cs.CVNov 13, 2026

Speed-Variation Distillation for Generative Modeling

Authors: Sukit Seripanitkarn, Phonphrm Thawatdamrongkit, Supasorn Suwajanakorn

Organizations: VISTEC, Thailand

Abstract

While diffusion models excel at image generation, their denoising trajectories pass through corrupted intermediate states far from the image manifold. We ask whether generation can instead proceed through recognizable images throughout the entire trajectory. We introduce a generative framework built around a variation-reducing degradation process that contracts diverse images toward a shared prototype while preserving recognizable intermediate states. Because such manifold traversal lacks a simple analytical form, we construct the trajectories using generative-prior-based image morphing. We then distill the reverse process into a diversification operator that transforms the prototype into increasingly varied samples. To resolve the one-to-many ambiguity of the reverse process, we associate each trajectory with its initial noise latent and apply perturbations to improve robustness against accumulated errors. At inference, every step yields a recognizable image, allowing early termination and enabling a controllable speed--variation trade-off.

Figures & tables

Explore similar work

CardsList
  1. Normalizing Trajectory Models

    May 8, 2026Jiatao Gu, Tianrong Chen, Ying Shen +3Normalizing FlowsDiffusion Model Distillation

  2. Restoring Diversity in Distilled Image and Video Generators by Probing Activations

    Nov 13, 2026Furkan Horoz, Ozgur Kara, Kaan Oktay +4Diffusion Model DistillationDiffusion-Based Image Generation

  3. Two Halves are More than One: Phase-wise Velocity Distillation for Fast and High-Quality Image Generation

    Oct 6, 2026Zhen Guo, Rongyuan Wu, Qiaosi Yi +3Diffusion Model DistillationDiffusion Distillation