#
Lists (1)
Starred repositories
(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis
Implementation of "Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision"
[IJCV] FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention
Wan: Open and Advanced Large-Scale Video Generative Models
(CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
PairDrop: Transfer Files Cross-Platform. No Setup, No Signup.
CoreFreq : CPU monitoring and tuning software designed for 64-bit processors.
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
Waypoints to the past and future of visual programming.
Production-ready platform for agentic workflow development.
Open-source Visual programming for backend logic that integrates with existing codebases. Flyde bridges the gap between technical and non-technical team members. Product managers, designers, and ba…
XCap is a cross-platform screen capture library written in Rust. It supports Linux (X11, Wayland), MacOS, and Windows. XCap supports screenshot and video recording (WIP).
A blazing-fast, GPU-accelerated screen capture tool written in Rust. Select, crop, and copy screen regions with pixel-perfect accuracy using keyboard shortcuts or mouse controls. 🚀
High-performance In-browser LLM Inference Engine
Model Context Protocol Servers
Effortless data labeling with AI support from Segment Anything and other awesome models.
BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models
Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
ETL, Analytics, Versioning for Unstructured Data
Get hundred of million of image+url from the crawling at home dataset and preprocess them
Easily compute clip embeddings and build a clip retrieval system with them
streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions