Kreativität und Medien · GitHub

PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud, CVPR 2019.

• Multiple GPUs for training
• GPU version rotated NMS

StableSwarmUI ist eine modulare Web-Benutzeroberfläche für Stable Diffusion, die den einfachen Zugriff auf leistungsstarke Werkzeuge, hohe Performance und Erweiterbarkeit in den Mittelpunkt stellt.

A simple powerful Discord music (multi-)bot built to fulfill your production desires. Easy to use, with no coding required.

• Production-ready, no coding required
• Request channel feature for seamless music experience

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

:strawberry: Strawberry Music Player

• Play and organize your music collection
• Support for WAV, FLAC, Ogg FLAC, WavPack, Ogg Vorbis, Opus, Ogg Speex, MPC, TrueAudio, AIFF, MP4/AAC, ALAC, MP3, ASF, Monkey’s Audio, and DSD (DSF/DSDIFF)

Synchronized viewing, theater, live streaming, video

• Synchronized room playback with real-time state updates.
• Media providers for Bilibili, Twitch, YouTube, Douyin, TikTok, Huya, Douyu, AcFun, CCTV, Alist, Cloudreve, Emby/Jellyfin, FNOS, QNAP, Synology, Nextcloud, Seafile, TrueNAS, direct URLs, and livestream sources.

Rtmp client on Android. Live Video Streaming.

WebGL map rendering engine for creative cartography

DEPRECATED - Memory efficient shimmering effect for Android applications by Supercharge.

V-Express aims to generate a talking head video under the control of a reference image, an audio, and a sequence of V-Kps images.

HunyuanVideo-1.5: A leading lightweight video generation model

• Video Super-Resolution Enhancement: We develop an efficient few-step super-resolution network that upscales outputs to 1080p. It enhances sharpness while correcting distortions, thereby refining details and overall visual texture.

Pseudo-3D shooter written completely in gawk using raycasting technique

An implementation of the Grammar of Graphics in R

[TMLR 2025] Latte: Latent Diffusion Transformer for Video Generation.

(Unity3D) Test multiplayer without building

• Test multiplayer gameplay without building the project
• GUI tools for managing all project clones

Video.js plugin for supporting the MPEG-DASH playback through a video.js player

vokoscreenNG is a powerful screencast creator in many languages to record the screen, an area or a window. Recording of audio from multiple sources is supported. With the built-in camera support, you can make your video more personal. Other tools such as systray, magnifying glass, countdown, timer, Showclick and Halo support will help