Open-source alternatives to MinimaxDiffusion

Official repository for CaO 2 : Rectifying Inconsistencies in Diffusion-Based Dataset Distillation.

This repository is the official implementation of the paper:

This is the official implementation of paper Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset Distillation (CVPR2025) .

Official implementation of HIERAMP, a coarse-to-fine semantic amplification framework for generative dataset distillation based on visual autoregressive models.

🎯 Distilling Dataset in an Optimization-Free manner. 🎯 The distillation process is Architecture-Free. (Getting over the Cross-Architecture problem.) 🎯 Distilling large-scale datasets (ImageNet-1K) efficiently. 🎯 The distilled datasets are high-quality and versatile.

The code used in the following paper: Task-Specific Generative Dataset Distillation with Difficulty-Guided Sampling (ICCVW 2025)

The experiment data have been released in Google Drive. The released data include: 1 pretrained BigGAN Generators; 2 GAN Inversion learned latent vectors (z); 3 IT-GAN learned latent vectors (z).

Official implementation of "DiM: Distilling Dataset into Generative Model".

Official implementation of our CVPR 2026 paper.

If you find this repository useful, please consider giving it a star ⭐ on GitHub. - July 2025: Release preprint in arXiv. - June 2025: Our paper has been accepted to ICCV 2025.

ICLR 2026 This repository contains the official implementation of the paper: "CoDA: From Text-to-Image Diffusion Models to Training-Free Dataset Distillation".