StepX-OPD: Rethinking Multi-Teacher On-Policy Distillation in Diffusion Models
AuthorsChenru Wang, Xuanyang Zhang, Yucheng Han, Wenbo Nie, Wei Cheng, Xianfang Zeng, Gang YU, Chi Zhang
AffiliationsStepFun
StepX-OPD trains diffusion models to combine specialist capabilities and generate images in just a few steps, without the usual separate compression stage.
Key results
StepX-OPD inference setting evaluated on SD3.5-Medium and FLUX.1-dev.
StepX-OPD score across GenEval, OCR, DeQA, and PickScore.
StepX-OPD score across GenEval, OCR, DeQA, and PickScore.
Reduction versus sequential DiffusionOPD followed by TDM on SD3.5-Medium.
Images with prompt-word recurrence for StepX-OPD, compared with 218 for DiffusionOPD.
Recurrence count when StepX-OPD uses the optional precise teacher target.
What the paper found
StepX-OPD combines multi-teacher capability integration and few-step distillation in one training run, rather than first building a full-step teacher and compressing it later. On SD3.5-Medium and FLUX.1-dev, frozen specialists supervise states from the student’s own randomized rollout; source routing matches each training batch to the relevant specialist, while interpolated rollout states and exact re-noising provide supervision between steps. The method pairs trajectory distribution matching with velocity regression concentrated at low noise, where the paper’s reverse-KL analysis assigns greater weight to velocity mismatch. At 4 sampling steps, StepX-OPD achieves normalized average scores of 0.8901 on SD3.5-Medium and 0.8902 on FLUX.1-dev, the highest among the compared four-step methods and higher than the forty-step Flow-OPD model. On SD3.5-Medium, it uses about 37% fewer GPU-hours than sequential DiffusionOPD followed by TDM; training runs use NVIDIA H800 GPUs. The authors also measure unintended prompt-word rendering: on SD3.5-Medium, recurrence rises from 21 images for the base model to 218 for DiffusionOPD, while StepX-OPD reduces it to 94, or 84 with an optional more precise teacher target.
Original 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.
Read the original paperMore in Diffusion Models
Browse all 82 papers →FewStepRL: Fine-tuning Few-step Diffusion Models with Reinforcement Learning
Haitao Lin, Minsi Ren, Yang Li, Xingtong Ge, Zheyuan Hu, Peiyan Hu, Tailin Wu
FewStepRL adapts multiple reinforcement-learning fine-tuning methods to make reward-driven improvements to fast, few-step diffusion models.
JVT: Just Video Transformer makes pixel-space video diffusion simple
Jianjun Zhou, Hua Geng, Haoyu Guo
JVT shows that a straightforward Transformer can generate video directly in pixels—and even produce matching depth-like geometry alongside it.
Restoring Diversity in Distilled Image and Video Generators by Probing Activations
Furkan Horoz, Ozgur Kara, Kaan Oktay, Adil Kaan Akan, Atakan Kara, Anand Bhattad, James Matthew Rehg
The paper restores variety in fast distilled image and video generators by finding and correcting a collapse in their internal activation directions.