Lists (2)
Starred repositories
Control Color: Multimodal Diffusion-based Interactive Image Colorization
High-Resolution Image/Video Harmonization [ECCV 2022]
simple library to make life easy when deploying superpoint, superglue models
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
Code for "Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed", CVPR 2024
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
Use your Mac trackpad as a weighing scale
OmniGen2: Exploration to Advanced Multimodal Generation.
Open3D: A Modern Library for 3D Data Processing
π WorldGen - Generate Any 3D Scene in Seconds
A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.
Get your documents ready for gen AI
100% working container for Nominatim
[ICCV 2025] π₯π₯ UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning
[ICCV 2025] Code & Data for: SuperEdit - Rectifying and Facilitating Supervision for Instruction-Based Image Editing
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
[Official Implementation] Subject-driven Video Generation via Disentangled Identity and Motion
[SIGGRAPH Asia 2025] DreamO: A Unified Framework for Image Customization
https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.
Solve Visual Understanding with Reinforced VLMs
Training-free Regional Prompting for Diffusion Transformers π₯
TextCrafter: Accurately Rendering Multiple Texts in Complex Visual Scenes
SkyReels-A2: Compose anything in video diffusion transformers
[CVPR 2025 Highlight] VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step
π₯ [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer