SHI-Labs / NATTENLinks
Fast Multi-dimensional Sparse Attention
☆703Updated 3 weeks ago
Alternatives and similar repositories for NATTEN
Users that are interested in NATTEN are comparing it to the libraries listed below
Sorting:
- [ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation☆506Updated last year
- [ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think☆1,525Updated 10 months ago
- [ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"☆435Updated 3 months ago
- A method to increase the speed and lower the memory footprint of existing vision transformers.☆1,166Updated last year
- Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)☆593Updated last year
- Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"☆1,089Updated last month
- A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model☆637Updated last month
- Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch☆510Updated 2 weeks ago
- Neighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022☆1,173Updated last year
- When it comes to optimizers, it's always better to be safe than sorry☆402Updated 4 months ago
- [CVPR 2024] DeepCache: Accelerating Diffusion Models for Free☆951Updated last year
- Code for Fast Training of Diffusion Models with Masked Transformers☆420Updated last year
- [CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models☆1,371Updated last month
- A library for calculating the FLOPs in the forward() process based on torch.fx☆137Updated last month
- A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model" (ECCV 2024)☆344Updated 10 months ago
- [ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention☆902Updated 6 months ago
- A PyTorch implementation of the paper "All are Worth Words: A ViT Backbone for Diffusion Models".☆1,086Updated 2 years ago
- [NeurIPS 2024] Official implementation of "Faster Diffusion: Rethinking the Role of UNet Encoder in Diffusion Models"☆350Updated 10 months ago
- EDM2 and Autoguidance -- Official PyTorch implementation☆812Updated last year
- DDT: Decoupled Diffusion Transformer☆358Updated 5 months ago
- This repo contains the code for 1D tokenizer and generator☆1,102Updated 10 months ago
- Implementation of rectified flow and some of its followup research / improvements in Pytorch☆421Updated this week
- Official implementation of Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer☆442Updated last year
- Scaling Diffusion Transformers with Mixture of Experts☆416Updated last year
- Causal depthwise conv1d in CUDA, with a PyTorch interface☆707Updated 2 weeks ago
- Pytorch implementation of MeanFlow on ImageNet and CIFAR10☆414Updated 3 weeks ago
- [ICML 2024 Spotlight] FiT: Flexible Vision Transformer for Diffusion Model☆430Updated last year
- Code for NeurIPS 2024 paper - The GAN is dead; long live the GAN! A Modern Baseline GAN - by Huang et al.☆852Updated last year
- [ICLR 2025 Spotlight] Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures☆540Updated 11 months ago
- [NeurIPS 2024] The official code of "U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers"☆232Updated last year