Image Upscaling
- 575 installs
- 680 repo stars
- Updated August 3, 2026
- inference-sh/skills
image-upscaling is a Claude Code skill that upscales and enhances low-resolution or AI-generated images through the inference.sh CLI using Real-ESRGAN, Thera, Topaz, and FLUX Dev Upscaler models for developers who need h
About
image-upscaling is a belt/inference.sh CLI skill that enlarges and sharpens images from terminal-driven agent workflows. It routes jobs to four named upscaler backends—Real-ESRGAN, Thera (any input size), FLUX Dev Upscaler, and Topaz Image Upscaler—so developers can restore old photos, upscale AI art, or push assets toward HD/4K without leaving Bash. The skill expects the belt CLI (`npx skills add belt-sh/cli`) and triggers on phrases like upscale image, real esrgan, super resolution, and 4k upscale. Reach for image-upscaling when a coding agent must batch-enhance screenshots, generated art, or legacy assets as part of build or content automation rather than manual Photoshop work.
- Upscales images while preserving details and reducing artifacts
- Optimized for AI-generated content and illustrations
- Runs locally or via cloud inference endpoints
- Integrates directly with Claude, Cursor, and other agent workflows
- Supports batch processing for product assets and marketing visuals
Image Upscaling by the numbers
- 575 all-time installs (skills.sh)
- +12 installs in the week ending Aug 2, 2026 (Skillselion tracking)
- Ranked #377 of 1,335 Generative Media skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/inference-sh/skills --skill image-upscalingAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 575 |
|---|---|
| repo stars | ★ 680 |
| Last updated | August 3, 2026 |
| Repository | inference-sh/skills ↗ |
How do you upscale AI images from the CLI?
Automatically upscale and enhance AI-generated or low-resolution images inside their workflows.
Who is it for?
Developers automating image enhancement inside agent or CI workflows that already use the inference.sh belt CLI.
Skip if: Developers who need in-app GPU upscaling SDKs, real-time video super-resolution, or editing without installing belt/inference.sh.
When should I use this skill?
User asks to upscale, enhance, super-resolve, or increase resolution of images using inference.sh, Real-ESRGAN, Thera, Topaz, or FLUX upscalers.
What you get
Higher-resolution image files produced by Real-ESRGAN, Thera, Topaz, or FLUX Dev Upscaler via inference.sh belt commands.
- Upscaled PNG/JPEG image files
- CLI command recipes for batch upscaling
By the numbers
- Supports 4 upscaler models: Real-ESRGAN, Thera, FLUX Dev Upscaler, and Topaz Image Upscaler
Files
Install the belt CLI skill: npx skills add belt-sh/cliImage Upscaling
Upscale and enhance images via inference.sh CLI.
Quick Start
Requires inference.sh CLI (belt). Install instructionsbelt login
belt 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
belt app run falai/topaz-image-upscaler --input '{"image_url": "https://low-res-image.jpg"}'Workflow: Generate and Upscale
# 1. Generate image with FLUX Klein (fast)
belt app run falai/flux-2-klein-lora --input '{"prompt": "landscape painting"}' > image.json
# 2. Upscale the result
belt 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
# Full platform skill (all 250+ apps)
npx skills add inference-sh/skills@infsh-cli
# 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-removalBrowse all image apps: belt app store --category image
Documentation
- Running Apps - How to run apps via CLI
- Image Generation Example - Complete image workflow guide
- Apps Overview - Understanding the app ecosystem
Related skills
Remotion Best PracticesGet Remotion-specific coding guidance that prevents common video rendering mistakes when creating animated React videos.451k4.2k
Ai Video GenerationGenerate videos using 40+ AI models including Veo, Seedance, and others via inference.sh442k665Ai Image GenerationGenerate images using 50+ AI models including FLUX, Gemini, and Replicate via inference.sh441k665Ai Avatar VideoGenerate videos featuring AI avatars for product demos, tutorials, marketing, or explainers441k665Remotion RenderRender videos programmatically using React components and Remotion framework441k665
Remotion RenderGenerate high-quality MP4 videos from React code using Remotion inside an AI coding agent.363k665How it compares
Choose image-upscaling when terminal/agent automation with inference.sh is preferred over manual GUI editors or embedding upscalers directly in application code.
FAQ
Which upscaler models does image-upscaling support?
image-upscaling supports four inference.sh backends: Real-ESRGAN, Thera (any size), FLUX Dev Upscaler, and Topaz Image Upscaler. Developers pick the model that matches quality, speed, and input dimensions for their asset pipeline.
What CLI does image-upscaling require?
image-upscaling runs through the belt/inference.sh CLI. Install belt with `npx skills add belt-sh/cli`, then invoke upscaling via Bash(belt *) commands referenced in the skill triggers.