Ideogram 4: Open image model at the forefront of design

[CVPR 2026 Best Paper Finalist] Pixel Diffusion Transformers for Image Generation

Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)

[ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

A unified framework for easy reinforcement learning in Flow-Matching models

[CVPR 2026 Oral] VGGT Omega

Implementation of our paper "RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO"

Official Implementation of "What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion"

PyTorch code and models for VJEPA2 self-supervised learning from video.

Official PyTorch Implementation of "Latent Denoising Makes Good Visual Tokenizers"

SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles

[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++

Project Lyra: Open Generative 3D World Models

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

from vibe coding to agentic engineering - practice makes claude perfect

Helios: Real Real-Time Long Video Generation Model

Official code for "LagerNVS Latent Geometry for Fully Neural Real-time Novel View Synthesis" (CVPR 2026)

Unified Codebase for Advanced World Models.

Our method reconstructs 3D worlds from video diffusion models using non-rigid alignment to resolve inherent 3D inconsistencies in the generated sequences.

[CVPR 2026] ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training

Code release for paper "Test-Time Training Done Right"

[ICML 2026][Ultra Powerful Few-Step Diffusion RL] TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward

Advancing Open-source World Models

[CVPR 2026] WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories (WorldExpand of HY-World 2.0)

Depth Anything 3

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Open-source MCP to use Blender with any LLM