Skip to content
Projektkategorien

Kreativität und Medien · GitHub

Entdecke Werkzeuge für Bilder, Video, Audio, Zeichnungen und 3D.

Nützliche GitHub-Projekte

10,484 Projekte
817Sterne

EasyQRCodeJS is a flexible QR code generator using JavaScript, supporting various drawing methods (Canvas, SVG, Table) and customization options. It's compatible with major frameworks and can be directly downloaded in the browser.

684Sterne

Display design token documentation generated from your stylesheets and icon files. Preview design token changes in the browser. Add your design tokens to your Storybook Docs pages using the custom Doc Blocks.

LANVP

VaanaCZ

555Sterne

L.A. Noire - V Patch | A community-made open source patch for the 2011's video game L.A. Noire containing a set of fixes like an unlocked framerate or support for custom aspect ratios.

ComChan

Vaishnav-Sabari-Girish

178Sterne
ComChan preview

A Blazingly Fast Minimal Serial Monitor with serial plottter TUI and more

  • BLE Support - Stream data wirelessly via Nordic UART Service (NUS).
  • Dual Monitor Side-by-Side View - View two serial ports simultaneously in a split-pane TUI with independent scrollbars and auto-split logging.

OVGGT

VAISR

59Sterne
OVGGT preview

[ECCV 2026] OVGGT is a training-free framework enabling streaming 3D reconstruction from arbitrarily long video with constant memory.

Valen

Valen-Team

914Sterne

Open, lightweight multimodal decision models for text, images, and video. Train and run them yourself.

32Sterne
GuitarRackCraft preview

Guitar LV2 host app for Android with X11 GUI support + experimental Windows VST plugin support

  • Chain multiple LV2 plugins with drag-and-drop reordering
  • Real-time audio processing with low-latency Oboe I/O

MIDI-3D

VAST-AI-Research

961Sterne
MIDI-3D preview

[CVPR 2025] MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

  • High Quality: It produces diverse 3D scenes at high quality with intricate shape.
  • High Generalizability: It generalizes to real image and stylized image inputs although trained only on synthetic data.