No fortress, purely open ground. OpenManus is Coming.

[CVPR 2025] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

CatV2TON is a lightweight DiT-based visual virtual try-on model, capable of supporting try-on for both images and videos.

Wan 2.1 for the GPU Poor

A cross-platform, high performance renderer for Gaussian Splatting using Vulkan Compute. Supports Windows, Linux, macOS, iOS, and visionOS

A tool for recompiling Xbox 360 games to native executables.

6D Rotation Representation for Unconstrained Head Pose Estimation

Wan: Open and Advanced Large-Scale Video Generative Models

Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"

Official implementation of "Sonic: Shifting Focus to Global Audio Perception in Portrait Animation"

Original reference implementation of "EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis"

Video Generation Foundation Models: https://saiyan-world.github.io/goku/

This repo contains the official authors implementation associated with the MeshSplats paper

Depth Estimation model, DepthPro by Apple, trained for Image Segmentation and Image Super Resolution.

Official implementation of Continuous 3D Perception Model with Persistent State

Original implementation of "Radiant Foam: Real-Time Differentiable Ray Tracing"

MambaGlue: Fast and Robust Local Feature Matching With Mamba @ ICRA'25

A generalist Python node editor

Fully local web research and report writing assistant

[CVPR 2025] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

💪 [ARXIV 2025] Pytorch implementation of 'HAC++: Towards 100X Compression of 3D Gaussian Splatting'

A free, open-source SaaS app starter for React & Node.js with superpowers. Full-featured. Community-driven.

Gaga: Group Any Gaussians via 3D-aware Memory Bank

[CVPR 2025] Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera

Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.

LLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.

Illumination Drawing Tools for Text-to-Image Diffusion Models