Browse skills

Generates captivating cover images for videos in a style inspired by classic Chinese literature and art.

Baoyu Xhs Images converts video segments into still images, useful for creating image galleries or extracting keyframes from videos.

Compress images using advanced AI techniques for smaller file sizes while preserving visual quality.

This skill provides detailed descriptions of images for visually impaired users, enhancing content accessibility and inclusivity.

This skill applies Three.js postprocessing effects to generated images, enhancing visuals and creating stunning artistic results.

Removes Gemini watermarks from images automatically, letting you use your creations freely and without restrictions.

Anti Render prevents unwanted rendering of images or media, safeguarding against potential exploits and ensuring secure content delivery.

Amazon Listing Images — provides AI agent assistance for software development workflows.

Generates favicons from images for your website, ensuring consistent branding across browsers and improving user recognition.

Automates visual inspection tasks using AI, identifying defects and inconsistencies in product images with high accuracy.

Official replicate skill for software development workflows.

Draw Io generates unique, surreal digital art images based on simple prompts – perfect for sparking creativity and quick visual ideas.

Automate containerized application deployment, management, and scaling using Docker images and registries.

Draw Io allows you to generate unique, abstract art images through simple interactive controls – a fun and easy way to create visuals!

Generate visually appealing recipe presentations—including images, descriptions, and steps—from ingredient lists and desired cuisine.

Analyzes images, audio, and text together to provide comprehensive insights and contextually relevant responses.

Generate images from text prompts using Google's Gemini model, offering creative visuals based on your descriptions.

This skill uses Blip 2's image understanding to generate detailed captions and descriptions from images, boosting accessibility and content creation.

Extracts images and associated data directly from Philips Watchman Red Book documentation using AI.

This skill uses Google Veo to generate realistic, high-quality images from text prompts, offering creative visual content quickly.

Organizes, catalogs, and tracks digital artifacts (images, documents, code) for efficient retrieval and version control.

This skill analyzes images to identify objects and patterns, offering insights for automation, analysis, and understanding visual data.

Githuman generates realistic human-like images from text prompts, enabling creative content generation and visual concept exploration.

Tamagui allows you to create interactive art and experiences by drawing directly onto images, offering a unique blend of digital and analog creativity.