Salvation Lies Within: Eliciting Inherent Style Transfer in Step-Distilled Diffusion Models

arXiv:2610.05066 · cs.CV · Submitted 2026-10-04 · Read on arXiv

cs.CV

Submitted: 2026-10-04

Updated: 2026-10-13

Comments: 29 pages

Code: https://github.com/ZichenMiao/Pairwise_Sample_Optimization3https:

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes

Sources

• Qwen3-VL Technical Report
• Controllable Generation with Text-to-Image Diffusion Models: A Survey
• Compressing Image Style Training into a Single Model Forward
• StyleShot: A Snapshot on Any Style
• MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping
• FreeStyle: Free Lunch for Text-guided Style Transfer using Diffusion Models
• D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
• GenAI Arena: An Open Evaluation Platform for Generative Models
• FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining
• SDXL-Lightning: Progressive Adversarial Diffusion Distillation
• Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield
• Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
• Adversarial Diffusion Distillation
• Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling
• GDiffRetro: Retrosynthesis Prediction with Dual Graph Enhanced Molecular Representation and Diffusion Generation
• PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
• JuDi: Revisiting Judge Decoding from First Principles via Training-Free Distributional Divergence
• InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation
• Diffusion Models: A Comprehensive Survey of Methods and Applications
• Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models