Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)

High performance self-hosted photo and video management solution.

Portable ComfyUI for Windows, macOS and Linux 🔹 Pixaroma Community Edition 🔹

Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans

BoxMOT: Pluggable SOTA multi-object tracking modules modules for segmentation, object detection and pose estimation models

A Trimap-Free Portrait Matting Solution in Real Time [AAAI 2022]

A simple and smart bulk file renamer

Official pytorch implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"

Gaze-LLE-DINOv3: Gaze Target Estimation via Large-Scale Learned Encoders with DINOv3.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

A new large-scale noise-controlled face recognition dataset.

[DEIMv2] Real Time Object Detection Meets DINOv3

Lynx: Towards High-Fidelity Personalized Video Generation

Official PyTorch implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation

[NeurIPS 2025] Pixel-Perfect Depth

Official implement of VGGT-Long

🌊 Images to → 3D Parallax effect video. A free and open source ImmersityAI alternative

🎞 mpv.net is a media player for Windows with a modern GUI.

This is a implementation of the 3D FLAME model in PyTorch

Open-source video compositing software. Node-graph based. Similar in functionalities to Adobe After Effects and Nuke by The Foundry.

Repository for the paper "3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow", CVPR 2024

Official repository for the paper "CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models"

Python bindings for FFmpeg - with complex filtering support

A python binding for FFmpeg which provides sync and async APIs

Simple Synthetic Head Generator

Python GUI builder. GUI builder for Tkinter, CustomTkinter, Kivy and PySide (upcoming)

[CVPR 2025] Diffusion Self-Distillation for Zero-Shot Customized Image Generation

Puppet Warp: A Python library for advanced image transformations, inspired by Photoshop's Puppet Warp, designed for automation in scripting environments.