[NeurIPS 2024] RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
-
Updated
Oct 13, 2024 - Jupyter Notebook
[NeurIPS 2024] RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
🔥 [WACV'25] Official implementation of "DiffQRCoder: Diffusion-based Aesthetic QR Code Generation with Scanning Robustness Guided Iterative Refinement"
[CVPR 2025] Official source codes for the paper: EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing.
[ICLR 2022] Denoising Likelihood Score Matching for Conditional Score-based Data Generation
Diffusion Tutorials (Enhanced Chinese Edition) — A Chinese-translated and theory-enhanced version of tsmatz/diffusion-tutorials, bridging diffusion model theory (DDPM/SMLD/SDE) with practical PyTorch implementations.
A stainer translates HE stained slices to IHC stained slices. A solution for Breast Cancer Immunohistochemical Image Generation Challenge.
[ICLR 2022] Toy Experiments for Denoising Likelihood Score Matching for Conditional Score-based Data Generation
PyTorch implementation of Dhariwal and Nichol (2021) and training it on CIFAR-10
Official implementation of "Adaptive Moments Are Surprisingly Effective for Plug-and-Play Diffusion Sampling" (ICLR 2026)
Extensions of DiGress for molecular graph generation with logical constraints, focusing on Lipinski’s Rule of Five.
Tests whether minority guidance (Um et al., 2024) is timestep-localized in diffusion denoising. Selected to EEML 2026.
2024 experiments in conditional diffusion for distributional regression: EDM, classifier and classifier-free guidance. Built on lucidrains/denoising-diffusion-pytorch.
Practicing deep learning
To associate your repository with the classifier-guidance topic, visit your repo's landing page and select "manage topics."