8 papers
An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models
Dengyang Jiang, Ruoyi Du, Zhennan Chen +10
This paper investigates an increasingly important topic in generative modeling: pixel-space diffusion models. Although numerous studies have explored this topic, most focus on smal…
Z-Reward: Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions
Xin Jin, Huanqia Cai, Zhen Li +9
The paper introduces Z-Reward, a teacher‑student framework that learns to predict full rubric‑aligned score distributions for text‑to‑image generation instead of single scalar rewa…
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
Image Team, Huanqia Cai, Sihan Cao +21
The landscape of high-performance image generation models is currently dominated by proprietary systems, such as Nano Banana Pro and Seedream 4.0. Leading open-source alternatives,…
Distribution Matching Distillation Meets Reinforcement Learning
Dengyang Jiang, Dongyang Liu, Zanyi Wang +12
Distribution Matching Distillation (DMD) facilitates efficient inference by distilling multi-step diffusion models into few-step variants. Concurrently, Reinforcement Learning (RL)…
High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation
Dongyang Liu, Ruoyi Du, David Liu +7
Few-step diffusion distillation has become increasingly mature for 4-8-step generation, yet pushing further to 2 steps remains challenging. In this work, we introduce Z-Image Turbo…
D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
Dengyang Jiang, Xin Jin, Dongyang Liu +9
The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterparts (e.g, Z-Image-Turbo and…