Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

Official Implementation of Amuse: Human-AI Collaborative Songwriting with Multimodal Inspirations

Consistency Models Made Easy

Codebase for evaluation of deep generative models as presented in Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models

Official implementation of Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning (NeurIPS 2024).

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

ReMoDetect: Reward Models Recognize Aligned LLM's Generations (NeurIPS 2024)

[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

ElasticTok: Adaptive Tokenization for Image and Video

Author's Implementation for E-LatentLPIPS

Official Pytorch Implementation of Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

(ICLR 2023) Official PyTorch implementation of "What Do Self-Supervised Vision Transformers Learn?"

[ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation

Train high-quality text-to-image diffusion models in a data & compute efficient manner

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

Official inference repo for FLUX.1 models

Extract frames and motion vectors from H.264 and MPEG-4 encoded video.

Coarse-to-fine Q-Network

This repo contains the code for 1D tokenizer and generator

Refine high-quality datasets and visual AI models

Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition (ICLR 2024)

[CVPR 2024] On the Content Bias in Fréchet Video Distance

PyTorch implementation of RCG https://arxiv.org/abs/2312.03701

Hierarchical Patch Diffusion Models for High-Resolution Video Synthesis [CVPR 2024]

[ICLR 2024] Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models