Image Upscaling
Skill Verified ActiveUpscale 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
To provide users with a straightforward way to enhance low-resolution images, upscale AI-generated art, and restore old photos with professional-grade AI upscaling technology.
Features
- Upscale and enhance images using Real-ESRGAN, Thera, and Topaz models
- Leverages the inference.sh CLI for model execution
- Supports various use cases including AI art, photo restoration, and high-DPI display preparation
- Provides clear installation and quick start guides
Use Cases
- Upscale AI art for higher resolution prints
- Restore and enhance the resolution of old photographs
- Prepare web images for high-DPI displays
- Increase the resolution of images for large print formats
Non-Goals
- Performing general image editing tasks like cropping or color correction
- Generating new images from scratch (though it can upscale generated images)
- Operating without the required inference.sh CLI ('belt') installed
Practical Utility
- info:Edge casesThe skill documentation does not explicitly list failure modes or recovery steps for edge cases such as malformed input or rate limits, though the quick start implies basic error handling via the CLI.
Documentation
- info:Configuration & parameter referenceWhile the example shows how to pass input parameters, there is no explicit documentation of all available options, defaults, or precedence for the `belt app run` command within the skill's documentation.
Versioning
- info:Release ManagementThe repository has a `pushedAt` date but no explicit versioning in the SKILL.md frontmatter or a CHANGELOG, and installation references `main`, making version pinning difficult.
Errors
- info:Actionable error messagesThe skill documentation does not explicitly detail error messages or remediation steps for potential failures during the image upscaling process.
Execution
- info:Pinned dependenciesThe skill itself does not have direct dependencies. The external `belt` CLI is referenced, but its specific versioning or pinning mechanism is not detailed within the skill's documentation.
Installation
npx skills add inferen-sh/skillsRuns the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.
Quality Score
VerifiedSimilar Extensions
Upscale Low Resolution Image
99Upscale a low-resolution image using AI super-resolution for print or high-DPI display.
AI Image Generation
97Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image
Openclaw
100Generate images and videos from text with multi-provider routing — supports GPT Image 2.0 (near-perfect text rendering), Nanobanana 2, Seedream 5.0, Midjourney V8.1 (unified photorealistic + anime), Flux 2 Klein (cheap drafts), Seedance 2.0 / Happyhorse 1.0 / Veo 3.1 video, and local ComfyUI workflows. Includes 1,446 curated prompts and style-aware prompt enhancement. Use when users want to create images/videos, design assets, animate photos, enhance prompts, or manage AI art workflows. NOT for: generic chat, code generation, document writing, video editing of existing footage, audio/TTS, or any task unrelated to AI image/video creation.
Watermark An Image
100Apply a text watermark to a photo using layer-based image composition for brand protection and copyright.
Image Transformation API
100Transform images with resize, crop, smart crop, upscale, remove background, and 20+ operations.
Baoyu Compress Image
100Compresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress image", "optimize image", "convert to webp", or reduce image file size.