lucidrains / mmditView external linksLinks
Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch
☆514Jan 18, 2026Updated 3 weeks ago
Alternatives and similar repositories for mmdit
Users that are interested in mmdit are comparing it to the libraries listed below
Sorting:
- Implementation of rectified flow and some of its followup research / improvements in Pytorch☆427Jan 30, 2026Updated 2 weeks ago
- Implementation of Autoregressive Diffusion in Pytorch☆432Dec 4, 2025Updated 2 months ago
- Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI☆1,326Jan 27, 2026Updated 2 weeks ago
- Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"☆1,094Dec 22, 2025Updated last month
- Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"☆8,352May 31, 2024Updated last year
- EDM2 and Autoguidance -- Official PyTorch implementation☆819Dec 9, 2024Updated last year
- A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes…☆4,107Jan 5, 2026Updated last month
- Minimal implementation of scalable rectified flow transformers, based on SD3's approach☆632Jul 1, 2024Updated last year
- Consistency Models Made Easy☆324Oct 13, 2024Updated last year
- [ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think☆1,544Mar 16, 2025Updated 10 months ago
- Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation☆1,932Aug 15, 2024Updated last year
- Scaling Diffusion Transformers with Mixture of Experts☆416Sep 9, 2024Updated last year
- Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"☆182Jun 20, 2024Updated last year
- (NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis☆1,226Mar 5, 2025Updated 11 months ago
- Official Implementation of Rectified Flow (ICLR2023 Spotlight)☆1,543Jul 20, 2024Updated last year
- code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"☆1,152Nov 9, 2025Updated 3 months ago
- [ECCV 2024, Oral] FMBoost: Boosting Latent Diffusion with Flow Matching☆256Oct 17, 2025Updated 3 months ago
- PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838☆1,859Sep 27, 2024Updated last year
- PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis☆3,279Oct 31, 2024Updated last year
- A PyTorch implementation of the paper "All are Worth Words: A ViT Backbone for Diffusion Models".☆1,092Mar 25, 2023Updated 2 years ago
- A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model☆641Dec 19, 2025Updated last month
- Lumina-T2X is a unified framework for Text to Any Modality Generation☆2,251Feb 16, 2025Updated 11 months ago
- Implementation of a holodeck, written in Pytorch☆18Nov 1, 2023Updated 2 years ago
- Code for Fast Training of Diffusion Models with Masked Transformers☆421May 15, 2024Updated last year
- Official implementation of Inductive Moment Matching☆572Jul 11, 2025Updated 7 months ago
- Implementation of MagViT2 Tokenizer in Pytorch☆661Jan 12, 2025Updated last year
- TorchCFM: a Conditional Flow Matching library☆2,294Nov 11, 2025Updated 3 months ago
- PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator (NeurIPS 2024)☆534Sep 8, 2025Updated 5 months ago
- A suite of image and video neural tokenizers☆1,704Feb 11, 2025Updated last year
- [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL☆1,979Nov 4, 2025Updated 3 months ago
- VideoSys: An easy and efficient system for video generation☆2,017Aug 27, 2025Updated 5 months ago
- Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)☆594Apr 23, 2024Updated last year
- Implementation of Infini-Transformer in Pytorch☆112Jan 4, 2025Updated last year
- Open(MM)DiT: An Easy, Fast and Memory-Efficient System for (MM)DiT Training and Inference☆43Mar 13, 2024Updated last year
- The codebase of our paper "Improving the Training of Rectified Flows", NeurIPS 2024☆128Oct 18, 2024Updated last year
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆172Feb 4, 2026Updated last week
- MiniSora: A community aims to explore the implementation path and future development direction of Sora.☆1,281Feb 18, 2025Updated 11 months ago
- SEED-Voken: A Series of Powerful Visual Tokenizers☆993Nov 25, 2025Updated 2 months ago
- T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!☆415Feb 26, 2025Updated 11 months ago