lucidrains / titok-pytorch
Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"
☆159Updated 2 months ago
Related projects: ⓘ
- Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch☆236Updated 3 weeks ago
- ☆65Updated this week
- Implementation of a multimodal diffusion transformer in Pytorch☆92Updated 2 months ago
- ☆74Updated 8 months ago
- Scaling Diffusion Transformers with Mixture of Experts☆178Updated last week
- ☆89Updated 2 months ago
- [ICML 2024 Spotlight] FiT: Flexible Vision Transformer for Diffusion Model☆357Updated 7 months ago
- Official PyTorch Implementation of "Scalable Autoregressive Image Generation with Mamba"☆95Updated 3 weeks ago
- Scalable Diffusion Models with State Space Backbone☆146Updated 6 months ago
- FMBoost: Boosting Latent Diffusion with Flow Matching (ECCV 2024 Oral)☆123Updated last month
- WIP☆76Updated last month
- [ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"☆157Updated last month
- This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation☆394Updated last week
- ☆168Updated 2 months ago
- Simple large-scale training of stable diffusion with multi-node support.☆122Updated last year
- Implementation of rectified flow and some of its followup research / improvements in Pytorch☆141Updated 3 weeks ago
- ☆147Updated last year
- Implementation of Autoregressive Diffusion in Pytorch☆247Updated last month
- Scaling RWKV-Like Architectures for Diffusion Models☆110Updated 5 months ago
- The codebase of our paper "Improving the Training of Rectified Flows"☆65Updated 2 months ago
- Implementation of a framework for Gamengen in Pytorch☆81Updated this week
- PyTorch implementation for "Parallel Sampling of Diffusion Models", NeurIPS 2023 Spotlight☆120Updated 11 months ago
- Open source implementation and models of One-step Diffusion with Distribution Matching Distillation☆103Updated 3 months ago
- Code for Fast Training of Diffusion Models with Masked Transformers☆351Updated 4 months ago
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆233Updated 4 months ago
- TerDiT: Ternary Diffusion Models with Transformers☆57Updated 3 months ago
- An in-context conditioning version of MUSE with pre-trained checkpoints.☆105Updated last year
- Transformer implementation for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"☆53Updated last month
- Implementation of the text to video model LUMIERE from the paper: "A Space-Time Diffusion Model for Video Generation" by Google Research☆50Updated last week
- MoVQGAN - model for the image encoding and reconstruction☆115Updated 10 months ago