Alternatives and similar repositories for Sparse_Attention_API

Users that are interested in Sparse_Attention_API are comparing it to the libraries listed below

• Zehong-Ma / MagCache
  The official code for NeurIPS 2025 "MagCache: Fast Video Generation with Magnitude-Aware Cache"
  ☆257Updated 2 months ago
• UnicomAI / LeMiCa
  [NeurIPS 2025 Spotlight] LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation
  ☆96Updated this week
• mit-han-lab / radial-attention
  [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation
  ☆575Updated 2 months ago
• GoatWu / CausVid-Plus
  Unofficial extension implementation of CausVid
  ☆73Updated 9 months ago
• Vchitect / FasterCache
  [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality
  ☆258Updated last year
• Lightricks / LTX-Video-Q8-Kernels
  ☆75Updated 8 months ago
• DualParal-Project / DualParal
  [AAAI 2026] Minute-Long Videos with Dual Parallelisms
  ☆45Updated 2 months ago
• ModelTC / ComfyUI-Lightx2vWrapper
  ComfyUI custom node for lightx2v
  ☆74Updated 2 weeks ago
• chengzeyi / ParaAttention
  https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching
  ☆416Updated 6 months ago
• Centaurusalpha / DialogGen
  ☆26Updated last year
• choi403 / ALG
  Enhancing Motion Dynamics of Image-to-Video Models via Adaptive Low-Pass Guidance (arXiv 2025)
  ☆54Updated 6 months ago
• lodestone-rock / flow
  ☆166Updated this week
• Alpha-VLLM / Lumina-Accessory
  ☆113Updated 9 months ago
• MingXiangL / Teacache-xDiT
  Combining Teacache with xDiT to Accelerate Visual Generation Models
  ☆32Updated 9 months ago
• Eyeline-Labs / CineScale
  Code for CineScale, higher-resolution video generation based on Wan
  ☆183Updated 5 months ago
• bebebe666 / OptimalSteps
  Official PyTorch Implementation of "Optimal Stepsize for Diffusion Sampling".
  ☆195Updated 9 months ago
• ModelTC / Wan2.2-Lightning
  Wan2.2-Lightning: Speed up wan2.2 model with distillation
  ☆266Updated 2 months ago
• czg1225 / AsyncDiff
  [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
  ☆212Updated 4 months ago
• Biangbiang0321 / SpotEdit
  SpotEdit:Selective Region Editing in Diffusion Transformers
  ☆167Updated 3 weeks ago
• ChenDarYen / Normalized-Attention-Guidance
  Official implementation of "Normalized Attention Guidance"
  ☆178Updated 7 months ago
• judian17 / ComfyUI-UniWorld-jd17
  Unofficial ComfyUI implementation of UniWorld.
  ☆21Updated 7 months ago
• Huage001 / URAE
  [ICML 2025] Official PyTorch implementation of paper "Ultra-Resolution Adaptation with Ease".
  ☆116Updated 8 months ago
• madebyollin / taehv
  Tiny AutoEncoder for Hunyuan Video (and other video models)
  ☆286Updated 2 weeks ago
• xlite-dev / comfyui-cache-dit
  cache-dit for comfyui
  ☆29Updated 4 months ago
• spacepxl / HunyuanVideo-Training
  ☆79Updated 10 months ago
• W2GenAI-Lab / UltraFlux
  UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios
  ☆110Updated last month
• sdbds / qinglong-captions
  Multimodal captioner
  ☆203Updated this week
• Shakker-Labs / RepText
  RepText: Rendering Visual Text via Replicating 🔥
  ☆141Updated 7 months ago
• deepbeepmeep / mmgp
  Memory Management for the GPU Poor, run the latest open source frontier models on consumer Nvidia GPUs
  ☆171Updated 2 weeks ago
• zer0int / CLIP-fine-tune-registers-gated
  Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!
  ☆47Updated 7 months ago