home / skills / inference-sh / skills / image-upscaling

image-upscaling skill

safe

This skill upscales and enhances images using Real-ESRGAN and other upscalers via inference.sh, improving resolution for art, photos, and web images.

This is most likely a fork of the image-upscaling skill from openclaw

npx playbooks add skill inference-sh/skills --skill image-upscaling

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

2.5 KB

---
name: image-upscaling
description: "Upscale and enhance images with Real-ESRGAN, Thera, Topaz, FLUX Upscaler via inference.sh CLI. Models: Real-ESRGAN, Thera (any size), FLUX Dev Upscaler, Topaz Image Upscaler. Use for: enhance low-res images, upscale AI art, restore old photos, increase resolution. Triggers: upscale image, image upscaler, enhance image, increase resolution, real esrgan, ai upscale, super resolution, image enhancement, upscaling, enlarge image, higher resolution, 4k upscale, hd upscale"
allowed-tools: Bash(infsh *)
---

# Image Upscaling

Upscale and enhance images via [inference.sh](https://inference.sh) CLI.

![Image Upscaling](https://cloud.inference.sh/u/33sqbmzt3mrg2xxphnhw5g5ear/01k8d77p126y82zfecnt46hy4h.png)

## Quick Start

> Requires inference.sh CLI (`infsh`). Get installation instructions: `npx skills add inference-sh/skills@agent-tools`

```bash
infsh login

infsh app run infsh/real-esrgan --input '{"image_url": "https://your-image.jpg"}'
```


## Available Upscalers

| Model | App ID | Best For |
|-------|--------|----------|
| Topaz Image Upscaler | `falai/topaz-image-upscaler` | Professional quality, any image |

## Examples

### Upscale Any Image

```bash
infsh app run falai/topaz-image-upscaler --input '{"image_url": "https://low-res-image.jpg"}'
```

### Workflow: Generate and Upscale

```bash
# 1. Generate image with FLUX Klein (fast)
infsh app run falai/flux-2-klein-lora --input '{"prompt": "landscape painting"}' > image.json

# 2. Upscale the result
infsh app run falai/topaz-image-upscaler --input '{"image_url": "<url-from-step-1>"}'
```

## Use Cases

- **AI Art**: Upscale generated images for print
- **Old Photos**: Restore and enhance resolution
- **Web Images**: Prepare for high-DPI displays
- **Print**: Increase resolution for large prints
- **Thumbnails**: Create high-res versions

## Related Skills

```bash
# Full platform skill (all 150+ apps)
npx skills add inference-sh/skills@agent-tools

# Image generation (generate then upscale)
npx skills add inference-sh/skills@ai-image-generation

# FLUX models
npx skills add inference-sh/skills@flux-image

# Background removal
npx skills add inference-sh/skills@background-removal
```

Browse all image apps: `infsh app list --category image`

## Documentation

- [Running Apps](https://inference.sh/docs/apps/running) - How to run apps via CLI
- [Image Generation Example](https://inference.sh/docs/examples/image-generation) - Complete image workflow guide
- [Apps Overview](https://inference.sh/docs/apps/overview) - Understanding the app ecosystem

Overview

This skill provides command-line access to multiple AI upscalers (Real-ESRGAN, Thera, FLUX Dev Upscaler, Topaz Image Upscaler) via the inference.sh CLI. It lets you enhance low-resolution images, restore old photos, and prepare artwork or web images for high-DPI and print. Use simple infsh commands to run models and get upscaled outputs quickly.

How this skill works

The skill invokes preconfigured upscaler apps through the inference.sh CLI and returns enhanced image URLs or files. You supply an image URL or a generated image artifact; the chosen model (Real-ESRGAN, Thera, FLUX, or Topaz) performs super-resolution and artifact reduction. Outputs are ready for download or further processing in image pipelines.

When to use it

Upscaling AI-generated art for print or display
Restoring and increasing resolution of old or scanned photos
Preparing web images for high-DPI or retina displays
Converting thumbnails to higher-resolution variants
Generating 4K/HD versions of low-res images

Best practices

Choose Topaz for professional-quality upscales when fidelity matters
Use Real-ESRGAN or Thera for fast, general-purpose upscaling
Pass a stable, high-quality source URL to avoid amplifying compression artifacts
Run a small test crop before batch-processing many images to confirm settings
Combine upscaling with denoising or background-removal steps if needed

Example use cases

Upscale a generated image: infsh app run falai/topaz-image-upscaler --input '{"image_url":"https://example.com/image.jpg"}'
Generate then upscale: produce an image with a FLUX model, then feed its URL into the upscaler
Restore old photos: upload scan, run Real-ESRGAN or Topaz to recover detail for prints
Prepare site assets: batch upscale product thumbnails to serve high-DPI versions

FAQ

Which model gives the best quality?

Topaz Image Upscaler is targeted at professional-quality results; Real-ESRGAN and Thera are efficient and general-purpose alternatives.

How do I provide an image to upscale?

Provide a publicly accessible image URL to the CLI input JSON. You can also pipe or save generated output and pass its URL to the upscaler.