Skip to main content
Glama

Upscale images with AI (coming soon)

upscale_image
Read-only

Upscale images 2x or 4x using Real-ESRGAN to sharpen edges and reduce blur/JPEG noise. Returns a public download URL, making small photos, thumbnails, or artwork ready for print, store, or OCR.

Instructions

COMING SOON: this Kanto Labs actor is not public on the Apify Store yet. Until it is, calls return an 'actor not yet public' error and nothing is charged. Enlarge images 2x or 4x with Real-ESRGAN, the open-source AI super-resolution model, run inside the actor (no third-party AI API): sharper edges and textures, less blur and JPEG noise than a normal resize. Two models: "general" for photos, product shots, screenshots and scans; "anime" for anime, cartoons, illustrations, logos and line art. Transparency is kept. Returns a public download URL for each upscaled file with input and output dimensions. Use it to make small product photos, thumbnails or artwork print- or store-ready, or to enlarge small text before OCR. Inputs up to about 0.3 megapixels (640x480) are standard price (output up to 2560x1920 at 4x); bigger inputs are reduced to that size unless allowLargeImages is true, which upscales inputs up to about 2.1 MP (1920x1080) at full size at the large price. Upscaling takes about 12 s per standard image and about 80 s per large one, and a call must finish within 300 s, so send at most about 15 standard or 3 large images per call. Only images you have the right to process; social-network and stock-photo links are refused. Cost: $0.01 per image upscaled, $0.06 per large image, billed to your Apify account; failed or refused images are free. Runs the Apify actor kantolabs/ai-image-upscaler with your APIFY_TOKEN; maxTotalChargeUsd caps the spend per call.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNo"general" (default) for photos and real-world images; "anime" for anime, cartoons, illustrations and line art.
scaleNoUpscale factor, "4" (default) or "2". Same price.
qualityNoJPEG / WEBP quality. Default 95.
imageUrlsYesDirect links to images (JPEG, PNG, WEBP, GIF first frame, BMP, TIFF; up to 40 MB), e.g. ["https://example.com/product-small.jpg"].
timeoutSecsNoGive up after this many seconds (max 300, Apify's limit for synchronous runs). Default 280. For big batches, split the input into several calls.
outputFormatNo"jpeg" (default, smallest for photos), "png" (lossless, keeps transparency) or "webp" (small, keeps transparency).
allowLargeImagesNoUpscale inputs up to ~2.1 MP at full size and charge the large price ($0.06). Default false: bigger inputs are first reduced to ~0.3 MP and charged $0.01.
maxTotalChargeUsdNoHard spending cap for this call in USD, enforced by Apify: the run stops once it has charged this much. Default 1 (server setting KANTO_MAX_CHARGE_USD).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.2.0

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds substantial behavioral context beyond the annotations: the actor is currently non-public and returns an error, pricing per image, call duration limits, max batch sizes, output URL details, transparency handling, and the APIFY_TOKEN requirement. This fully compensates for the lack of output schema and aligns with the non-destructive readOnlyHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but dense, with the 'coming soon' caveat front-loaded before the core functionality. Every section earns its place: purpose, model choice, output behavior, pricing, limits, and constraints. It is not minimal, but the complexity of the tool justifies the length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter tool with no output schema, the description is remarkably complete. It covers current unavailability, cost, failure behavior, timeout constraints, input restrictions, output format, and return shape (public download URLs with dimensions). An agent has enough context to decide whether and how to invoke it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

While schema coverage is 100%, the description adds meaningful semantics beyond individual parameter descriptions: standard vs large pricing, input megapixel thresholds, output dimensions at 4x, and guidance on batching (15 standard or 3 large images). Not every parameter is explained in the prose, but the key operational implications are covered.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Enlarge images 2x or 4x with Real-ESRGAN...' and explains the effect (sharper edges, less blur and JPEG noise). It also distinguishes two model variants and output behavior, so an agent can clearly tell what this tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit use cases: 'make small product photos, thumbnails or artwork print- or store-ready, or to enlarge small text before OCR.' It also explains when larger inputs require allowLargeImages and notes that social-network and stock-photo links are refused, giving clear context without explicitly naming alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.