atlury

atlury.github.io

ATMx

Revolutionizing Interactions, Redefining Possibilities! 🚀

audio-recorder

Free, Simple Audio Recorder App for Android!

automotive-configurator

A web demo app for configuring the visual look of a retail car using WebGL rendering. The project was created using ThreeJS WebGL library with model formats in glTF.

camera-samples

Multiple samples showing the best practices in camera APIs on Android.

epaper-slow-generative-art

examples

TensorFlow examples

Fooocus-MRE

Focus on prompting and generating

GCVit

[ICML 2023] Official PyTorch implementation of Global Context Vision Transformers

gesture-classify

GestureCam

Android camera app which provides gesture recognition for image capture.

gesturecam-legacy

gesturecam-workflow-enabled

GhostFaceNets

GSOC-23

Journey Book of Google SoC'23

HathiTrust-downloader

Small and simple command line tool to automate downloading pages from HathiTrust

HomeBrewLiveStreamer

A customizable, roll-your-own solution for live A/V recording to your Android device or for live media streaming.

mediapipe

Cross-platform, customizable ML solutions for live and streaming media.

mediapipe-google-samples

mediapipemultihandstrackingapp

Gesture recognition through mediapipe

nanoowl

A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.

noScribe

Cutting edge AI technology for automated audio transcription. A nice GUI for OpenAIs Whisper and pyannote (speaker identification)

OnnxStream

Stable Diffusion XL 1.0 Base on a Raspberry Pi Zero 2 (or in 298MB of RAM)

receiverapp

samba-ad-dc

🐳 Docker Image of Samba Domain Controller Compiled From Source

samba-ad-dc-integrated-services

Integración de proxy, correo y jabber con Samba AD DC

voltaML-fast-stable-diffusion

Beautiful Stable Diffusion API and UI with support for AITemplate acceleration

webgi-jewelry

Jewelry project using threejs and webgi

WhisperInput

Offline voice input panel & keyboard with punctuation for Android.

Wuerstchen

Official implementation of Würstchen: Efficient Pretraining of Text-to-Image Models