Image Upscaler API
WaveSpeedAI Image Upscaler — upscale any image to 2K, 4K, or 8K with AI super-resolution. Detail preservation, JPEG artifact removal, and dedicated face-enhancement mode.

About the Image Upscaler API
What Image Upscaler does, how it fits in the WaveSpeedAI model lineup, and why teams reach for it.
Image Upscaler is a AI upscaling model from WaveSpeedAI, available through the WaveSpeedAI REST API. WaveSpeedAI Image Upscaler — upscale any image to 2K, 4K, or 8K with AI super-resolution. Detail preservation, JPEG artifact removal, and dedicated face-enhancement mode.
The Image Upscaler family on WaveSpeedAI ships 1 REST endpoint 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 Image Upscaler 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 Image Upscaler API endpoints
1 endpoint available now on WaveSpeedAI — pick the variant that matches your workflow.
See Image Upscaler in action
Real outputs generated by the Image Upscaler API. Hover any video to preview, click to open the full-size viewer.
How to use the Image Upscaler 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/image-upscaler. 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 Image Upscaler variant you called.
What you can build with Image Upscaler
Common workflows developers and creators use the Image Upscaler API for.
Photo restoration and archive
Bring vintage, low-res, or compressed photos up to modern print/display resolutions — useful for personal archives, museum digitization, and historical content publishing.
E-commerce catalog imagery
Upscale product photography to 2K/4K for retina displays and zoom views — improves perceived quality without re-shooting.
Print and large-format preparation
Prepare images for poster, billboard, or print-quality output — push small-format images up to 4K/8K with details preserved.
AI-generation post-processing
Most AI image models cap at 1K-2K native output. Use Image Upscaler as a 2x/4x post-process pass to push generations to delivery resolution.
Tips for prompting Image Upscaler
Practical advice for getting better outputs from Image Upscaler — drawn from the patterns that work across upscaler models in production pipelines.
Pick the smallest scale factor that meets your target
2x is the sweet spot for most footage. 4x and 8x amplify any compression artifacts, banding, or noise in the source. If you need 4x, consider running 2x twice with different settings rather than a single 4x pass.
Use face-enhanced mode for portraits
Many upscalers have a face-specific enhancement mode that preserves identity and skin texture better than the generic pass. If the source has visible faces, switch it on — generic upscalers often over-smooth skin and 'fix' subtle facial features in ways that lose likeness.
Match codec and color space on the way out
After upscaling video, re-encode to a codec and color space that match your downstream pipeline (Rec.709 for delivery, ProRes for editorial). The upscaler's raw output is usually fine; the encode is where many quality losses happen.
Image Upscaler 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 |
|---|---|---|
| wavespeed-ai/image-upscaler | upscaler | $0.010 |
Call the Image Upscaler 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/image-upscaler" \
-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/image-upscaler", {});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"wavespeed-ai/image-upscaler",
{}
)
print(output["outputs"][0]) # → URL of the generated outputImage Upscaler vs alternatives
When to pick Image Upscaler over similar models on WaveSpeedAI.
Image Upscaler vs Topaz Gigapixel
Topaz Gigapixel is a desktop app requiring local GPU. Image Upscaler is a REST API — easier to integrate into automated pipelines, no per-seat licensing, no local hardware requirements.
Image Upscaler vs Real-ESRGAN
Real-ESRGAN is open-source — you can self-host. Image Upscaler is hosted (no infra setup), with consistent quality on portrait/face crops via the dedicated face-enhancement mode.
Image Upscaler vs Magnific AI
Magnific is a web app. Image Upscaler is API-first — better for batch operations and SaaS integration. Comparable quality on the typical AI-generation upscale use case.
Image Upscaler API — Frequently asked questions
Pricing, license, integration — common questions about running Image Upscaler on WaveSpeedAI.
What is the Image Upscaler API?
Image Upscaler is a WaveSpeedAI upscaler model exposed as a REST API on WaveSpeedAI. WaveSpeedAI Image Upscaler — upscale any image to 2K, 4K, or 8K with AI super-resolution. Detail preservation, JPEG artifact removal, and dedicated face-enhancement mode. You can call it programmatically or try it from the playground linked above.
How do I call the Image Upscaler API?
Sign up for a WaveSpeedAI account, copy your API key from /accesskey, then POST to https://api.wavespeed.ai/api/v3/wavespeed-ai/image-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]. Full Python / Node.js / cURL examples are above.
How much does the Image Upscaler API cost?
Image Upscaler starts at $0.010 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 Image Upscaler variants are available?
WaveSpeedAI hosts 1 Image Upscaler endpoints: wavespeed-ai/image-upscaler. Each variant has its own playground page and pricing.
Can I use Image Upscaler 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 Image Upscaler on WaveSpeedAI instead of going direct?
One API key + one billing account across Image Upscaler 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 Image Upscaler 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 Image Upscaler on WaveSpeedAI
Free starter credits on signup. One API key across 1,000+ AI models from WaveSpeedAI and every other provider.




