This repository includes the official implementation of our paper "Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers"
☆55May 21, 2025Updated 9 months ago
Alternatives and similar repositories for GRAT
Users that are interested in GRAT are comparing it to the libraries listed below
Sorting:
- ☆17Dec 11, 2024Updated last year
- [Interspeech 2024] LiteFocus is a tool designed to accelerate diffusion-based TTA model, now implemented with the base model AudioLDM2.☆34Mar 11, 2025Updated 11 months ago
- Code for Draft Attention☆99May 22, 2025Updated 9 months ago
- PyTorch implementation of paper "StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization" in ICML 2024.☆15Jun 4, 2024Updated last year
- Code for CVPR 2024 Oral "Neural Lineage"☆17Jun 18, 2024Updated last year
- [ECCV2024] Vista3D: Unravel the 3D Darkside of a Single Image☆56Sep 19, 2024Updated last year
- [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving☆275Aug 4, 2025Updated 7 months ago
- diffusers with search engine☆12Jan 13, 2026Updated last month
- ☆22Nov 18, 2025Updated 3 months ago
- An Tensorflow.keras implementation of Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorizatio…☆10Dec 18, 2019Updated 6 years ago
- In this paper, we propose Filter Gradient Decent (FGD), an efficient stochastic optimization algorithm that makes a consistent estimation…☆12May 18, 2021Updated 4 years ago
- DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation☆39Aug 3, 2025Updated 7 months ago
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆373Feb 16, 2026Updated 2 weeks ago
- GitHub repository for the Bria 3.2 pipeline☆44Sep 10, 2025Updated 5 months ago
- [MICCAIW 2025] ShapeKit☆20Jan 6, 2026Updated 2 months ago
- Optimizing diffusion for production-ready speeds☆37Jan 10, 2026Updated last month
- More reliable Video Understanding Evaluation☆14Sep 23, 2025Updated 5 months ago
- Dimple, the first Discrete Diffusion Multimodal Large Language Model☆115Jul 9, 2025Updated 7 months ago
- LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding☆35Jan 16, 2026Updated last month
- This node is base on VisualCloze method, A Universal Image Generation Framework via Visual In-Context Learning☆11May 21, 2025Updated 9 months ago
- ☆13Nov 25, 2021Updated 4 years ago
- Efficient Scaling laws and collaborative pretraining.☆21Sep 18, 2025Updated 5 months ago
- [Preprint] Efficient Generative Model Training via Embedded Representation Warmup☆36Oct 15, 2025Updated 4 months ago
- [NeurIPS 2025] VeriThinker: Learning to Verify Makes Reasoning Model Efficient☆65Sep 27, 2025Updated 5 months ago
- This is a implementation of Orthogonal Matching Pursuit algorithm for sparse approximation☆14Dec 25, 2019Updated 6 years ago
- ☆23Jul 20, 2025Updated 7 months ago
- Vico: Compositional Video Generation as Flow Equalization☆59Nov 15, 2024Updated last year
- ☆63Jul 11, 2025Updated 7 months ago
- Official PyTorch and Diffusers Implementation of "LinFusion: 1 GPU, 1 Minute, 16K Image"☆314Dec 23, 2024Updated last year
- [Preprint] UCGM: Unified Continuous Generative Models☆182May 27, 2025Updated 9 months ago
- Learnable Semi-structured Sparsity for Vision Transformers and Diffusion Transformers☆14Feb 7, 2025Updated last year
- Official Implementation of Frequency-enhanced Data Augmentation for Vision-and-Language Navigation (NeurIPS2023)☆14Jan 8, 2024Updated 2 years ago
- The official code for NeurIPS 2025 "MagCache: Fast Video Generation with Magnitude-Aware Cache"☆261Nov 17, 2025Updated 3 months ago
- [ICML 2025] Official PyTorch implementation of paper "Ultra-Resolution Adaptation with Ease".☆117May 3, 2025Updated 10 months ago
- lite attention implemented over flash attention 3☆45Updated this week
- [NeurIPS 2025] Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".☆215Sep 27, 2025Updated 5 months ago
- ☆17Dec 9, 2024Updated last year
- official implementation of the paper "Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability".☆48Dec 25, 2025Updated 2 months ago
- 🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …☆101Sep 8, 2025Updated 5 months ago