Media · Apify actor
Enlarge images 2x or 4x with AI, not blur
Paste image links and get back public download links to upscaled files with sharper detail, cleaner edges and less blur and JPEG noise than a normal resize. Two models: one for photos and real-world images, one for anime, cartoons, illustrations and line art. It runs Real-ESRGAN, the widely used open-source model, inside the actor: no third-party AI API, no watermark.
Launching soon. AI Image Upscaler is built, tested and priced, and is waiting to go public on the Apify Store. The button below opens its Store page, which will be live shortly.
What it does
AI Image Upscaler, in short
- Real-ESRGAN general x4v3 for photos, products, screenshots and scans; AnimeVideo v3 for drawn art
- 4x or 2x at the same price
- Transparency kept; JPEG, PNG or WEBP output
- A public download link for every upscaled file, with input and output dimensions
- Standard size: inputs up to about 0.3 megapixels, output up to 2560x1920 at 4x
- Large mode (
allowLargeImages): inputs up to about 2.1 MP (1920x1080), output up to 7680x4320
Who it's for
Built for
Example
Input and output
One dataset row per result, downloadable as JSON, CSV or Excel, or read through the Apify API.
{
"imageUrls": ["https://example.com/product-small.jpg"],
"scale": "4",
"model": "general",
"outputFormat": "png"
}From a real cloud run with allowLargeImages on, shortened; the 960x431 input is above 0.3 MP, so it was upscaled at full size and charged as a large image.
{
"imageUrl": "https://upload.wikimedia.org/.../960px-Fronalpstock_big.jpg",
"outputUrl": "https://api.apify.com/v2/key-value-stores/.../records/0000-960px-Fronalpstock_big-x4.jpg",
"model": "general",
"scale": 4,
"width": 960,
"height": 431,
"outputWidth": 3840,
"outputHeight": 1724,
"tier": "large",
"hasTransparency": false,
"inferenceMs": 15684,
"chargedAs": "large-image-upscaled",
"error": null
}Pricing
Pay per result. Failures are free.
No subscription, no monthly minimum. Apify platform compute is included in the price; Apify also adds a tiny start fee per run ($0.00005 per GB of run memory).
| You run | You pay |
|---|---|
| 100 product photos, standard size | $1.00 |
| 1,000 standard images | $10.00 |
| 20 full-HD images, large mode | $1.20 |
6 failed downloads = $0.00
Not charged:
- Failed downloads and unreadable files
- Images refused because they are already bigger than the result would be
- Links from social networks and stock-photo sites, which are refused on purpose
Without allowLargeImages, bigger inputs are first reduced to about 0.3 MP and charged $0.01. On the default 4 GB memory, a standard image takes about 12 seconds and a full 1920x1080 input about 80 seconds. You can set Maximum cost per run in the run options and the actor stops cleanly when it is reached.
FAQ
Questions
How good is it?
Real-ESRGAN is the reference open-source upscaler used by many desktop and web tools. It recovers edges and textures and removes compression noise; it does not invent faces or text that were never there. Tiny text and faces benefit less than landscapes, products and art.
Which model should I pick?
general for photos, product shots, screenshots and scans; anime for anything drawn: anime, cartoons, comics, game art, logos and line art.
Is my image stored anywhere else?
No. It is downloaded by the run, processed inside the actor and saved only in your own run storage.
Which images can I use?
Any direct image link you have the right to process. Links from social networks and stock-photo sites are refused.
Try AI Image Upscaler on Apify
Apify's free plan includes monthly platform credit you can use to try it. Also callable from AI assistants through the Kanto Labs MCP server.
Other Kanto Labs tools
Tech Stack Detector
CMS, ecommerce, analytics, frameworks, CDN and hosting for any list of domains.
Document to Markdown
PDF, DOCX, PPTX, XLSX, EPUB and HTML to clean Markdown with RAG chunks.
Website SEO Audit
0-100 score and a prioritized fix list per page, broken links and AI crawler checks.