Tag: image-processing
Batch Screenshot Text and UI Extraction
Extract text, UI elements, and data tables from up to 500 screenshots in a single API call. The service uses a flat-fee USDC payment model via the x402 protocol.
Extract Structured Data from Invoice Images
This tool converts invoice or receipt images into structured JSON data, extracting key fields such as vendor details, line items, and totals. It utilizes local AI vision, eliminating the need for cloud uploads or external API keys.
Batch WCAG Alt Text Generation for Images
This tool facilitates the batch generation of WCAG-compliant alt text and descriptions for up to 500 image URLs via a single API call. It accepts an array of image links and an optional shared context to ensure consistent, high-quality meta…
image-to-retail-asset-pipeline-studio
This comprehensive tool executes a 10-stage creative pipeline, transforming a single image into a complete set of print-ready assets. It handles everything from background removal and colour palette extraction to CMYK conversion, SVG vector…
High-Performance Node.js Image Processing Utility
This module provides high-performance image processing capabilities for Node.js. It is optimised for resizing and manipulating various formats including JPEG, PNG, WebP, GIF, AVIF, and TIFF.
Raster to SVG Vectorization Pipeline
Converts raster images to SVG using Recraft, vtracer, or potrace-based pipelines. It includes automated path-count validation and SVGO optimisation to ensure production-ready vector assets.
Generating Assets with True RGBA Transparency
Provides a robust workflow for generating assets with true RGBA transparency, utilising native-RGBA providers or post-processing matting models like BiRefNet. It includes validation logic to detect and prevent common failures such as checke…
Vectorize Raster Images to SVG
This utility converts raster images into scalable SVG format using multiple paths, including high-quality hosted APIs and local binaries like vtracer and potrace. It supports multi-color and single-color inputs, optimising the output with S…
Production-Grade Logo Generation and Vectorization
This skill generates comprehensive brand marks, providing master PNG, optimized SVG vector, and monochrome variants. It employs advanced model routing and multi-stage post-processing pipelines to ensure reliable wordmark integration and hig…
Automated asset failure diagnosis and repair
This skill diagnoses asset generation failures by mapping specific validation codes (e.g., checkerboard, palette drift) to concrete repair primitives. It systematically applies fixes like inpainting, matte extraction, or route changes, resp…
Multi-Path Raster to SVG Vectorization Tool
This utility provides multiple pipelines for converting raster images to scalable vector graphics (SVG), offering options from high-quality hosted services (Recraft) to local, specialized binary tracers like vtracer and potrace. It includes…
Automated production-grade logo generation
Automates the generation of production-ready logos by routing prompts to optimal models based on text complexity and performing post-processing for SVG vectorisation and monochrome variants.
Convert raster images to scalable SVG vectors
This skill provides multiple pipelines for converting raster images to SVG, offering options for high-quality commercial vectorization, multi-color local tracing, or single-bit icon conversion. It includes advanced post-processing steps lik…
Generating True RGBA Transparent Assets
A pipeline for generating high-quality RGBA-transparent assets using native-alpha providers or post-process matting models. It includes validation logic to detect and prevent common issues such as checkerboard artifacts or opaque background…
Raster to SVG Vectorisation Pipeline
Converts raster images to optimised SVGs using Recraft, vtracer, or potrace pathways. It incorporates automated quality validation via path count analysis and SVGO-driven optimisation.
Generating Assets with True RGBA Transparency
Implements a hierarchical workflow to produce RGBA-transparent assets from text-to-image models, overcoming checkerboard artifacts and flat backgrounds using native-RGBA providers, matting models, and automated alpha validation.
Systematic Asset Generation Failure Diagnosis and Repair
This skill diagnoses asset generation failures by mapping specific failure codes (e.g., checkerboard, palette drift) to appropriate repair primitives. It executes a systematic, budget-aware pipeline, preferring deterministic fixes over cost…
Immich Photo Duplicate Analysis Skill
This skill analyses Immich photo libraries using perceptual hashing to identify visually identical images across different import sources, even when re-encoding has altered file checksums. It generates detailed reports and provides recommen…
Automated Ad Creative Generation and Formatting
Automates the generation of multi-platform ad creatives, including display images, video processing, and copy variations for A/B testing. It handles resizing and formatting for platforms such as Google Ads, Meta, and LinkedIn.
Slack Animated GIF Creator Toolkit
A toolkit for generating animated GIFs optimised for Slack, providing utilities for frame assembly, easing functions, and validation. It leverages PIL to implement various animation concepts like pulsing, bouncing, and rotating.
Slack-optimized animated GIF creation toolkit
A comprehensive utility suite for generating and optimizing animated GIFs specifically for Slack. It provides frame building, advanced animation concepts (e.g., easing, pulsing), and validation tools to ensure compliance with platform dimen…