Projects sharing features with Gifify

Bilive is a multimodal AI video pipeline and live stream recording tool designed to capture real-time broadcasts and automate the creation of highlight clips. It functions as a multi-platform stream orchestrator capable of distributing looped pre-recorded content and managing the automated upload of processed video clips to various destinations. The system distinguishes itself through AI-driven content generation, using comment density to detect high-energy segments and multimodal models to automatically produce descriptive titles and synchronized subtitles. It further utilizes image-to-image

PHP-FFmpeg is an object-oriented wrapper for executing FFmpeg binary commands within PHP applications. It serves as a multimedia processing library and toolkit for transcoding, clipping, merging, and filtering audio and video files through a standardized programmatic interface. The project provides specialized drivers for video manipulation, audio editing, and media metadata extraction. These drivers allow for the application of visual filters, the modification of audio sample rates, and the probing of multimedia files to retrieve technical specifications and validate file integrity. The lib

mmaction2 is a PyTorch video understanding toolbox designed for training and evaluating deep learning models. It serves as a framework for action recognition, temporal localization, and spatio-temporal action detection, providing specialized tools for both pixel-based video analysis and skeleton-based action recognition. The project distinguishes itself through a modular architecture featuring registry-based component discovery and hierarchical, config-driven model assembly. It supports multi-modal feature fusion, integrating RGB frames, optical flow, and audio, and includes capabilities for

ffmpeg-python is a Python wrapper that translates programmatic method calls into command-line arguments for executing FFmpeg media processing tasks. It functions as a multimedia transcoding interface and a media stream capture tool, allowing for the recording of live audio and video from hardware devices and network sources. The library features a fluent interface for constructing complex directed graphs of audio and video filters through method chaining. It also includes an FFprobe metadata extractor that retrieves structured technical properties from media files and returns them as Python d

Gifski is a native macOS desktop application and video processing utility designed to convert video files into high-quality animated GIFs. It functions as a video-to-GIF converter that allows for the adjustment of frame rates and dimensions to balance visual fidelity with file size. The tool features capabilities for animation loop generation, including the creation of bounce effects by reversing video playback. It employs palette-based color quantization and error-diffusion dithering to maintain color accuracy and reduce banding in the final output. The application integrates with macOS sys

This project is a content-addressable digital archive and historical text digitization tool. It provides a system for storing and retrieving verified historical texts, replacing low-quality image scans with human-verified text overlays to improve reading accuracy and accessibility. The archive utilizes cryptographic hashes for content-addressing to ensure data integrity and verification of historical documents. It employs a local-first storage model, keeping digitized texts on the device for offline availability and fast access. The system organizes book titles and page references through a

gifski-app is a native macOS desktop application used to convert video files into high-quality animated GIFs. It functions as both a standalone tool and a macOS system extension, allowing for the transformation of media files into animations with configurable dimensions, frame rates, and looping options. The application includes a specialized bounce animation generator that creates yo-yo effect images, which play forward and then backward in a continuous loop. Integration with the macOS ecosystem enables conversion directly from the system share menu within other applications. The software a

This project is an AI-driven suite of tools designed to repurpose long-form video content into short-form clips. It integrates a speech-to-text engine for automated transcription, a highlighting system that ranks engaging segments based on emotional hooks, and a video processor that converts horizontal footage into vertical formats. The system distinguishes itself through intelligent video cropping that utilizes face tracking and motion smoothing to keep subjects centered. It also employs an analysis system to extract viral highlights by scoring segments for engagement and practical value. T

FunClip is an open-source tool that transcribes speech from video files and clips segments based on text, speaker, or AI analysis. It combines speech recognition with speaker diarization, audio event detection, and visual content understanding to identify and extract relevant portions of a video. The tool distinguishes itself through several integrated capabilities. It supports hotword-weighted speech recognition, which improves transcription accuracy for specific terms like names or jargon by boosting their probability during decoding. A large language model can interpret the transcribed tex

AI-Media2Doc is a self-hosted media transcription and content repurposing platform. It converts audio and video files into structured documents, searchable transcripts, and notes using a local speech-to-text pipeline and language model integration. The system enables the creation of illustrated articles by extracting video frames based on subtitle timestamps. Users can control the style and structure of generated text through custom behavioral prompts and integrate external language models via configurable API endpoints. The platform covers automated speech transcription, multimedia content

Headtrackr is a JavaScript library and computer vision face tracker designed to monitor head position and orientation via a webcam. It provides a head tracking API that detects face location and spatial coordinates within a live video stream to create head-coupled perspective effects. The project functions as a tool for shifting 3D rendering perspectives in real time based on physical head movements. It utilizes WebRTC and media stream integration to capture video data and identify a user's face and rotation within a web browser. The library covers computer vision capabilities for face and h

PySceneDetect is a suite of tools for identifying cuts and transitions in video files using content, threshold, and histogram detection algorithms. It functions as a scene detector, frame extractor, statistics analyzer, metadata exporter, and video scene splitter. The project identifies scene boundaries and can divide video files into smaller clips using external processing tools. It allows for the extraction of representative image frames from detected changes and the export of scene lists into industry-standard formats such as EDL, FCP, HTML, OTIO, and CSV. The toolset includes capabilitie

Video analyzer is a toolkit that processes video files through computer vision and automatic speech recognition to produce structured JSON data and natural language summaries. The system extracts visual frames, samples key moments based on pixel differences, and transcribes soundtrack audio into written text to generate comprehensive descriptions across chronological timelines. The software coordinates sequential processing stages that combine frame-by-frame visual analysis with audio transcripts using local or cloud AI models. It supports adaptive and uniform frame sampling, hardware-accele

SmartSub is a cross-platform desktop application for AI-driven video transcription and subtitle generation. It converts audio and video files into text subtitles using local AI models and incorporates hardware acceleration to increase processing speed. The tool features a subtitle translator that leverages large language models, such as OpenAI and DeepSeek, to convert subtitles between different languages. It includes a visual editor for proofreading and polishing transcribed text, paired with a video preview for frame-accurate synchronization. The software supports batch processing of multi

PhotoEditor is an image editing library and canvas-based photo editor designed for in-app image manipulation. It serves as a toolkit for applying filters, text, stickers, and freehand drawing to images, functioning as both a bitmap image processor and a digital photo annotation tool. The project enables the creation of social media style stories by allowing users to add emojis, text, and stickers to photos. It supports non-destructive image manipulation, allowing users to remove elements or revert changes before exporting the final composition. The library covers a broad range of capabilitie

This project is an AI video post-production suite that uses large language models and programmatic tools to automate editing, transcription, and subtitle generation. It functions as an AI editing agent that translates natural language instructions into shell commands, providing a programmatic interface for manipulating media via FFmpeg. The toolkit includes a motion graphics engine that generates technical animations and visual overlays through code-driven rendering and mathematical definitions. It distinguishes itself by combining an AI-powered transcriber for word-level timestamps with an a

Editly is a headless, programmatic video engine and automated assembler. It functions as a declarative video editor that generates MP4 and GIF exports from structured data or code, removing the need for a manual graphical user interface. The system is distinguished by its ability to integrate GLSL fragment shaders as visual layers within a programmatic timeline. It uses a configuration-based model to define clips, layers, and audio tracks, allowing for reproducible video assembly and the generation of custom programmatic graphics. The engine covers a broad range of media production capabilit

gif.js is a JavaScript GIF encoder and client-side color quantizer that generates animated GIF files directly within the web browser. It functions as an HTML5 canvas exporter and image processor, allowing for the creation of animated images from web sources without the need for a backend server. The library utilizes web workers to offload heavy image encoding tasks to background threads, which prevents the browser user interface from freezing during the generation process. This architecture enables the tool to act as a web worker image processor for dynamic image generation. The system cover

This project is a cross-platform implementation of the WebRTC standard, providing a comprehensive library for building real-time audio, video, and data communication applications. It functions as a peer-to-peer networking framework and media processing engine, enabling direct, low-latency connections between devices without relying on central servers. By strictly adhering to official protocol specifications, the library ensures interoperability with browsers and other native communication software across mobile, desktop, and server environments. The engine distinguishes itself through a modul

Jimp is a zero-dependency JavaScript image processing library and programmatic editor designed for manipulating, resizing, and filtering images in Node.js. It functions as a multi-format image encoder and extensible pipeline that operates entirely in JavaScript to ensure portable deployment across different environments without requiring native system dependencies. The engine features a modular architecture that allows for custom image processor builds and the registration of custom processing plugins. This extensibility enables the addition of specific visual effects and custom file-type enc

Kdenlive is an open-source non-linear video editing suite designed for digital video post-production. Built on the MLT Framework and utilizing KDE Frameworks for its user interface, it provides a multi-track environment for assembling clips, applying transitions, and rendering final video files. The editor distinguishes itself through a comprehensive set of animation and effect tools, including keyframe-based parameter animation with a visual curve editor for fine-tuning transitions. It supports advanced visual modifications such as clip speed remapping, effect region masking, and the integra

Rope is a graphical user interface for swapping faces in images and videos. It functions as a deepfake video editor and image face swapper that utilizes pre-trained deep learning models to replace identities in visual media. The tool includes specialized capabilities for AI video post-production, such as occlusion-aware blending to handle foreground objects and mouth-parsing refinement to align facial expressions. It also serves as an AI face restoration tool, using saliency-based restoration to recover clarity and sharpness in swapped facial regions. The software provides a pipeline for vis

openMVS is a multi-view stereo library and photogrammetry pipeline used for 3D scene reconstruction. It transforms Structure from Motion data—specifically camera poses and sparse point clouds—into detailed 3D models consisting of dense point clouds and textured meshes. The project provides a sequence of processing stages to densify point clouds, generate 3D surface meshes, and apply photorealistic textures. It uses multi-view texture blending to map accurate colors onto reconstructed geometry and employs iterative refinement to optimize mesh details. The system includes capabilities for impo

This project is a neural style transfer framework that provides a suite of computer vision tools for applying artistic styles to images and video. It functions as a system for training feedforward neural networks, an iterative style optimizer, and a real-time video stylizer. The framework supports two primary methods of stylization: a feedforward model that applies styles in a single pass and an iterative optimization method that generates stylized images by minimizing content and style loss without a pre-trained model. It also enables real-time processing of live webcam feeds using trained m

Imaginary is a self-hosted HTTP server for image processing that applies transformations like resizing, cropping, rotating, and format conversion through URL parameters. It operates as a stateless request-response pipeline, processing images fetched from remote URLs or served from a local directory without requiring client-side dependencies. The server distinguishes itself through its security and access control capabilities, offering optional API key validation, HMAC-signed URL verification, and remote origin whitelisting to restrict which image sources are permitted. It also provides a heal

Licecap is an animated GIF capture utility designed to record desktop screen activity and export the results as portable GIF image files. It functions as a screen recorder that allows users to capture a selected area of the screen and save the recording as a short animation. The tool includes a selection overlay for defining the recording area via mouse interactions and utilizes palette-based encoding to compress captured frames into a single looped GIF file. It integrates with Windows and macOS APIs to manage screen capture permissions and window positioning. The application covers a range