NUS-HPC-AI-Lab / SpeeDLinks
SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
☆188Updated 11 months ago
Alternatives and similar repositories for SpeeD
Users that are interested in SpeeD are comparing it to the libraries listed below
Sorting:
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.☆52Updated last year
- Codes accompanying the paper "Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment"☆36Updated 11 months ago
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆116Updated last year
- ☆188Updated last year
- [CVPR 2025] Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis☆129Updated 8 months ago
- MoVQGAN - model for the image encoding and reconstruction☆257Updated 2 years ago
- Score identity Distillation with Long and Short Guidance for One-Step Text-to-Image Generation☆94Updated last month
- Official Implementation for Diffusion Models Without Classifier-free Guidance☆168Updated 10 months ago
- The official implementation of Diffusion-KTO: Aligning Diffusion Models by Optimizing Human Utility☆69Updated 5 months ago
- PyTorch code and model checkpoints for Score identity Distillation (SiD) and its adversarial version (SiDA)☆147Updated 9 months ago
- Open source implementation and models of One-step Diffusion with Distribution Matching Distillation☆177Updated last year
- The official implementation for "MonoFormer: One Transformer for Both Diffusion and Autoregression"☆89Updated last year
- STAR: Scale-wise Text-to-image generation via Auto-Regressive representations☆148Updated 10 months ago
- [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"☆242Updated last year
- A list of papers, docs, codes about diffusion distillation.This repo collects various distillation methods for the Diffusion model. Welc…☆40Updated 2 years ago
- ☆50Updated 7 months ago
- [ICLR 2025] OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation☆379Updated 7 months ago
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"☆164Updated last year
- An in-context conditioning version of MUSE with pre-trained checkpoints.☆116Updated 2 years ago
- AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more samp…☆310Updated last year
- Scaling Diffusion Transformers with Mixture of Experts☆414Updated last year
- Official PyTorch Implementation of "Diffusion Autoencoders are Scalable Image Tokenizers"☆163Updated 11 months ago
- (ICCV 2025) "Principal Components" Enable A New Language of Images☆76Updated 5 months ago
- Official Pytorch implementation for LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR 2025 Oral).☆98Updated 11 months ago
- My Implementation of Adversarial Diffusion Distillation https://arxiv.org/pdf/2311.17042.pdf☆94Updated last year
- [ICML'25] EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling.☆168Updated 6 months ago
- [ICML 2025 Spotlight] Direct Discriminative Optimization: Supercharging Diffusion/Autoregressive with GAN-type Discrimination☆109Updated 5 months ago
- [ICLR 2025][arXiv:2406.07548] Image and Video Tokenization with Binary Spherical Quantization☆194Updated last month
- official repo for "VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation" [EMNLP2024]☆108Updated last month
- Autoregressive Image Generation with Randomized Parallel Decoding☆83Updated 2 months ago