svg-project/Sparse-VideoGen external links

---

GitHub - View repository

GitHub.dev - Open in online code editor

Star history - Growth chart over time

deps.dev - Dependencies and security vulnerabilities

Gitingest - Export source code for LLM usage

Repomix - Export source code for LLM usage

uithub - Export source code for LLM usage

Close

svg-project/Sparse-VideoGen

Readme badge preview -

If you own this repo, copy the snippet below and add it to your README.md

---

Copy

[![RelatedRepos](https://img.shields.io/badge/related-repos-yellow)](https://relatedrepos.com/gh/svg-project/Sparse-VideoGen)

Close

svg-project / Sparse-VideoGenView on GitHubMore

• External links
• Readme badge

[ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention

☆646Mar 6, 2026Updated 2 weeks ago

Alternatives and similar repositories for Sparse-VideoGen

Users that are interested in Sparse-VideoGen are comparing it to the libraries listed below

• mit-han-lab / radial-attention

  View on GitHub
  [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation
  ☆587Nov 11, 2025Updated 4 months ago
• hao-ai-lab / FastVideo

  View on GitHub
  A unified inference and post-training framework for accelerated video generation.
  ☆3,247Updated this week
• thu-ml / SpargeAttn

  View on GitHub
  [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
  ☆961Feb 25, 2026Updated 3 weeks ago
• thu-nics / DiTFastAttn

  View on GitHub
  ☆191Jan 14, 2025Updated last year
• tianweiy / CausVid

  View on GitHub
  (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
  ☆1,269Aug 7, 2025Updated 7 months ago
• shawnricecake / draft-attention

  View on GitHub
  Code for Draft Attention
  ☆100May 22, 2025Updated 10 months ago
• Peyton-Chen / Sparse-vDiT

  View on GitHub
  The official implementation of "Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers" (arXiv …
  ☆51Jun 6, 2025Updated 9 months ago
• mit-han-lab / x-attention

  View on GitHub
  [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring
  ☆273Jul 6, 2025Updated 8 months ago
• NVlabs / LongLive

  View on GitHub
  [ICLR 2026] LongLive: Real-time Interactive Long Video Generation
  ☆1,127Feb 26, 2026Updated 3 weeks ago
• SandAI-org / MAGI-1

  View on GitHub
  MAGI-1: Autoregressive Video Generation at Scale
  ☆3,663Jun 17, 2025Updated 9 months ago
• thu-nics / ViDiT-Q

  View on GitHub
  [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
  ☆153Mar 21, 2025Updated last year
• AdaCache-DiT / AdaCache

  View on GitHub
  Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"
  ☆170Nov 5, 2024Updated last year
• Vchitect / FasterCache

  View on GitHub
  [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality
  ☆261Dec 27, 2024Updated last year
• mit-han-lab / Block-Sparse-Attention

  View on GitHub
  A sparse attention kernel supporting mix sparse patterns
  ☆480Jan 18, 2026Updated 2 months ago
• KlingAIResearch / VMoBA

  View on GitHub
  Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"
  ☆62Jul 1, 2025Updated 8 months ago
• JIA-Lab-research / Jenga

  View on GitHub
  [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving
  ☆277Aug 4, 2025Updated 7 months ago
• NUS-HPC-AI-Lab / VideoSys

  View on GitHub
  VideoSys: An easy and efficient system for video generation
  ☆2,020Aug 27, 2025Updated 6 months ago
• ali-vilab / TeaCache

  View on GitHub
  Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
  ☆1,292Jun 8, 2025Updated 9 months ago
• baaivision / NOVA

  View on GitHub
  [ICLR 2025] Autoregressive Video Generation without Vector Quantization
  ☆635Oct 29, 2025Updated 4 months ago
• xdit-project / xDiT

  View on GitHub
  xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
  ☆2,572Updated this week
• SandAI-org / MagiAttention

  View on GitHub
  A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training
  ☆676Updated this week
• huggingface / finetrainers

  View on GitHub
  Scalable and memory-optimized training of diffusion models
  ☆1,344Jun 4, 2025Updated 9 months ago
• chengzeyi / ParaAttention

  View on GitHub
  https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching
  ☆426Jul 5, 2025Updated 8 months ago
• Shenyi-Z / TaylorSeer

  View on GitHub
  [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
  ☆378Mar 2, 2026Updated 2 weeks ago
• THU-SI / Video-T1

  View on GitHub
  [ICCV 2025] Video-T1: Test-Time Scaling for Video Generation
  ☆307Mar 7, 2026Updated 2 weeks ago
• WaveSpeedAI / QuantumAttention

  View on GitHub
  [WIP] Better (FP8) attention for Hopper
  ☆32Feb 24, 2025Updated last year
• Vchitect / VBench

  View on GitHub
  [CVPR2024 Highlight] VBench - We Evaluate Video Generation
  ☆1,532Mar 13, 2026Updated last week
• guandeh17 / Self-Forcing

  View on GitHub
  Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)
  ☆3,230Sep 12, 2025Updated 6 months ago
• NJU-PCALab / OpenVid-1M

  View on GitHub
  [ICLR 2025] OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
  ☆408May 30, 2025Updated 9 months ago
• thu-ml / SageAttention

  View on GitHub
  [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…
  ☆3,226Jan 17, 2026Updated 2 months ago
• GeekGuru123 / ProfilingDiT

  View on GitHub
  ☆20Jan 1, 2026Updated 2 months ago
• Yaofang-Liu / Pusa-VidGen

  View on GitHub
  Pusa: Thousands Timesteps Video Diffusion Model
  ☆674Feb 13, 2026Updated last month
• THU-SI / VideoScene

  View on GitHub
  [CVPR 2025 Highlight] VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step
  ☆352Jul 4, 2025Updated 8 months ago
• Huage001 / CLEAR

  View on GitHub
  [NeurIPS 2025] Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".
  ☆214Sep 27, 2025Updated 5 months ago
• mit-han-lab / distrifuser

  View on GitHub
  [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
  ☆725Dec 2, 2024Updated last year
• madebyollin / taehv

  View on GitHub
  Tiny AutoEncoder for Hunyuan Video (and other video models)
  ☆332Mar 14, 2026Updated last week
• desaixie / pa_vdm

  View on GitHub
  CVPRW 2025 paper Progressive Autoregressive Video Diffusion Models: https://arxiv.org/abs/2410.08151
  ☆90May 12, 2025Updated 10 months ago
• sandyresearch / chipmunk

  View on GitHub
  🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …
  ☆103Sep 8, 2025Updated 6 months ago
• tsinghua-ideal / Twilight

  View on GitHub
  [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning
  ☆89Nov 29, 2025Updated 3 months ago