We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.
- diffusion-models
- high-resolution
- sparse-attention
- video-generation
47,133 repositories indexed
169–192 of 485 · Most stars
We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.
TagLib Audio Meta-Data Library
My curated list of audio DSP and plugin development resources (Github fork)
Self hosted file converter and compression tool for images, video, audio, json, excel and more. Supports over 3,000 conversions!
Python DSP module
Python CD-DA ripper preferring accuracy over speed
Open-source AI video replacement workflow by TEIN. Combine depth maps, SAM segmentation, face meshes, and audio processing to replace characters and objects with Seedance. Includes a local web UI to prepare inputs, review masks, preview generations, and export with original audio.
A curated list of awesome WebAudio packages and resources.
Beep is a JavaScript toolkit for building browser-based synthesizers.
Reads an audio file and displays the waveform
Kima Hub is built for music lovers who want the convenience of streaming services without sacrificing ownership of their library. Point it at your music collection, and Kima handles the rest: artist discovery, personalized playlists, podcast subscriptions, and seamless integration with tools you already use like Lidarr and Audiobookshelf.
:sound: Play and Record Sound with Python :snake:
Real-time audio streaming over the network.
SwiftySound is a simple library that lets you play sounds with a single line of code.
Tailor-made Pokémon themes for your Hyper terminal
.NET bindings for Direct3D12, Direct3D11, WIC, Direct2D1, XInput, XAudio, X3DAudio, DXC, Direct3D9 and DirectInput.
🅿️ PandoraPlayer is a lightweight music player for iOS, based on AudioKit and completely written in Swift.
🎤 a simple audio programming language implemented in JS
Band.js - Music composer interface for the Web Audio API.
TranslatedContent aggregation Android client: novels / short dramas / comic dramas / audiobooks / comics, Flutter UI + in-process Rust core, no self-hosted server, no root required
Webbased old-school Amiga music tracker in plain old javascript - Plays and edits Amiga Mod files and FastTracker XM files
Libav github mirror, clone of git://git.libav.org/libav
A simple C++ library for reading and writing audio files.
Audio processing by using pytorch 1D convolution network