OneDiff: An out-of-the-box acceleration library for diffusion models.

A Direct-to-Driver open mobility platform powering the next-generation of mobility applications in India.

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

The official repository for paper "Tora: Trajectory-oriented Diffusion Transformer for Video Generation"

The Memory layer for your AI apps

Code of Pyramidal Flow Matching for Efficient Video Generative Modeling

[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

Cog inference for flux models

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Clarity AI | AI Image Upscaler & Enhancer - free and open-source Magnific Alternative

This is the repo for our new project Highly Accurate Dichotomous Image Segmentation

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation

Auto_Jobs_Applier_AIHawk is a tool that automates the jobs application process. Utilizing artificial intelligence, it enables users to apply for multiple job offers in an automated and personalized…

A fast multimodal LLM for real-time voice

Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

This is the official repository for the paper "Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On". CVPR 2024

A chrome extension to easily do visual trials of clothing from any e-commerce store. Fill the form below to get notified about release of the simple non-tech version of the extension 👇

ReelsMaker is a Python-based/streamlit application designed to create captivating faceless videos for social media platforms like TikTok and YouTube.

GUI-focused roop

Zero-Shot Detection of AI-Generated Images

AutoSplice: A Text-prompt Manipulated Image Dataset for Media Forensics, WMF@CVPR2023

Kolors Team

structured outputs for llms

🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

High-resolution models for human tasks.

An open-source RAG-based tool for chatting with your documents.

Code for ICCV 2023 paper "Contrastive Pseudo Learning for Open-World DeepFake Attribution"