Media & Images - GitHub Trending Knowledge Graph
GitRank indexes and ranks trending Media & Images repositories on GitHub for the This week period. Covering 100 monitored repositories, updated every 6 hours with verified net stars gained.
Media & Images
Video · Images · Voice & Audio100 tracked reposVideo editing, image tools, audio and photo libraries
A fully local open-source voice studio for cloning, dubbing, transcription and audiobook creation across 646 languages.
An offline file converter that handles 263 formats by drag and drop, with no uploads or Office needed.
A Chinese-localized AI pose reference gallery with 2,878 images, built as a zero-dependency static site.
Turn plain HTML into rendered video with GSAP animation and ffmpeg, built for AI agents.
AI turns documents or topics into native PowerPoint decks with animations, charts, narration, and custom templates.
Collection of 232 code-driven pixel art visual effects paired with a Claude Code skill for creating custom game animations.
Open-source agentic video production system that turns your AI coding assistant into a full studio with 12 pipelines and 100+ tools.
Local-first voice dictation for macOS. Hold a shortcut, speak, and paste into any app. Native Rust, on-device speech recognition, and a Linux beta.
A code-based film style toolbox with 66 ready-made style prompts and custom ones, no video model needed.
An open-source photo editor written from scratch in pure Rust, useful for studying image processing and desktop GUI work.
Free offline speech-to-text desktop app built with Tauri and Rust, cross-platform and extensible, no cloud dependency.
Turns ordinary WiFi signals into pose estimation, vital-sign monitoring, and presence detection without any camera.
An AI video skill for Claude Code and Codex that builds editable product promos in Remotion, with 124 shot recipe cards and editing export.
Create videos programmatically with React components, useful for data-driven or batch video production.
A feature-rich command-line audio/video downloader, the actively maintained youtube-dl fork.
A free, local-first, cross-platform video editor that replaces CapCut and is scriptable via JSON-RPC and MCP.
Generates HD short videos from a topic or keyword using an automated AI workflow.
Open-source IELTS vocabulary app with 7,298 illustrated words, UK/US audio, and FSRS spaced repetition.
An open-source document parsing model using an RSI loop in post-training for state-of-the-art accuracy and speed.
A local-first, self-hostable video metadata scraper and media manager for organizing personal video libraries.
Baidu's open-source OCR project parses long documents in one shot for document recognition.
AI agents clone a viral video's entire workflow—face, script, and B-roll—then generate 100 variants in one command.
Removes Suno, Udio and neural audio watermarks using ISO 226 perceptual masking to defeat forensic attribution.
Brings local Wallpaper Engine wallpapers into a DSH web UI with real-time WebGL rendering.
A node-based GUI and backend for diffusion models, offering fast local inference and modular workflows.
Android camera app that turns fast motion into a single stroboscopic photo using on-device computer vision.
Wraps 42 FFmpeg tools into an MCP server so coding agents can edit video locally without cloud or API keys.
Local open-source video character swapping studio built on ComfyUI, MiniMax H3, and FLUX.3 relighting for one-click subject replacement.
Turns coding agents into video agents, with an editor to adjust whatever it generates.
A multi-platform scraper for posts and comments on Xiaohongshu, Douyin, Bilibili, Weibo, Tieba, and Zhihu.
Turns a freshly built project into a shareable launch video with one command.
Turns a reference image and prompt into replayable 3D scenes along a camera path, with browser previews of color, depth, and Gaussian splats.
Claude Code skill that reverse-engineers web animations frame by frame and verifies that the reconstructed motion matches the original.
Cross-platform open-source screen recorder with GPU acceleration, no watermarks or subscriptions, built for quickly capturing product demo videos.
FilmCraft: An open-source, nonlinear video editor written by scratch in pure Rust
Third-party desktop player for Hongguo short dramas on Windows/macOS, no Android emulator needed.
A transparent animated desktop pet installed with one command, supporting multiple instances and custom AI video assets.
Generates animation-ready stylized hair card meshes from a single image, skipping manual modeling and rigging.
Open-source AI tool for short dramas and motion comics: script, storyboard, characters, image and video generation in one self-hosted canvas workflow.
Creates Apple-style dimensional drawings of UI components for visual reference.
Turns a reference image into a code-only, animation-ready Three.js 3D model, saving manual modeling and tuning work.
End-to-end AI short video creation agent skill that automates topic planning, script storyboarding, and direct Jianying draft project export.
Real-time local webcam invisibility effects with clean virtual camera output, no recording or upload, for streaming and meetings.
Differentiable geometric computer vision library on PyTorch, offering image transforms, camera models and feature matching as neural network layers for spatial AI.
Blender plugin that lets any LLM control 3D scenes via MCP, so you can model and edit with natural language instead of menus.
Android app that parses cloud-drive share links and downloads files directly to your phone, skipping extra clients and membership limits.
Mirror and control your Android device from your computer with low latency, open source.
Turns a script into animated stickman videos with voiceover, captions and sound effects, automating faceless YouTube video production.
Turns a single illustration into an animated 2D mesh avatar, with a local editor and coding-agent help, saving manual rigging and animation work.
awesome-short-drama-skills is an active open-source project written in HTML.
Rust-based high-performance inference engine for LLMs and TTS, using Metal acceleration to speed up local model inference.
All-in-one local AI desktop studio bundling chat, image/video generation and a coding agent, no Docker, terminal or cloud needed.
A Kotlin YouTube Music client with a clean Apple Music-inspired interface, making it easy to browse and play music on Android.
Official inference codebase from Pika Labs for running the Pika H3 Flex joint video and audio generation model.
Create polished demo videos without editing skills. Mac/Windows/Linux
Native Windows video motion capture tool integrating FlowHMR and GVHMR with contact correction, humanoid retargeting, and FBX or VMD export.
Reconstruct editable Three.js rooms from iPhone LiDAR scans and photos, viewable directly in the browser.
Search inside documents, code, and even screenshots - instantly and locally. A free, open-source file launcher with OCR, semantic search, and MCP agent access.
Rootless Android call recorder using Shizuku, storing AES-256-GCM encrypted audio in a biometric-protected vault with auto-cleanup.
Open-source MCP tool giving coding agents ears to hear, review audio and generate sound; runs CPU-only.
Self-hosted PDF toolbox that merges, splits, converts, OCRs and edits files locally, so documents never leave your own server.
Open-source Android and Windows music player with discovery, synced lyrics, radio, and artwork—no ads or tracking.
GPU-powered video and image mosaic restoration tool with GUI and CLI; free core, paid supporter models.
Official GreenSock AI coding skills that teach agents best practices, timeline patterns, and plugin usage for GSAP web animations.
LightCraft: An open-source non-destructive photo editor written by scratch in pure Rust
Edit videos through coding agents, turning natural-language instructions into automated timeline edits without manual dragging.
MOSS-Image is a 5B-parameter text-to-image base model with accurate text rendering, layout control, and efficient fine-tuning.
Motion capture pipeline and skill that extracts 3D skeletal rigs from dual-view AI videos using DINOv2 joint tracking into GLB files.
A community-supported supercharged document management system: scan, index and archive all your documents
High-precision PDF and academic document parser to structured Markdown.
Cross-platform voice dictation app with local Whisper/Parakeet and BYOK cloud models, privacy-first for fast speech-to-text input.
OpenAI's general-purpose speech recognition model trained on 680k hours of weak supervision, robust multilingual transcription and translation out of the box.
Turns one idea into comic-drama plans, asset prompts, episode scripts, storyboards and video prompts across 21 genres.
hongguo-desktop-releases is an active open-source project written in Code.
Virtual whiteboard with a charming hand-drawn feel for architecture diagrams.
Generate and edit Excalidraw-style vector diagrams through natural-language chat, self-hosted, replacing manual drag-and-drop diagramming.
Curated 180 open-source skills and toolkits letting Claude Code and Codex agents generate video, sorted by type with security grades.
Agent skills for image, video, audio and 3D generation: model routing, cost preview, brand consistency via MCP, plus Blender/Maya/Unreal drivers.
Open-source OpusClip alternative that auto-extracts highlights from long videos into social-ready short clips.
Generative AI workflow that converts video clips into playable, interactive web mini-games.
Open-source studio interface for AI image and video generation featuring a unified prompt bar, per-model settings, and gallery.
Lightweight one-million-parameter OCR model running on CPU at 15x Tesseract speed while achieving accuracy comparable to billion-parameter vision models.
Lightweight OCR toolkit converting images and PDFs into structured data for LLMs, supporting 100+ languages and document parsing.
Local SIP telephone daemon for Apple Silicon Macs that pairs on-device speech and language models for automated voice calls.
Decomposes a single anime character image into separate hair, eye, and body layers for animation and editing.
Complete cross-platform multimedia framework to decode, encode, transcode, mux, demux, stream, filter, and play audio and video files.
Local GPU song generator with editable scores, vocals, covers and exact replay; native Windows installer, no Python required.
Open-source Loom alternative built with Rust and Tauri for capturing, editing, and instantly sharing studio-quality screen recordings.
Lets Claude watch any video by downloading, extracting frames and transcribing audio, then feeding everything to the model.
Procedural animation in any style for Claude Code: short single-file canvas videos with story, look and storyboard check-ins. 7 built-in styles or one matched from your references, your own music (beat-mapped), real product screenshots, every format from one piece.
Lightweight native third-party NetEase Cloud Music desktop client written in Go for fast startup and distraction-free music streaming.
AI agent skill that generates polished HTML slide decks featuring editorial and Swiss layouts, image prompts, and WebGL presentation playback.
