microsoft / RASLinks
An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional variability in sampling steps
☆138Updated 2 months ago
Alternatives and similar repositories for RAS
Users that are interested in RAS are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆242Updated 7 months ago
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆203Updated 6 months ago
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆266Updated 2 weeks ago
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity☆412Updated 2 months ago
- Adaptive Caching for Faster Video Generation with Diffusion Transformers☆156Updated 9 months ago
- [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching☆170Updated 5 months ago
- Official Implementation: Training-Free Efficient Video Generation via Dynamic Token Carving☆232Updated 3 weeks ago
- Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".☆209Updated 4 months ago
- ☆173Updated 7 months ago
- Radial Attention Official Implementation☆483Updated 2 weeks ago
- Official PyTorch and Diffusers Implementation of "LinFusion: 1 GPU, 1 Minute, 16K Image"☆305Updated 8 months ago
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆111Updated last year
- Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"☆38Updated last month
- [ICML 2025] Official PyTorch implementation of paper "Ultra-Resolution Adaptation with Ease".☆103Updated 3 months ago
- ☆103Updated 8 months ago
- (ToCa-v2) A New version of ToCa，with faster speed and better acceleration!☆39Updated 5 months ago
- Video-Infinity generates long videos quickly using multiple GPUs without extra training.☆185Updated last year
- [ICCV2025] The code of our work "Golden Noise for Diffusion Models: A Learning Framework".☆173Updated 2 weeks ago
- Official code for ICCV 205 paper, X2I: Seamless Integration of Multimodal Understanding into Diffusion Transformer via Attention Distilla…☆81Updated last month
- Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think!☆118Updated 5 months ago
- An Efficient Text-to-Image Generation Pretrain Pipeline☆114Updated 4 months ago
- Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)☆132Updated this week
- An official implementation of EvoSearch: Scaling Image and Video Generation via Test-Time Evolutionary Search☆87Updated 2 months ago
- GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset☆217Updated last week
- [ICLR 2025] Official Implementation of Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image…☆327Updated last month
- VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation☆300Updated 4 months ago
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.☆48Updated last year
- Inference-time scaling of diffusion-based image and video generation models.☆165Updated last month
- [ICCV 2025] Code for FreeScale, a tuning-free method for higher-resolution visual generation☆130Updated last week
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆356Updated last month