A tool designed for low-level examination and modification of Unreal Engine game assets by hand.

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it.

Windows app which allows using mouse without clicking - by moving it only. It's mainly for disabled people, but it can also be used in case of a mouse button failure.

🖱️ 纯粹的Windows右键菜单管理程序

High-Quality Text-to-Video Generation with Alpha Channel

开源免费的 Wispr Flow 替代方案 | 集成FunASR本地模型和可配置大语言模型的下一代中文桌面语音工作流

[SIGGRAPH Asia 2025] Implementation of "StableMotion: Training Motion Cleanup Models with Unpaired Corrupted Data"

Generates an LLM .md file from the Godot sphynx/rst documentation repo (godotengine/godot-docs).

High quality training free inpaint for every stable diffusion model. Supports ComfyUI

多平台 文生图/图生图 等能力接入MCP

Det-Model offer bbox as conditional prompt in SAM2 video predictor Pipeline

[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"

[CVPR2025] PyTorch-based reimplementation of CrossFlow, as proposed in 'Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution'

📄 Awesome OCR multiple programing languages toolkits based on ONNXRuntime, OpenVINO, PaddlePaddle and PyTorch.

Transform your 3D texturing workflow with the power of generative AI, directly within Blender!

删库

We provide a way to fuse MANO parameters into SMPLX.

Expanding FramePack into a multifunction video creation tool

The simplest, fastest repository for training/finetuning small-sized VLMs.

Context-first AI coding extension for VS Code, Cursor, and others. Free, open-source, and privacy-focused.

Football pitch plotting library for matplotlib

Lets make video diffusion practical!

Code for MetaMorph Multimodal Understanding and Generation via Instruction Tuning

Implementation of "EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"(ICCV2025)