Skip to content

Latest commit

 

History

2 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 

Repository files navigation

CCD: Continual Consistency Diffusion for Lifelong Generative Modeling

arXiv License Python

Jingren Liu, Zhong Ji, Shuning Xu, Yun Wang, Xiangyu Chen


🔥 News

  • [2026-03-13] Repository initialized.
  • [2026-03-13] README released.
  • [2026-xx-xx] Training code will be released.
  • [2026-xx-xx] Evaluation code will be released.
  • [2026-xx-xx] Reproducibility guide will be released.

🧩 Overview

This repository provides the official implementation for:

CCD: Continual Consistency Diffusion for Lifelong Generative Modeling

Diffusion models have shown remarkable performance in high-fidelity generation, but they remain highly vulnerable to Generative Catastrophic Forgetting (GCF) in continual learning scenarios. When trained on non-stationary task streams, newly learned generative abilities often overwrite previously acquired knowledge, causing severe degradation or even generative collapse.

To address this problem, we propose a principled continual diffusion framework consisting of:

  • a standardized Continual Diffusion Generation (CDG) pipeline for training and evaluation,
  • a Continual Consistency Diffusion (CCD) framework for stable lifelong generative modeling,
  • a theoretical cross-task diffusion analysis that identifies the core factors behind forgetting in diffusion models.

Our method introduces three key consistency principles:

  • Inter-task Knowledge Consistency (IKC) for aligning score predictions across tasks,
  • Unconditional Knowledge Consistency (UKC) for preserving reverse-time denoising trajectories,
  • Prior Knowledge Consistency (PKC) for maintaining semantic alignment in label/prior space.

By jointly enforcing these consistency objectives with rehearsal, CCD improves long-term generative retention and delivers strong continual generation performance across multiple benchmarks.


✨ Highlights

  • A standardized continual diffusion generation pipeline for fair and reproducible evaluation
  • A theory-driven continual diffusion framework grounded in cross-task SDE analysis
  • Three complementary consistency objectives: IKC, UKC, and PKC
  • A practical CCD training framework for mitigating generative catastrophic forgetting
  • Strong continual generation results on MNIST, OxfordPets, CIFAR100, Flowers102, and CUB200
  • A replay-based extension with Hierarchical Diversity Buffer (HDB) for more stable sample retention

About

Repo for CCD: Continual Consistency Diffusion for Lifelong Generative Modeling

Resources

Stars

13 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors