lucidrains / mmdit
Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch
☆285Updated this week
Alternatives and similar repositories for mmdit:
Users that are interested in mmdit are comparing it to the libraries listed below
- Implementation of rectified flow and some of its followup research / improvements in Pytorch☆231Updated this week
- Scaling Diffusion Transformers with Mixture of Experts☆242Updated 4 months ago
- Code for Fast Training of Diffusion Models with Masked Transformers☆385Updated 8 months ago
- Implementation of Autoregressive Diffusion in Pytorch☆343Updated 2 months ago
- ☆320Updated last month
- Rectified Diffusion: Straightness Is Not Your Need☆161Updated last month
- This repo contains the code for 1D tokenizer and generator☆645Updated this week
- Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"☆742Updated 10 months ago
- Implementation of MagViT2 Tokenizer in Pytorch☆588Updated this week
- MoVQGAN - model for the image encoding and reconstruction☆212Updated last year
- Scalable Diffusion Models with State Space Backbone☆149Updated 10 months ago
- Code for "Diffusion Model Alignment Using Direct Preference Optimization"☆308Updated this week
- Official Pytorch Implementation of Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think☆791Updated last month
- EDM2 and Autoguidance -- Official PyTorch implementation☆610Updated last month
- [ICML 2024 Spotlight] FiT: Flexible Vision Transformer for Diffusion Model☆393Updated 2 months ago
- Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024☆329Updated 3 months ago
- Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"☆165Updated 6 months ago
- unofficial MaskGIT reproduction in PyTorch☆182Updated 11 months ago
- Train VAE like a boss☆252Updated 2 months ago
- Minimal implementation of scalable rectified flow transformers, based on SD3's approach☆465Updated 6 months ago
- Consistency Models Made Easy☆253Updated 3 months ago
- Official Implementation for "Consistency Flow Matching: Defining Straight Flows with Velocity Consistency"☆177Updated this week
- AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more samp…☆254Updated 2 months ago
- SEED-Voken: A Series of Powerful Visual Tokenizers☆810Updated 2 weeks ago
- PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator (NeurIPS 2024)☆476Updated 7 months ago
- FMBoost: Boosting Latent Diffusion with Flow Matching (ECCV 2024 Oral)☆212Updated last month
- Official pytorch implementation of the paper: "An Edit Friendly DDPM Noise Space: Inversion and Manipulations". CVPR 2024.☆305Updated 6 months ago
- ☆258Updated 3 months ago
- ☆211Updated last year
- Official code for "DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics" (NeurIPS 2023)☆106Updated 9 months ago