lumalabs / immLinks
Official implementation of Inductive Moment Matching
☆527Updated 3 weeks ago
Alternatives and similar repositories for imm
Users that are interested in imm are comparing it to the libraries listed below
Sorting:
- Minimal implementation of scalable rectified flow transformers, based on SD3's approach☆602Updated last year
- Train VAE like a boss☆284Updated 9 months ago
- Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch☆392Updated 6 months ago
- FlexTok: Resampling Images into 1D Token Sequences of Flexible Length☆229Updated 2 months ago
- [ECCV 2024, Oral] FMBoost: Boosting Latent Diffusion with Flow Matching☆241Updated 7 months ago
- PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator (NeurIPS 2024)☆524Updated last year
- DDT: Decoupled Diffusion Transformer☆267Updated last month
- [CVPR2025] PyTorch-based reimplementation of CrossFlow, as proposed in 'Flowing from Words to Pixels: A Noise-Free Framework for Cross-Mo…☆287Updated last month
- Implementation of rectified flow and some of its followup research / improvements in Pytorch☆345Updated this week
- EDM2 and Autoguidance -- Official PyTorch implementation☆746Updated 7 months ago
- The aim of this repository is to test and implement Flow-Matching-based models☆104Updated 6 months ago
- ☆254Updated 7 months ago
- ☆587Updated 7 months ago
- HART: Efficient Visual Generation with Hybrid Autoregressive Transformer☆621Updated 9 months ago
- [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"☆420Updated last month
- Pixel-Space Generative Models☆261Updated 2 months ago
- [ICLR 2025] Rectified Diffusion: Straightness Is Not Your Need☆234Updated 4 months ago
- Consistency Models Made Easy☆296Updated 9 months ago
- code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"☆939Updated 4 months ago
- ConceptAttention: A method for interpreting multi-modal diffusion transformers.☆309Updated 3 months ago
- ☆295Updated 9 months ago
- [ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers☆313Updated 2 weeks ago
- UniDisc: A discrete diffusion model for joint multimodal generation, enabling controllable and efficient text-image synthesis, editing, a…☆112Updated 4 months ago
- [ICML'25] EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling.☆138Updated last month
- JAX implementation of MeanFlow☆299Updated this week
- A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.☆172Updated last month
- Official Implementation for Diffusion Models Without Classifier-free Guidance☆140Updated 5 months ago
- Text to Image Latent Diffusion using a Transformer core☆194Updated 11 months ago
- (NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis☆869Updated 4 months ago
- [Preprint] UCGM: Unified Continuous Generative Models☆165Updated 2 months ago