Safety
UniCSG: Unified High-Fidelity Content-Constrained Style-Driven Generation via Staged Semantic and Frequency Disentanglement
arXiv:2604.17850v1 Announce Type: new Abstract: Style transfer must match a target style while preserving content semantics. DiT-based diffusion models often suffer from content-style entanglement, le
arXiv:2604.17850v1 Announce Type: new Abstract: Style transfer must match a target style while preserving content semantics. DiT-based diffusion models often suffer from content-style entanglement, leading to reference-content leakage and unstable generation. We present UniCSG, a unified framework for content-constrained, style-driven generation in both text-guided and reference-guided settings. UniCSG employs staged training: (i) a latent-space semantic disentanglement stage that combines low-frequency preprocessing with conditioning corruption to encourage content-style separation, and (ii) a latent-space frequency-aware detail reconstruction stage that refines details via multi-scale frequency supervision. We further incorporate pixel-space reward learning to align latent objectives with perceptual quality after decoding. Experiments demonstrate improved content faithfulness, style alignment, and robustness in both settings.
Related
- SHIFT: Steering Hidden Intermediates in Flow Transformers
- Region-Constrained Group Relative Policy Optimization for Flow-Based Image Editing
- Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
- MixFlow: Mixed Source Distributions Improve Rectified Flows
Source: arXiv cs.CV | 2026-04-21