Alternatives and similar repositories for radial-attention

Users that are interested in radial-attention are comparing it to the libraries listed below

• Shenyi-Z / TaylorSeer
  [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
  ☆334Updated 3 months ago
• chengzeyi / ParaAttention
  https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching
  ☆388Updated 4 months ago
• svg-project / Sparse-VideoGen
  [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention
  ☆585Updated last week
• Vchitect / FasterCache
  [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality
  ☆252Updated 11 months ago
• ModelTC / LightX2V
  Light Video Generation Inference Framework
  ☆816Updated last week
• Zehong-Ma / MagCache
  The official code for NeurIPS 2025 "MagCache: Fast Video Generation with Magnitude-Aware Cache"
  ☆224Updated last week
• microsoft / RAS
  An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…
  ☆146Updated 5 months ago
• Shenyi-Z / ToCa
  [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching
  ☆195Updated 8 months ago
• GoatWu / Self-Forcing-Plus
  Unofficial extension implementation of Self-Forcing to support I2V && 14B training.
  ☆251Updated last month
• dc-ai-projects / DC-Gen
  DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
  ☆293Updated last month
• dvlab-research / Jenga
  [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving
  ☆256Updated 3 months ago
• madebyollin / taehv
  Tiny AutoEncoder for Hunyuan Video (and other video models)
  ☆222Updated 3 weeks ago
• nunchaku-tech / deepcompressor
  Model Compression Toolbox for Large Language Models and Diffusion Models
  ☆698Updated 3 months ago
• vipshop / cache-dit
  🤗A PyTorch-native Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs.
  ☆588Updated this week
• thu-ml / SpargeAttn
  [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
  ☆785Updated last week
• czg1225 / AsyncDiff
  [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
  ☆207Updated 2 months ago
• huggingface / flux-fast
  Making Flux go brrr on GPUs.
  ☆155Updated 4 months ago
• bebebe666 / OptimalSteps
  Official PyTorch Implementation of "Optimal Stepsize for Diffusion Sampling".
  ☆192Updated 7 months ago
• tianweiy / CausVid
  (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
  ☆1,058Updated 3 months ago
• Huage001 / CLEAR
  [NeurIPS 2025] Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".
  ☆212Updated 2 months ago
• sayakpaul / diffusers-torchao
  End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).
  ☆385Updated 5 months ago
• FoundationVision / InfinityStar
  [NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation
  ☆550Updated 2 weeks ago
• AdaCache-DiT / AdaCache
  Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"
  ☆160Updated last year
• thu-nics / DiTFastAttn
  ☆187Updated 10 months ago
• mit-han-lab / hart
  HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
  ☆640Updated last year
• MingXiangL / Teacache-xDiT
  Combining Teacache with xDiT to Accelerate Visual Generation Models
  ☆32Updated 7 months ago
• Yaofang-Liu / Pusa-VidGen
  Pusa: Thousands Timesteps Video Diffusion Model
  ☆662Updated 2 months ago
• ModelTC / Wan2.2-Lightning
  Wan2.2-Lightning: Speed up wan2.2 model with distillation
  ☆223Updated 2 weeks ago
• Tencent-Hunyuan / HunyuanVideo-1.5
  HunyuanVideo-1.5: A leading lightweight video generation model
  ☆408Updated this week
• xdit-project / mochi-xdit
  faster parallel inference of mochi-1 video generation model
  ☆125Updated 9 months ago