos, social media content, and professional video enhancement workflows with simple integration, no coldstarts, and affordable pricing.

Ultimate Video Upscaler
Ultimate Video Upscaler converts low-resolution videos into crisp 4K footage with seamless motion dynamics and frame consistency. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Video Upscaler
AI Video Upscaler enhances resolution and clarity to fix blurry Sora 2 output and improve low-resolution footage with ML upscaling. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video Upscaler Pro
AI Video Upscaler Pro converts low-resolution videos into crisp 4K footage with seamless motion dynamics and frame consistency, ideal for upscaling Seedance 2.0 videos. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
See Video Upscaler Collection in action
Real outputs generated by the Video Upscaler Collection API. Hover any video to preview, click to open the full-size viewer.
How to use the Video Upscaler Collection API
Four steps from signup to a finished generation. Full Python, Node.js, and cURL examples are in the API section below.
- 1
Get an API key
Sign up for a WaveSpeedAI account and copy your API key from the dashboard. New accounts come with free starter credits — enough to run the playground a few dozen times before billing kicks in.
- 2
Submit a prediction
POST your input as JSON to https://api.wavespeed.ai/api/v3/wavespeed-ai/video-upscaler-pro. The endpoint returns a prediction id immediately — generations are async so you don't hold an open connection during inference.
- 3
Poll for completion
GET https://api.wavespeed.ai/api/v3/predictions/{request_id}/result every 1-2 seconds. The response includes a status field; keep polling until it flips from"queued" or"processing" to"completed".
- 4
Read the output URL
Once status is"completed", read the URL from data.outputs[0]. The URL points to your generated media on the WaveSpeedAI CDN — image, video, audio, or 3D file depending on the Video Upscaler Collection variant you called.
What you can build with Video Upscaler Collection
Common workflows developers and creators use the Video Upscaler Collection API for.
AI-generated video post-processing
wavespeed-ai/video-upscaler-pro is catalog-positioned as "ideal for upscaling Seedance 2.0 videos." Most AI video models output at 720p-1080p native; the Pro tier pushes them to 4K delivery without flicker artifacts. The Standard wavespeed-ai/video-upscaler is the cost-tuned variant for high-volume Sora 2 / Seedance / Wan output cleanup.
8K archival restoration with Bria
bria/fibo/video-upscaler ships 2x or 4x upscaling targeting up to 8K — the highest target resolution in the collection. Useful for archival broadcast, documentary, and film-grain restoration work where the output is destined for cinema-grade delivery.
Cost-tuned bulk pipelines
wavespeed-ai/video-upscaler (Standard) and clarity-ai/crystal-video-upscaler are the cost-tuned variants — useful when you're upscaling at volume (every Sora 2 generation, every Seedance Fast output) and don't need the Pro/Ultimate motion fidelity.
ByteDance Video Upscaler for first-party fidelity
bytedance/video-upscaler is ByteDance's first-party super-resolution model — strong fit when your source is itself a Seedance / Doubao output and you want the model's native motion language preserved through the upscale.
Ultimate tier for delivery-grade output
wavespeed-ai/ultimate-video-upscaler is the highest-quality WaveSpeedAI tier — slower per-second cost than Pro / Standard but used when the upscale is the final delivery artifact (broadcast master, streaming master, festival cut) and motion fidelity matters more than throughput.
Resolution targeting across the lineup
Pick target resolution per use case: 1080p for social, 2K for premium web, 4K for large-format and streaming, 8K for archival / cinema. Most endpoints take target as a parameter — same request body across the lineup, switch endpoint URL by tier / motion needs.
Documentary footage homogenization
Documentary work mixing archival low-res with modern 4K footage — upscale the archival material to homogenize resolution across the timeline. Bria for 8K archival masters; SeedVR2 / Ultimate for action documentary; Standard for talking-head archival.
Tips for prompting Video Upscaler Collection
Practical advice for getting better outputs from Video Upscaler Collection — drawn from the patterns that work across upscaler models in production pipelines.
Pick the model by source type, not just target resolution
AI-generated source (Sora 2, Seedance, Wan) → wavespeed-ai/video-upscaler-pro or wavespeed-ai/video-upscaler (catalog-positioned for AI output cleanup). Archival film → bria/fibo/video-upscaler (8K target). Complex motion → wavespeed-ai/seedvr2/video or wavespeed-ai/ltx-2-19b/video-upscaler. ByteDance-native source → bytedance/video-upscaler.
Match output resolution to delivery target
4K for streaming, 1080p for social, 720p for in-app, 8K only for cinema / archival masters. Don't upscale to the max just because you can — the higher you go, the more visible source artifacts become, and downstream encoders may not preserve the extra detail.
Cleaner source = better output
Heavy compression in source amplifies through the upscale. If you have access to the highest-quality master (ProRes, DNxHD, raw exports), use that. Re-encoded compressed source gives back compressed-looking upscales regardless of which model you pick.
Use the Standard tier as the bulk pipeline
wavespeed-ai/video-upscaler (Standard) and clarity-ai/crystal-video-upscaler are cost-tuned for high-volume passes — every AI-video generation, every social clip. Reserve Pro / Ultimate / SeedVR2 for delivery-grade output where motion fidelity matters.
Re-encode for the downstream pipeline
After upscaling, re-encode to the codec and color space your downstream needs (H.264 for web, H.265/HEVC for streaming, ProRes for editorial). Each upscaler outputs high-quality intermediates; the final encode determines what reaches viewers.
Frame consistency is the common differentiator
Every endpoint in the collection maintains temporal coherence — no inter-frame flicker, no detail popping. Frame-by-frame image upscalers applied to video can't promise this. Pick by tier, but trust temporal consistency across the lineup.
A/B route by source for cost-quality tuning
Same request shape across the eight endpoints means you can A/B route based on source characteristics — fast iteration on Standard, delivery on Pro / Ultimate / SeedVR2, archival on Bria. Useful for SaaS pipelines that need to balance per-call cost with output fidelity per shot.
Video Upscaler Collection API pricing
Pricing is per-output. The final charge scales with the parameters you set in each variant's playground (resolution, duration, output count, references).
| Endpoint | Type | Starting price |
|---|---|---|
| bria/fibo/video-upscaler | upscaler | $0.14 |
| wavespeed-ai/ltx-2-19b/video-upscaler | upscaler | $0.15 |
| bytedance/video-upscaler | upscaler | $0.007 |
| wavespeed-ai/seedvr2/video | upscaler | $0.10 |
| clarity-ai/crystal-video-upscaler | upscaler | $0.10 |
| wavespeed-ai/ultimate-video-upscaler | upscaler | $0.15 |
| wavespeed-ai/video-upscaler | upscaler | $0.025 |
| wavespeed-ai/video-upscaler-pro | upscaler | $0.15 |
Call the Video Upscaler Collection API
Sign up for an API key at wavespeed.ai/accesskey, then submit a prediction via REST. The playground generates ready-to-paste samples for any combination of inputs.
HTTP example
# 1. Submit a prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/video-upscaler-pro" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{}'
# 2. Poll the result until status = "completed"
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# Read the output URL from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY
const result = await client.run("wavespeed-ai/video-upscaler-pro", {});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"wavespeed-ai/video-upscaler-pro",
{}
)
print(output["outputs"][0]) # → URL of the generated outputVideo Upscaler Collection vs alternatives
When to pick Video Upscaler Collection over similar models on WaveSpeedAI.
Video Upscaler Collection vs Topaz Video AI
Topaz Video AI is desktop-only with high local GPU requirements and per-seat licensing. The Video Upscaler collection is a REST API surface — better for cloud pipelines, batch jobs, and SaaS integration, with eight model choices instead of one.
Video Upscaler Collection vs Frame-by-frame Real-ESRGAN
Applying Real-ESRGAN to video frame-by-frame produces flicker because each frame is upscaled independently. Every endpoint in this collection maintains temporal frame consistency — critical for delivery work where motion smoothness matters.
Video Upscaler Collection vs NVIDIA RTX Video Super Resolution
RTX VSR is consumer playback-only — upscales at decode time in supported browsers. The collection produces upscaled output files for production delivery, suitable for re-export, archive, and pipeline integration.
Video Upscaler Collection vs Single-model upscaler pipeline
Pinning a pipeline to one upscaler means no fallback when capacity hits and no tier choice between cost / fidelity / target resolution. Eight interchangeable endpoints let you route by source type (AI-generated vs archival), target (1080p / 4K / 8K), or per-call cost without rewriting downstream code.
Video Upscaler Collection API — Frequently asked questions
Pricing, license, integration — common questions about running Video Upscaler Collection on WaveSpeedAI.
What is the Video Upscaler Collection API?
Video Upscaler Collection is a WaveSpeedAI upscaler model exposed as a REST API on WaveSpeedAI. Eight video super-resolution endpoints from five providers — WaveSpeedAI (Standard, Pro, Ultimate, SeedVR2, LTX-2 19B), ByteDance, Bria, and Clarity AI — all reachable through one WaveSpeedAI API key. Pick by target resolution (up to 8K), source length, motion characteristics, and per-call cost. You can call it programmatically or try it from the playground linked above.
How do I call the Video Upscaler Collection API?
Sign up for a WaveSpeedAI account, copy your API key from /accesskey, then POST to https://api.wavespeed.ai/api/v3/wavespeed-ai/video-upscaler-pro 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]. Full Python / Node.js / cURL examples are above.
How much does the Video Upscaler Collection API cost?
Video Upscaler Collection starts at $0.007 per run. The exact cost scales with the parameters you set (resolution, duration, output count, references). The live cost preview next to the Generate button in the playground shows the exact price for your current input.
Which Video Upscaler Collection variants are available?
WaveSpeedAI hosts 8 Video Upscaler Collection endpoints: bria/fibo/video-upscaler, wavespeed-ai/ltx-2-19b/video-upscaler, bytedance/video-upscaler, wavespeed-ai/seedvr2/video, clarity-ai/crystal-video-upscaler, wavespeed-ai/ultimate-video-upscaler, wavespeed-ai/video-upscaler, wavespeed-ai/video-upscaler-pro. Each variant has its own playground page and pricing.
Can I use Video Upscaler Collection outputs commercially?
Commercial usage rights follow the WaveSpeedAI model license. Most WaveSpeedAI models permit commercial output use; see each model's playground page for the specific license summary, and WaveSpeedAI's Terms of Service for platform-level conditions.
Why use Video Upscaler Collection on WaveSpeedAI instead of going direct?
One API key + one billing account across Video Upscaler Collection AND 1,000+ other AI models from other providers. No per-vendor SDK setup, no separate rate-limit envelopes, no rewrite-per-vendor integration code. Pricing is typically at parity with or below WaveSpeedAI's direct API.
About WaveSpeedAI
The team behind Video Upscaler Collection and the broader WaveSpeedAI model lineup on WaveSpeedAI.
WaveSpeedAI runs an inference platform that hosts 1,000+ AI models from every major provider — ByteDance, Google, OpenAI, Alibaba, Kuaishou, ElevenLabs, and dozens of independent labs — behind one API key, one billing account, and one rate-limit envelope. WaveSpeedAI also ships first-party models (Image / Video Upscalers, Watermark Removers, Animate, InfiniteTalk) tuned for production pipelines.
Start building with Video Upscaler Collection on WaveSpeedAI
Free starter credits on signup. One API key across 1,000+ AI models from WaveSpeedAI and every other provider.