ziplab / BLADELinks
This is the official PyTorch implementation of "BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation."
☆38Updated 3 months ago
Alternatives and similar repositories for BLADE
Users that are interested in BLADE are comparing it to the libraries listed below
Sorting:
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"☆164Updated last year
- Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"☆60Updated 6 months ago
- Code for Draft Attention☆99Updated 8 months ago
- [ICCV 2025] The official implementation of "Neighboring Autoregressive Modeling for Efficient Visual Generation"☆58Updated 9 months ago
- [ICCV 2025][Few-Step Student Surpasses Teacher Diffusion] Learning Few-Step Diffusion Models by Trajectory Distribution Matching☆69Updated last month
- To pioneer training long-context multi-modal transformer models☆68Updated 5 months ago
- [ICML 2025] This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality…☆53Updated 10 months ago
- Official Code of "Distribution Matching Distillation Meets Reinforcement Learning"☆164Updated 3 weeks ago
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆116Updated last year
- ☆191Updated last year
- ☆20Updated 3 weeks ago
- [ICLR 2025] Implementation of Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding☆48Updated 9 months ago
- Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation☆106Updated last month
- The official implementation of "Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers" (arXiv …☆50Updated 7 months ago
- ☆109Updated last year
- A light-weight and high-efficient training framework for accelerating diffusion tasks.☆51Updated last year
- A survey for visual generation alignment☆110Updated 2 months ago
- [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving☆269Updated 5 months ago
- Codes accompanying the paper "Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment"☆36Updated 11 months ago
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.☆52Updated last year
- Official implementation of the paper "Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Vi…☆231Updated 10 months ago
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆621Updated last month
- [ICLR 2026] 🐻 Uniform Discrete Diffusion with Metric Path for Video Generation☆94Updated 2 weeks ago
- Towards Scalable Pre-training of Visual Tokenizers for Generation☆428Updated last month
- Official implementation of our paper: "Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing" …☆77Updated 8 months ago
- 4-steps distilled version of Wan2.2-TI2V-5B☆133Updated this week
- Image Tokenizer Needs Post-Training☆24Updated 3 months ago
- [CVPR 2025] Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis☆130Updated 8 months ago
- [CVPR2025] Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think☆23Updated 6 months ago
- Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation☆81Updated 6 months ago