NUS-HPC-AI-Lab / SpeeDLinks
SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
☆183Updated 7 months ago
Alternatives and similar repositories for SpeeD
Users that are interested in SpeeD are comparing it to the libraries listed below
Sorting:
- Official Implementation for Diffusion Models Without Classifier-free Guidance☆147Updated 6 months ago
- ☆179Updated 8 months ago
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆111Updated last year
- [CVPR 2025] Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis☆115Updated 3 months ago
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.☆48Updated last year
- Codes accompanying the paper "Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment"☆33Updated 6 months ago
- Open source implementation and models of One-step Diffusion with Distribution Matching Distillation☆151Updated last year
- [ICML'25] EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling.☆148Updated 2 months ago
- The official implementation for "MonoFormer: One Transformer for Both Diffusion and Autoregression"☆86Updated 10 months ago
- My Implementation of Adversarial Diffusion Distillation https://arxiv.org/pdf/2311.17042.pdf☆81Updated 8 months ago
- Score identity Distillation with Long and Short Guidance for One-Step Text-to-Image Generation☆84Updated last month
- STAR: Scale-wise Text-to-image generation via Auto-Regressive representations☆145Updated 6 months ago
- The official implementation of Diffusion-KTO: Aligning Diffusion Models by Optimizing Human Utility☆59Updated last week
- Adaptive Caching for Faster Video Generation with Diffusion Transformers☆156Updated 9 months ago
- PyTorch code and model checkpoints for Score identity Distillation (SiD) and its adversarial version (SiDA)☆132Updated 4 months ago
- ☆36Updated 2 months ago
- [ICML 2025 Spotlight] Direct Discriminative Optimization: Supercharging Diffusion/Autoregressive with GAN-type Discrimination☆95Updated 3 weeks ago
- [ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers☆331Updated last month
- MoVQGAN - model for the image encoding and reconstruction☆248Updated last year
- AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more samp…☆297Updated 9 months ago
- VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation☆300Updated 5 months ago
- (ICCV 2025) "Principal Components" Enable A New Language of Images☆58Updated 3 weeks ago
- [CVPR 2024] On the Content Bias in Fréchet Video Distance☆123Updated 10 months ago
- Official PyTorch Implementation of "Diffusion Autoencoders are Scalable Image Tokenizers"☆148Updated 6 months ago
- Scaling Diffusion Transformers with Mixture of Experts☆365Updated 11 months ago
- An in-context conditioning version of MUSE with pre-trained checkpoints.☆114Updated 2 years ago
- [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"☆236Updated last year
- [ICLR 2025] Official PyTorch implmentation of paper "T-Stitch: Accelerating Sampling in Pre-trained Diffusion Models with Trajectory Stit…☆103Updated last year
- [ICLR 2025][arXiv:2406.07548] Image and Video Tokenization with Binary Spherical Quantization☆165Updated last year
- Official implementation of "Controlling Text-to-Image Diffusion by Orthogonal Finetuning".☆293Updated 10 months ago