microsoft / RASLinks
An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional variability in sampling steps
☆149Updated 6 months ago
Alternatives and similar repositories for RAS
Users that are interested in RAS are comparing it to the libraries listed below
Sorting:
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"☆163Updated last year
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆347Updated 4 months ago
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆255Updated 11 months ago
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆210Updated 2 months ago
- [NeurIPS 2025] Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".☆212Updated 2 months ago
- [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving☆259Updated 4 months ago
- [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching☆197Updated 9 months ago
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆116Updated last year
- Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)☆243Updated 3 weeks ago
- DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space☆313Updated 2 months ago
- Official PyTorch and Diffusers Implementation of "LinFusion: 1 GPU, 1 Minute, 16K Image"☆311Updated last year
- ☆186Updated 11 months ago
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.☆52Updated last year
- [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation☆565Updated last month
- (ToCa-v2) A New version of ToCa，with faster speed and better acceleration!☆39Updated 9 months ago
- Official implementation of DiCache: Let Diffusion Model Determine Its Own Cache☆54Updated 2 months ago
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆605Updated 2 weeks ago
- An Efficient Text-to-Image Generation Pretrain Pipeline☆126Updated 8 months ago
- Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"☆57Updated 5 months ago
- Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think!☆120Updated 9 months ago
- [ICCV2025] The code of our work "Golden Noise for Diffusion Models: A Learning Framework".☆194Updated 4 months ago
- Official code for ICCV 2025 paper, X2I: Seamless Integration of Multimodal Understanding into Diffusion Transformer via Attention Distill…☆88Updated 6 months ago
- ☆108Updated last year
- Video-Infinity generates long videos quickly using multiple GPUs without extra training.☆189Updated last year
- Official Code of "Distribution Matching Distillation Meets Reinforcement Learning"☆136Updated 2 weeks ago
- Unofficial extension implementation of Self-Forcing to support I2V && 14B training.☆294Updated 2 months ago
- Unofficial extension implementation of CausVid☆70Updated 7 months ago
- Implementation of "S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models"☆145Updated 2 months ago
- [CVPR 2025] Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis☆128Updated 7 months ago
- [arXiv 2025] Upsample What Matters: Region-Adaptive Latent Sampling for Accelerated Diffusion Transformers☆50Updated 4 months ago