#
Starred repositories
ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM
Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.
Official code for the paper: Depth Anything At Any Condition
Official implementation of "XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation".
A simple Model Context Protocol (MCP) server for generating memes using the ImgFlip API
An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others.
Official implementations for paper: VACE: All-in-One Video Creation and Editing
Lightweight coding agent that runs in your terminal
Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets
Open-source Windows and Office activator featuring HWID, Ohook, TSforge, KMS38, and Online KMS activation methods, along with advanced troubleshooting.
disable most common windowsx64 systems patchguard
An open source payments switch written in Rust to make payments fast, reliable and affordable
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Official repository of T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
[SIGGRAPH 2025] PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformer
In-context subject-driven image generation while preserving foreground fidelity
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
[SIGGRAPH 2025] Official code of the paper "FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios"
DreamO: A Unified Framework for Image Customization
Model Context Protocol Servers
🌐 WebThinker: Empowering Large Reasoning Models with Deep Research Capability
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
[ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis
Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Training released! Surpasses GPT-4o in ID persistence! Official ComfyUI workflow release! Only 4GB VRAM is enou…
[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"
A TTS model capable of generating ultra-realistic dialogue in one pass.
SkyReels-V2: Infinite-length Film Generative model
MAGI-1: Autoregressive Video Generation at Scale