gstoica27 / DeltaFMView external linksLinks
[ICCV 2025] Official Implementation of Contrastive Flow Matching
☆160Jun 25, 2025Updated 7 months ago
Alternatives and similar repositories for DeltaFM
Users that are interested in DeltaFM are comparing it to the libraries listed below
Sorting:
- ☆95Jul 24, 2025Updated 6 months ago
- ☆70Dec 5, 2025Updated 2 months ago
- [ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think☆1,544Mar 16, 2025Updated 11 months ago
- ☆23Oct 15, 2024Updated last year
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆56Mar 10, 2025Updated 11 months ago
- [ICLR 2025] Rectified Diffusion: Straightness Is Not Your Need☆245Mar 11, 2025Updated 11 months ago
- 🔥 Official impl. of "DetailFlow: 1D Coarse-to-Fine Autoregressive Image Generation via Next-Detail Prediction"☆165Jul 10, 2025Updated 7 months ago
- Minimum implementation of EDM (Elucidating the Design Space of Diffusion-Based Generative Models) on cifar10 and mnist☆64Dec 16, 2023Updated 2 years ago
- ☆33Jan 6, 2025Updated last year
- [ICLR 2026] PixNerd: Pixel Neural Field Diffusion☆169Dec 10, 2025Updated 2 months ago
- Transition Models☆144Oct 7, 2025Updated 4 months ago
- The codebase of our paper "Improving the Training of Rectified Flows", NeurIPS 2024☆128Oct 18, 2024Updated last year
- [NeurIPS'25 Spotlight] Boosting Generative Image Modeling via Joint Image-Feature Synthesis☆111Nov 3, 2025Updated 3 months ago
- [Preprint] Efficient Generative Model Training via Embedded Representation Warmup☆36Oct 15, 2025Updated 4 months ago
- [arXiv 2025] Upsample What Matters: Region-Adaptive Latent Sampling for Accelerated Diffusion Transformers☆54Aug 8, 2025Updated 6 months ago
- source code of EfficientTTS 2☆20Feb 18, 2024Updated last year
- Adapting Self-Supervised Representations as a Latent Space for Efficient Generation☆39Oct 17, 2025Updated 4 months ago
- [Arxiv'25] MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization☆56Sep 16, 2025Updated 5 months ago
- [ICLR 2026] pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation☆268Updated this week
- Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"☆1,094Dec 22, 2025Updated last month
- [ICML 2025] The official implementation of the paper "On the Guidance of Flow Matching"☆83Sep 16, 2025Updated 5 months ago
- Official Implementation for "Consistency Flow Matching: Defining Straight Flows with Velocity Consistency"☆258Jan 17, 2025Updated last year
- Supporting code for the blog post on modular manifolds.☆115Sep 26, 2025Updated 4 months ago
- Simple reimplementation of Flow Matching for Generative Modeling (https://arxiv.org/abs/2210.02747) paper in PyTorch☆22Aug 10, 2024Updated last year
- Minimal implementation of scalable rectified flow transformers, based on SD3's approach☆632Jul 1, 2024Updated last year
- [Preprint] UCGM: Unified Continuous Generative Models☆180May 27, 2025Updated 8 months ago
- ☆739Dec 5, 2024Updated last year
- ☆28Mar 4, 2025Updated 11 months ago
- [ICLR2026] AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model☆53Oct 12, 2025Updated 4 months ago
- SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning☆51Jul 28, 2025Updated 6 months ago
- [CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models☆1,393Dec 16, 2025Updated 2 months ago
- DDT: Decoupled Diffusion Transformer☆361Aug 22, 2025Updated 5 months ago
- Simple, Efficient, and Effective Negative Guidance in Few-Step Image Generation Models By Value Sign Flip☆37Jan 27, 2026Updated 2 weeks ago
- Official PyTorch implementation for the paper Minimizing Trajectory Curvature of ODE-based Generative Models, ICML 2023☆91Feb 14, 2025Updated last year
- [Preprint] GMem: A Modular Approach for Ultra-Efficient Generative Models☆42Mar 11, 2025Updated 11 months ago
- Official repo for CFG-Zero*☆704May 2, 2025Updated 9 months ago
- Pixel-Space Generative Models☆301May 11, 2025Updated 9 months ago
- Implementations of the renormalization group-based diffusion model (RGDM).☆16Mar 10, 2025Updated 11 months ago
- F Lite is a 10B parameter diffusion model created by Freepik and Fal, trained exclusively on copyright-safe and SFW content.☆426Aug 25, 2025Updated 5 months ago