Skip to main content

Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers

:::info Stub — Full Engineering Breakdown Coming This paper was featured on Hugging Face Daily Papers on 2026-06-30 with 3 upvotes. A full breakdown with production viability rating, implementation notes, and honest limitations is being written. Subscribe to AI Letters → :::

AuthorsAnh Nguyen et al.
Year2026
HF Upvotes3
arXiv2606.32020
PDFDownload
HF PageView on Hugging Face

Abstract

Modern one-step diffusion models achieve impressive quality through distribution-based timestep distillation. Yet, they rely on a critical assumption: Teacher and Student must inhabit the same latent space. This Shared-Space constraint prevents knowledge transfer from modern high-capacity Teachers (e.g., SD 3.5 and Flux) into compact, deployment-friendly Students such as SD 1.5, whose latent resolution and VAE parameterization differ from the Teacher. We formalize this overlooked regime as Cross-Space Distillation, where Teacher and Student differ in both latent resolution and VAE space. To enable distillation under this mismatch, we introduce the Bridge, a lightweight latent interface that maps Student latents into the Teacher space without modifying the Student backbone. Bridge combines a frozen Student VAE decoder as a spatial prior with a compact learnable projector, and is trained with latent reconstruction and attention fidelity objectives for stable Teacher-space alignment. Across diverse modern Teachers, Bridge enables substantial gains for compact one-step Students; for example, it improves SD 1.5 from 5.4 to 9.4 HPSv3 while preserving one-step inference, low latency, and broad ecosystem compatibility. These results show that heterogeneous large Teachers can be distilled into efficient, deployable backbones through a lightweight latent-space interface.


Engineering Breakdown

The Problem

Modern one-step diffusion models achieve impressive quality through distribution-based timestep distillation.

The Approach

To enable distillation under this mismatch, we introduce the Bridge, a lightweight latent interface that maps Student latents into the Teacher space without modifying the Student backbone.

Key Results

Modern one-step diffusion models achieve impressive quality through distribution-based timestep distillation.

Research Areas

This paper contributes to the following areas of AI/ML engineering:

  • Machine learning
  • Deep learning
  • Neural networks
  • Model optimization
  • AI systems
  • Crossspace

:::tip Subscribe Get weekly breakdowns of papers like this in AI Letters - the newsletter for engineers building production AI systems. :::


Back to Research Lab → · Subscribe to AI Letters →

© 2026 EngineersOfAI. All rights reserved.