cs.CVNov 13, 2026

Restoring Diversity in Distilled Image and Video Generators by Probing Activations

Authors: Furkan Horoz, Ozgur Kara, Kaan Oktay, Adil Kaan Akan, Atakan Kara, Anand Bhattad, James Matthew Rehg

Organizations: University of Illinois at Urbana-Champaign · fal · Johns Hopkins University

Abstract

Distilling diffusion models into few-step student models substantially reduces sampling latency, but induces severe diversity collapse: samples generated from different random seeds show minimal variation. In this work, we investigate the root cause of this failure by probing the internal representations of student models relative to their teachers. We find that distilled students maintain total activation variance comparable to their teachers, but concentrate it into substantially fewer directions. This directional collapse is localized to an identifiable intermediate block at the initial denoising step. Consequently, diversity collapse stems from a misallocation of activation variance rather than an inherent loss of generative capacity. Guided by this finding, we propose ReDiverse to reinstate the missing variance directions. At training time, ReDiverse-FT fine-tunes a lightweight adapter that regresses student activations onto the teacher's, reviving the teacher's feature variance characteristic. At inference time, ReDiverse-TF introduces a training-free mechanism that steers activations along precomputed teacher principal directions. Across image and video distillation benchmarks, ReDiverse consistently restores sample diversity while preserving generation quality, further supported by the user study.

Figures & tables

Appendix figures & tables20 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. A First-Step Bias Restores Lost Diversity in Diffusion Model Distillation

    Oct 27, 2026Wenwu Tang, Dong Wang, Yun Cheng +1Diffusion Model DistillationDiffusion Models

  2. Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation

    Jun 16, 2026Siyi Chen, Shaowei Liu, Yixuan Jia +4Video Diffusion ModelsDiffusion Model Distillation

  3. STRIDE: Training-Free Diversity Guidance via PCA-Directed Feature Perturbation in Single-Step Diffusion Models

    May 12, 2026Ankit Yadav, Arpit Garg, Ta Duc Huy +1Diffusion Model GuidanceOne-Step Generative Modeling