🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

The agent engineering platform

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.5, DeepSeek, gpt-oss locally.

Rembg is a tool to remove images background

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

holehe allows you to check if the mail is used on different sites like twitter, instagram and will retrieve information on sites with the forgotten password function.

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

Toutatis is a tool that allows you to extract information from instagrams accounts such as e-mails, phone numbers and more

Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch

AudioLDM: Generate speech, sound effects, music and beyond, with text.

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

ignorant allows you to check if a phone number is used on different sites like snapchat, instagram.

[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"

An experiment in durability

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

OSINT tool to find breached emails, databases, pastes, and relevant information

Wav2Lip UHQ extension for Automatic1111

An advanced tool for email reconnaissance

+Jakarta Sans is a open-source fonts. Designed for Jakarta "City of collaboration" program in 2020.

Implementation of MusicLM, a text to music model published by Google Research, with a few modifications.

Official code of CVPR '23 paper "StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator"

[ECCV 2022 Oral] Code for "Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation"

Official implementation of the paper "IteraTeR: Understanding Iterative Revision from Human-Written Text" (ACL 2022)

COLING'24 Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attack

Watermarking Text Generated by Black-Box Language Models

Implementation for Machine-Generated Text Localization (ACL 2024 Findings)

[AAAI'24] ALISON: Fast and Effective Stylometric Authorship Obfuscation