mit-han-lab / radial-attentionView external linksLinks
[NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation
☆581Nov 11, 2025Updated 3 months ago
Alternatives and similar repositories for radial-attention
Users that are interested in radial-attention are comparing it to the libraries listed below
Sorting:
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆627Feb 3, 2026Updated last week
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,257Jun 8, 2025Updated 8 months ago
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆1,215Aug 7, 2025Updated 6 months ago
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆939Dec 31, 2025Updated last month
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,159Jan 17, 2026Updated 3 weeks ago
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆3,673Feb 9, 2026Updated last week
- A unified inference and post-training framework for accelerated video generation.☆3,086Updated this week
- Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)☆3,135Sep 12, 2025Updated 5 months ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆422Jul 5, 2025Updated 7 months ago
- Pusa: Thousands Timesteps Video Diffusion Model☆671Updated this week
- A sparse attention kernel supporting mix sparse patterns☆455Jan 18, 2026Updated 3 weeks ago
- [CVPR 2025 GMCV] Test-Time Frequency Scaling: Instant Frequency Control for Any Diffusion Model☆55May 31, 2025Updated 8 months ago
- The official code that integrates MagCache (Fast Video Generation with Magnitude-Aware Cache) with ComfyUI.☆267Nov 27, 2025Updated 2 months ago
- [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving☆272Aug 4, 2025Updated 6 months ago
- 📹 A more flexible framework that can generate videos at any resolution and creates videos from images.☆1,891Updated this week
- Light Image Video Generation Inference Framework☆1,939Updated this week
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention☆264Jan 17, 2026Updated 3 weeks ago
- [ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video☆1,739Nov 28, 2025Updated 2 months ago
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"☆166Nov 5, 2024Updated last year
- [CVPR2025 Highlight] SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration☆106Jun 18, 2025Updated 7 months ago
- (NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis☆1,226Mar 5, 2025Updated 11 months ago
- [ICCV2025] DCM: Dual-Expert Consistency Model for Efficient and High-Quality Video Generation☆202Jun 8, 2025Updated 8 months ago
- ☆28Sep 4, 2025Updated 5 months ago
- Official Code of "Distribution Matching Distillation Meets Reinforcement Learning"☆177Feb 1, 2026Updated 2 weeks ago
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆368Aug 11, 2025Updated 6 months ago
- The official code for NeurIPS 2025 "MagCache: Fast Video Generation with Magnitude-Aware Cache"☆259Nov 17, 2025Updated 2 months ago
- Tiny AutoEncoder for Hunyuan Video (and other video models)☆297Feb 7, 2026Updated last week
- Enhance-A-Video: Better Generated Video for Free☆593Mar 17, 2025Updated 10 months ago
- [CVPR 2025 Highlight] MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation☆63May 9, 2025Updated 9 months ago
- Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening☆69May 18, 2025Updated 8 months ago
- [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing☆3,638Oct 17, 2025Updated 3 months ago
- The official implementation of "Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers" (arXiv …☆50Jun 6, 2025Updated 8 months ago
- Model Compression Toolbox for Large Language Models and Diffusion Models☆753Aug 14, 2025Updated 6 months ago
- MAGI-1: Autoregressive Video Generation at Scale☆3,641Jun 17, 2025Updated 7 months ago
- Official PyTorch Implementation of "Optimal Stepsize for Diffusion Sampling".☆196Apr 13, 2025Updated 10 months ago
- ☆34Feb 9, 2026Updated last week
- [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL☆1,979Nov 4, 2025Updated 3 months ago
- MoviiGen 1.1: Towards Cinematic-Quality Video Generative Models☆183Jul 21, 2025Updated 6 months ago
- Code for CineScale, higher-resolution video generation based on Wan☆183Aug 25, 2025Updated 5 months ago