Bujiazi / DiCacheLinks
Official implementation of DiCache: Let Diffusion Model Determine Its Own Cache
☆52Updated last month
Alternatives and similar repositories for DiCache
Users that are interested in DiCache are comparing it to the libraries listed below
Sorting:
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"☆160Updated last year
- The official implementation of "Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers" (arXiv …☆49Updated 5 months ago
- ☆129Updated 4 months ago
- [NeurIPS 2025] Official implementation of HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance☆82Updated last month
- (ICCV2025) EEdit⚡: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing☆57Updated last month
- The official implementation of "Neighboring Autoregressive Modeling for Efficient Visual Generation"☆58Updated 7 months ago
- Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think!☆120Updated 8 months ago
- This is the official repository for the paper "FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehe…☆107Updated 2 months ago
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.☆51Updated last year
- [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving☆253Updated 3 months ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆146Updated 4 months ago
- DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space☆279Updated last month
- Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"☆52Updated 4 months ago
- An official implementation of EvoSearch: Scaling Image and Video Generation via Test-Time Evolutionary Search☆99Updated last month
- DiT for VAE (and Video Generation)☆35Updated last year
- [CVPR2025 Highlight] PAR: Parallelized Autoregressive Visual Generation. https://yuqingwang1029.github.io/PAR-project☆178Updated 7 months ago
- ☆72Updated 3 weeks ago
- [CVPR 2025] Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis☆126Updated 5 months ago
- ☆43Updated 5 months ago
- Implementation of SmoothCache, a project aimed at speeding-up Diffusion Transformer (DiT) based GenAI models with error-guided caching.☆45Updated 3 months ago
- [Arxiv 2025] SparseD: Sparse Attention for Diffusion Language Models☆49Updated last month
- [NeurIPS 2025] IEAP: Image Editing As Programs with Diffusion Models☆106Updated last month
- 🐻 Uniform Discrete Diffusion with Metric Path for Video Generation☆73Updated this week
- Finetuning and inference tools for the CogView4 and CogVideoX model series.☆104Updated 6 months ago
- (ToCa-v2) A New version of ToCa，with faster speed and better acceleration!☆38Updated 8 months ago
- An Efficient Text-to-Image Generation Pretrain Pipeline☆119Updated 6 months ago
- ☆132Updated last month
- A light-weight and high-efficient training framework for accelerating diffusion tasks.☆50Updated last year
- Edit-R1: Reinforce Image Editing with Diffusion Negative-Aware Finetuning and MLLM Implicit Feedback☆159Updated 2 weeks ago
- Transition Models☆133Updated last month