sihyun-yu / REPA
Official Pytorch Implementation of Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
☆633Updated this week
Related projects ⓘ
Alternatives and complementary repositories for REPA
- This repo contains the code for 1D tokenizer and generator☆534Updated this week
- Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"☆669Updated 8 months ago
- PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838☆986Updated last month
- Open-MAGVIT2: Democratizing Autoregressive Visual Generation☆690Updated last month
- Code for Fast Training of Diffusion Models with Masked Transformers☆370Updated 5 months ago
- [ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation☆454Updated last week
- Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)☆524Updated 6 months ago
- Implementation of MagViT2 Tokenizer in Pytorch☆559Updated 3 weeks ago
- [ICML 2024 Spotlight] FiT: Flexible Vision Transformer for Diffusion Model☆385Updated this week
- Analyzing and Improving the Training Dynamics of Diffusion Models (EDM2)☆523Updated 5 months ago
- Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation☆1,305Updated 2 months ago
- Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch☆253Updated 2 months ago
- code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"☆591Updated 3 weeks ago
- A suite of image and video neural tokenizers☆622Updated this week
- Implementation of Autoregressive Diffusion in Pytorch☆292Updated last week
- Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI☆690Updated last week
- Official Implementation of Rectified Flow (ICLR2023 Spotlight)☆932Updated 3 months ago
- ☆231Updated last month
- HART: Efficient Visual Generation with Hybrid Autoregressive Transformer☆324Updated 3 weeks ago
- PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator (NeurIPS 2024)☆442Updated 5 months ago
- A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model" (ECCV 2024)☆273Updated 2 months ago
- Minimal implementation of scalable rectified flow transformers, based on SD3's approach☆443Updated 4 months ago
- Scaling Diffusion Transformers with Mixture of Experts☆202Updated 2 months ago
- Code for "Diffusion Model Alignment Using Direct Preference Optimization"☆261Updated 10 months ago
- Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024☆317Updated last month
- Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.☆1,011Updated last week
- A PyTorch implementation of the paper "All are Worth Words: A ViT Backbone for Diffusion Models".☆915Updated last year
- unofficial MaskGIT reproduction in PyTorch☆163Updated 9 months ago
- Official PyTorch implementation of Video Probabilistic Diffusion Models in Projected Latent Space (CVPR 2023).☆303Updated 5 months ago
- [CVPR 2024] Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers☆523Updated 2 weeks ago