Implementation of SmoothCache, a project aimed at speeding-up Diffusion Transformer (DiT) based GenAI models with error-guided caching.
☆48Jul 17, 2025Updated last year
Alternatives and similar repositories for SmoothCache
Users that are interested in SmoothCache are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆12Sep 24, 2025Updated last year
- ☆22Nov 3, 2025Updated 11 months ago
- The official project website of "Morse: Dual-Sampling for Lossless Acceleration of Diffusion Models" (accepted to ICML 2025).☆11Jun 23, 2025Updated last year
- A forked version of flux-fast that makes flux-fast even faster with cache-dit, 3.3x speedup on NVIDIA L20.☆24Jul 18, 2025Updated last year
- ☆192Jan 14, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Easy recipes to speed up latency of Flux, QwenImage, and LTX-2 with NVFP4 and MXFP8 on Blackwell.☆14Apr 10, 2026Updated 6 months ago
- Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis (ICCV, 2025)☆52Oct 2, 2026Updated 3 weeks ago
- Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"☆65Jul 1, 2025Updated last year
- run flux1/sd3 model with beginner GPU (low cost) or even CPU☆13Apr 12, 2025Updated last year
- [ICML 2024] Official Repository for the paper "Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models"☆11Jul 19, 2024Updated 2 years ago
- [ICLR 2025] Weighted-Reward Preference Optimization for Implicit Model Fusion☆14Mar 17, 2025Updated last year
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.☆56Jul 8, 2024Updated 2 years ago
- Wan: Open and Advanced Large-Scale Video Generative Models☆31Jul 28, 2025Updated last year
- [NeurIPS 2026]EditBridge: Towards Faithful and Efficient Ultra-High-Resolution Image Editing☆26Aug 19, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Official PyTorch implementation of [PSA: Pyramid Sparse Attention for Efficient Video Understanding and Generation](https://arxiv.org/abs…☆25Jan 25, 2026Updated 9 months ago
- [Preprint 2026] EditWorld: Precise Editing and Flexible Referencing for Interactable Worlds☆22Sep 29, 2026Updated last month
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆268Dec 27, 2024Updated last year
- Official Implementations of "RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling"☆20Jun 5, 2026Updated 4 months ago
- [ECCV 2026] Glance: Accelerating Diffusion Models with 1 Sample☆155Jul 24, 2026Updated 3 months ago
- Official implementation of Sharpness-Aware Flow Matching☆17Jul 25, 2026Updated 3 months ago
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆215Sep 27, 2025Updated last year
- [ECCV 2026] Implementation of "CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation"☆33Jun 25, 2026Updated 4 months ago
- [ICLR 2026] Code for Evolutionary Caching to Accelerate Your Off-the-Shelf Diffusion Model☆30Mar 1, 2026Updated 7 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆53Dec 20, 2024Updated last year
- [ICLR 2026] Official implementation of DiCache: Let Diffusion Model Determine Its Own Cache☆67Jan 26, 2026Updated 9 months ago
- Official implementation of "Tetris3D: 3D Scene Generation with Objects That Fit Together"☆44Oct 14, 2026Updated 2 weeks ago
- The official repo of continuous speculative decoding☆36Mar 28, 2025Updated last year
- Official implementation of "Token Perturbation Guidance for Diffusion Models" [NeurIPS 2025]☆19May 19, 2026Updated 5 months ago
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"☆173Nov 5, 2024Updated last year
- [AAAI 2026] Official implementation of DreamRunner: Fine-Grained Storytelling Video Generation with Retrieval-Augmented Motion Adaptation☆78Jun 11, 2025Updated last year
- T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!☆418Feb 26, 2025Updated last year
- Ulysses sequence-parallel all-to-all as a torch custom op, moved by the GPU copy engines into torch symmetric memory. Zero SM usage; 1.66…☆54Aug 25, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICCV 2025] Code for FreeScale, a tuning-free method for higher-resolution visual generation☆148Oct 9, 2025Updated last year
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆125Jul 15, 2024Updated 2 years ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆157Apr 10, 2026Updated 6 months ago
- [NeurIPS 2025] Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".☆219Sep 27, 2025Updated last year
- [ICLR 2026] Offical implementation of "OBS-Diff".☆67Mar 5, 2026Updated 7 months ago
- Official implementation of Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents (NeurIPS 2025)☆47Nov 24, 2025Updated 11 months ago
- Code for Draft Attention☆104May 22, 2025Updated last year