👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.

Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, Du…

An open-sourced end-to-end VLM-based GUI Agent

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

A pipeline parallel training script for diffusion models.

The official implementation of paper "ColorFlow: Retrieval-Augmented Image Sequence Colorization"

Official Implementations for Paper - AniDoc: Animation Creation Made Easier

Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.

Build ultra fast, tiny, and cross-platform desktop apps with Typescript.

A Multipurpose toolkit for managing, editing and creating models.

[ECCV 2024] OMG: Occlusion-friendly Personalized Multi-concept Generation In Diffusion Models

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".

[SIGGRAPH Asia 2024, Best Paper Honorable Mention] This is the official implementation of our SIGGRAPH Asia journal artical: TEXGen: a Generative Diffusion Model for Mesh Textures

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Video Depth without Video Models

Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion

[CVPR 2024] EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

Out-of-the-box (OOTB) GUI Agent for Windows and macOS

Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

Auto detecting, masking and inpainting with detection model.

LLaVA-CoT, a visual language model capable of spontaneous, systematic reasoning

GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation

Implementation of MeshGPT, SOTA Mesh generation using Attention, in Pytorch

From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"

Multi-view Diffusion for 3D Generation

The code releasing for https://image-dream.github.io/