The open source coding agent.

Official repo for: Epipolar Geometry Improves Video Generation Models

Tensors, for human consumption

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

A native policy enforcement layer for AI coding agents. Built on OPA/Rego.

SoFlow: Solution Flow Models for One-Step Generative Modeling

Official implementation of SimFlow

Official PyTorch Implementation of "Don't Play Favorites: Minority Guidance for Diffusion Models" (ICLR 2024)

Official repo for Discriminator Guidance.

Official Implementation of "MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives"

SR-DiT Speedrunning ImageNet Diffusion

📷 Camera-controlled text-to-video generation, now with intrinsics, distortion and orientation control!

Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion

An open-source toolbox for fast sampling of diffusion models. Official implementations of our works published in ICML, NeurIPS, CVPR, J. Stat. Mech.

Official implementation of Constrained Synthesis with Projected Diffusion Models (NeurIPS 2024)

Official implementation of Training-Free Constrained Generation With Stable Diffusion Models (NeurIPS 2025 Spotlight)

What's in a Prior? Learned Proximal Networks for Inverse Problems

[ICLR'24] Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition

A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

[NeurIPS'25] Official implementation of "Emergent Temporal Correspondences from Video Diffusion Models"

[NeurIPS 2025] VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models

[NeurIPS 2025] Official Implementation of DINO-Foresight: Looking into the Future with DINO

Official Code of the paper “Equivariant Sampling for Improving Diffusion Model-based Image Restoration“

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

Implementation of Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models

Official implementation of Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling

Implemented a stable diffusion architecture using PyTorch.

Evaluation of Text-to-Video Generation Models: A Dynamics Perspective[NeurIPS 2024].

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.