Skip to content
Project categories

Creative & Media · GitHub

Make, edit, and manage images, video, and audio.

Useful GitHub projects

10,829 projects

NextStep-1

stepfun-ai

696stars
NextStep-1 preview

[🚀 ICLR 2026 Oral] NextStep-1: SOTA Autogressive Image Generation with Continuous Tokens. A research project developed by the StepFun’s Multimodal Intelligence team.

Creative & MediaPythonApache-2.0GitHub

Step-Audio2

stepfun-ai

1,529stars
Step-Audio2 preview

Step-Audio 2 is an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation.

Creative & MediaPythonApache-2.0GitHub

StereoKit

StereoKit

1,093stars
StereoKit preview

An easy-to-use XR engine for building AR and VR applications with C# and OpenXR!

  • Mixed Reality inputs like hands and eyes are trivial to access
  • Easy and powerful UI and interactions

dummy

sterrasec

69stars
dummy preview

Generator of static files(csv, jpeg, png, pdf) for testing file upload. It can generate csv and png files of any number of bytes!

YouTube-Music

steve228uk

2,801stars
YouTube-Music preview

:musical_note: A Mac app wrapper for music.youtube.com

  • Keyboard shortcuts
  • "Now Playing" Notification Center widget

loki

SteveCastle

87stars
loki preview

A minimalist web native image viewer, curation and tagging tool, and media server.

  • Fast. Opens enormous folders without hanging. Renders 4K videos and high-res images without stutter. Developed against a working library of 2 million+ media items and 5 million+ tag assignments.
  • Local-first. Your media stays where you put it. Tags live in a SQLite database in your home directory that you own and can back up. Nothing syncs anywhere, and there's no account.

Pangolin

stevenlovegrove

2,758stars

Pangolin is a lightweight portable rapid development library for managing OpenGL display / interaction and abstracting video input.

  • Build for Windows, Linux, OSX and the Web (with Emscripten)
  • Support different windowing implementations including off-screen buffers

raspberry_ninja

steveseguin

201stars
raspberry_ninja preview

Publish or capture VDO.Ninja streams with Python (Raspberry Pi, Linux, Mac, Windows WSL)

  • Single Stream Recording: Record any VDO.Ninja stream to disk
  • Room Recording: Automatically record all participants in a room

bytebeat-composer

SthephanShinkufag

159stars
bytebeat-composer preview

Bytebeat player with a collection of many formulas from around the internet.

  • Interactive Timeline Cursor: Renders a moving playback cursor that you can color-customize. At high zoom levels, it moves faster and stops being displayed.
  • Stereo Channel Splitting: Renders left and right audio channels using distinct colors, with multiple color preset configurations available.

stipple-effect

stipple-effect

622stars
stipple-effect preview

Stipple Effect is a pixel art editor that supports animation and scripting (available on Windows, macOS and Linux)

  • Linked-cel layers (contents persist across frames)
  • Two-color system: Stipple Effect's brush, pencil, and gradient tool allow for interesting combinations of the primary and secondary colors
58stars
fretwise-listener preview

Real-Time Guitar Note Recognition Trainer App 2026: Learn Fretboard Pitch Detection

  • 🎧 Real-time pitch detection from microphone or audio interface input
  • 🎼 Automatic string and fret inference based on detected fundamental frequency