Ideogram 4: Open image model at the forefront of design

Official inference code for Krea 2

A tiny single-file coding agent for self-hosted models (llama.cpp / vLLM / SGLang).

[SIGGRAPH 2026] Pixal3D: Pixel-Aligned 3D Generation from Images

Faster Whisper transcription with CTranslate2

1K resolution vision transformers pretrained on 1B human images.

Project Lyra: Open Generative 3D World Models

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

ERNIE-Image is an open text-to-image generation model developed by the ERNIE-Image team at Baidu. It is built on a single-stream Diffusion Transformer (DiT), with only 8B DiT parameters, it reaches…

[SIGGRAPH 2026] AniGen: Unified S^3 Fields for Animatable 3D Asset Generation

Fast state-of-the-art image and video segmentation in portable C/C++

Code for the Boxer research paper

An open-source desktop app for generating videos with LTX models

Official repository for LTX-Video

8x Faster JavaScript 3D Library.

A Rust crate for cooking up terminal user interfaces (TUIs) 👨‍🍳🐀 https://ratatui.rs

"Single-image Layer Decomposition for Anime Characters" (SIGGRAPH 2026 Conference Paper)

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

JavaScript animation engine

A port of Quake to Three.js.

Worlds first open-source real-time end-to-end spoken dialogue model with personalized voice cloning.

Seamless operability between C++11 and Python

GLM-Image: Auto-regressive for Dense-knowledge and High-fidelity Image Generation.

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…

Qwen-Image-Layered: Layered Decomposition for Inherent Editablity