cloneofsimo / minRF
Minimal implementation of scalable rectified flow transformers, based on SD3's approach
☆491Updated 8 months ago
Alternatives and similar repositories for minRF:
Users that are interested in minRF are comparing it to the libraries listed below
- Train VAE like a boss☆270Updated 5 months ago
- Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch☆328Updated 2 months ago
- Huggingface-compatible SDXL Unet implementation that is readily hackable☆413Updated last year
- PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator (NeurIPS 2024)☆492Updated 9 months ago
- EDM2 and Autoguidance -- Official PyTorch implementation☆663Updated 3 months ago
- Text to Image Latent Diffusion using a Transformer core☆172Updated 6 months ago
- Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"☆790Updated last year
- (NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis☆720Updated 2 weeks ago
- T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!☆388Updated 3 weeks ago
- [ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think☆882Updated last week
- [ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation☆488Updated 4 months ago
- Code for Fast Training of Diffusion Models with Masked Transformers☆396Updated 10 months ago
- ☆411Updated 3 months ago
- Official code for "RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control"☆372Updated this week
- Implementation of rectified flow and some of its followup research / improvements in Pytorch☆263Updated last month
- Officail Implementation for "Cross-Image Attention for Zero-Shot Appearance Transfer"☆359Updated 10 months ago
- DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support☆511Updated last year
- Code for "Diffusion Model Alignment Using Direct Preference Optimization"☆397Updated last month
- FMBoost: Boosting Latent Diffusion with Flow Matching (ECCV 2024 Oral)☆223Updated 3 months ago
- Implementation of Key-Locked Rank One Editing, from Nvidia AI☆233Updated last year
- Implementation of Lumiere, SOTA text-to-video generation from Google Deepmind, in Pytorch☆269Updated 7 months ago
- Official Pytorch Implementation of DenseDiffusion (ICCV 2023)☆491Updated last year
- [ICML 2024 Spotlight] FiT: Flexible Vision Transformer for Diffusion Model☆407Updated 4 months ago
- This repo contains the code for 1D tokenizer and generator☆748Updated last week
- Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024☆333Updated 5 months ago
- AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more samp…☆278Updated 4 months ago
- HART: Efficient Visual Generation with Hybrid Autoregressive Transformer☆441Updated 5 months ago
- Consistency Models Made Easy☆276Updated 5 months ago
- Implementation of MagViT2 Tokenizer in Pytorch☆597Updated 2 months ago