Stars
Official PyTorch Implementation of "Optimal Stepsize for Diffusion Sampling".
Official implementation of Learning to Discretize Denoising Diffusion ODEs
Official Implementation for "Consistency Flow Matching: Defining Straight Flows with Velocity Consistency"
Official Implementation of Rectified Flow (ICLR2023 Spotlight)
TorchCFM: a Conditional Flow Matching library
[ICML 2025] Gaussian Mixture Flow Matching Models (GMFlow)
A summary of related works about flow matching, stochastic interpolants
Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling" by Geng et al.
【三年面试五年模拟】AIGC算法工程师面试秘籍。涵盖AIGC、传统深度学习、自动驾驶、AI Agent、机器学习、计算机视觉、自然语言处理、强化学习、大数据挖掘、具身智能、元宇宙、AGI等AI行业面试笔试干货经验与核心知识。
PyTorch implementation of JiT https://arxiv.org/abs/2511.13720
[ICLR 2025] A training-free timestep-skipping strategy for accelerating diffusion model sampling, orthogonal to existing fast solvers.
Codebase for evaluation of deep generative models as presented in Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
Code release for the paper Generative Modeling With Inverse Heat Dissipation
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
Official implementation of IADB (Iterative α-(de)Blending: a Minimalist Deterministic Diffusion Model), published at Siggraph 2023.
A collection of noise designs for diffusion models [Eurographics Tutorial / SIGGRAPH Course, 2025]
[NeurIPS 2024, spotlight] Multivariate Learned Adaptive Noise for Diffusion Models
Official implementation of Cold-Diffusion for different transformations in pytorch.
[TCSVT 2025] RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion
[IEEE TIP 2024] Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model
[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Official implementation of "Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform", ICCV 2021
[ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers
PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838