Browse skills

This AI agent generates realistic, high-quality images based on "Canghe XHS" prompts, useful for creative visuals and concept art.

Automatically compress and resize images for web use, reducing file size without noticeable quality loss.

Generates captivating cover images tailored to your content using AI, perfect for social media and presentations.

Removes unwanted logos from images using Gemini AI, quickly enhancing visuals for branding or creative projects.

Generates high-quality, stylized fashion photography images featuring models in various poses and settings, perfect for marketing.

Quickly view rendered images of individual components from CivitAI models to understand their impact on results.

Generate short videos in dynamic manga/anime styles from text prompts or existing images using FreestyleFly's AI.

Automates building container images from a defined set of files and dependencies, streamlining deployment workflows for consistent environments.

Detects human body keypoints from images/video using Mediapipe, enabling applications like motion tracking and gesture recognition.

Seamlessly copies selected text/images to clipboard with a customizable hotkey for rapid sharing across applications.

This skill restores old or damaged photos using AI, bringing faded memories back to life and preserving precious images.

This skill generates layered visual effects for images, streamlining complex compositing and enhancing creative visuals quickly.

Creates diverse digital assets like images, code snippets, or text based on user prompts and specified styles.

This skill transforms text prompts into images mimicking various artistic styles, offering creative visual interpretations quickly and easily.

Combines microscopic banana images into novel textures and patterns based on user prompts.

Extracts text, tables, and images from PDF documents with high accuracy using advanced OCR and layout analysis.

Access, query, and analyze media assets (images, videos, audio) within a structured gtmagents database for efficient content management.

Extracts valuable data points, patterns, and insights from large collections of images using advanced AI analysis.

Solid Detection identifies and highlights stable, unmoving objects in images/videos, crucial for robotics, automation, and scene understanding.

Sirv Dynamic Imaging transforms images into optimized formats for web delivery, boosting site speed and reducing bandwidth usage.

Sharpens blurry images, reduces noise, and enhances details using advanced AI algorithms for clearer visuals.

Quickly identifies objects, text, and key visual elements within images or video frames.

Analyzes product images & descriptions to suggest optimal styling choices for enhanced online presentation.

This skill teaches you the fundamentals of Dockerfiles, enabling you to build and manage container images for consistent deployments.