Stars
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
[NeurIPS25] Official Implementation (Pytorch) of "Blockwise Flow Matching"
Clarity: A Minimalist Website Template for AI Research
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
Comparison between Frechet Video Distance implementation from StyleGAN-V and the original paper
A PyTorch implementation of the paper "All are Worth Words: A ViT Backbone for Diffusion Models".
Pytorch implementation of MeanFlow on ImageNet and CIFAR10
Codebase for evaluation of deep generative models as presented in Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
PyTorch code and model checkpoints for Score identity Distillation (SiD) and its adversarial version (SiDA)
[ICML 2024 Spotlight] FiT: Flexible Vision Transformer for Diffusion Model
Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"
[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
A generative world for general-purpose robotics & embodied AI learning.
[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation
Official inference repo for FLUX.1 models
A one stop repository for generative AI research updates, interview resources, notebooks and much more!
Fast and memory-efficient exact attention
Enjoy the magic of Diffusion models!
[ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling
[NeurIPS 24] Official Implementation (Pytorch) of "Inversion-based Latent Bayesian Optimization"
Official Implementation (Pytorch) of "DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations", ICLR 2024
Official implementation of CVPR 2024 paper "Prompt Learning via Meta-Regularization".
Official Implementation (Pytorch) of the "LLaMo: Large Language Model-based Molecular Graph Assistant", NeurIPS 2024
Official Implementation (Pytorch) of "Constant Acceleration Flow", NeurIPS 2024