jt-zhang / Sparse_Attention_APILinks
☆64Updated last month
Alternatives and similar repositories for Sparse_Attention_API
Users that are interested in Sparse_Attention_API are comparing it to the libraries listed below
Sorting:
- The official code for NeurIPS 2025 "MagCache: Fast Video Generation with Magnitude-Aware Cache"☆228Updated 2 weeks ago
- Wan2.2-Lightning: Speed up wan2.2 model with distillation☆227Updated 3 weeks ago
- Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!☆47Updated 6 months ago
- ☆73Updated 6 months ago
- [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation☆559Updated 3 weeks ago
- [NeurIPS 2025 Spotlight] LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation☆57Updated this week
- ComfyUI custom node for lightx2v☆56Updated this week
- ☆26Updated last year
- ☆79Updated 9 months ago
- Unofficial extension implementation of CausVid☆66Updated 7 months ago
- Code for CineScale, higher-resolution video generation based on Wan☆177Updated 3 months ago
- Memory Management for the GPU Poor, run the latest open source frontier models on consumer Nvidia GPUs☆157Updated last week
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆396Updated 5 months ago
- flux lora merge☆25Updated 11 months ago
- Combining Teacache with xDiT to Accelerate Visual Generation Models☆32Updated 7 months ago
- [AAAI 2026] Minute-Long Videos with Dual Parallelisms☆42Updated 3 weeks ago
- Official PyTorch Implementation of "Optimal Stepsize for Diffusion Sampling".☆193Updated 7 months ago
- ☆112Updated 7 months ago
- ☆165Updated last week
- Accelerates Flux.1 image generation, just by using this node.☆141Updated 11 months ago
- a ComfyyUI custom node for QwenImage Diffsynth☆67Updated 3 months ago
- Enhancing Motion Dynamics of Image-to-Video Models via Adaptive Low-Pass Guidance (arXiv 2025)☆52Updated 4 months ago
- Official implementation of "Normalized Attention Guidance"☆174Updated 5 months ago
- ☆90Updated 4 months ago
- Official implementation of MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement☆277Updated last month
- 🔥🔥 Official Repo of UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward☆169Updated 2 months ago
- Tiny AutoEncoder for Hunyuan Video (and other video models)☆235Updated this week
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆253Updated 11 months ago
- Controlnet module for Wan2.2☆37Updated last month
- RepText: Rendering Visual Text via Replicating 🔥☆139Updated 5 months ago