| title | StepX-OPD: Rethinking Multi-Teacher On-Policy Distillation in Diffusion Models |
|---|---|
| authors | Chenru Wang, Xuanyang Zhang, Yucheng Han, Wenbo Nie, Wei Cheng, Xianfang Zeng, Gang YU, Chi Zhang |
| date | 2026-11-03 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2611.04386 |
| affiliation | StepFun |
| upvotes | 4 (Hugging Face Daily Papers, 2026-11-08) |
| links | abs pdf hf code |
| cite | |
| related | StepAudio 3 Realtime Technical Report StepAudio 3 Music Technical Report onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction P^2-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter Priors ShutterMuse: Capture-Time Photography Guidance with MLLMs |
| abstract | A deployable text-to-image diffusion model must hold several capabilities at once, such as instruction following, text rendering and human preference, and must sample in a few steps. Capabilities and few-step sampling are built in separate stages: a full-step model first consolidates capabilities through multi-teacher on-policy distillation, then serves as a fixed teacher for step distillation. Every full-step model we evaluate scores lower once compressed, and the second stage cannot begin until the first finishes. We introduce StepX-OPD, which merges the two stages: one student acquires every capability while learning to sample in a few steps, so frozen specialists supervise it on the states its own rollout visits rather than on a longer trajectory it never runs. Because a decomposition of the rollout's KL weights velocity mismatch most heavily near the clean end, we also regress the student's velocity on the low-noise part of the rollout. Separately, we find that capability integration makes models write prompt words into images on prompts that never asked for text, and we give a variant that lowers it. We evaluate on SD3.5-Medium and FLUX.1-dev across instruction following, text rendering, image quality and human preference. On both architectures, StepX-OPD attains the highest normalized average score among the four-step methods compared and exceeds the forty-step Flow-OPD model, and on SD3.5-Medium it trains with about 37% fewer GPU-hours than sequential DiffusionOPD followed by step distillation. |
bibtex
@misc{wang2026stepx,
title={StepX-OPD: Rethinking Multi-Teacher On-Policy Distillation in Diffusion Models},
author={Chenru Wang and Xuanyang Zhang and Yucheng Han and Wenbo Nie and Wei Cheng and Xianfang Zeng and Gang YU and Chi Zhang},
year={2026},
eprint={2611.04386},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2611.04386}
}