[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Scalable and memory-optimized training of diffusion models

Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling

[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning.

A playbook for systematically maximizing the performance of deep learning models.

Towards Human-Sounding Speech

A Conversational Speech Generation Model

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Browser extension to add git graph to GitHub website.

Zettelkasten environment for productive people

Simple frontend for LLMs built in react-native.

LLM2CLIP significantly improves already state-of-the-art CLIP models.

Erasing Concepts from Diffusion Models

Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

Autonomous agents for everyone

[ICCV 2025 Highlight] OminiControl: Minimal and Universal Control for Diffusion Transformer

aider is AI pair programming in your terminal

Development repository for the Triton language and compiler

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Visual Studio Code

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

🌀 R2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding (ECCV 2024)

A personal knowledge management and sharing system for VSCode

ControlNet++: All-in-one ControlNet for image generations and editing!

Omnivore is a complete, open source read-it-later solution for people who like reading.

Official pytorch repository for CG-DETR "Correlation-guided Query-Dependency Calibration in Video Representation Learning for Temporal Grounding"