# UniCSG: Unified High-Fidelity Content-Constrained Style-Driven Generation via Staged Semantic and Frequency Disentanglement

arXiv: https://arxiv.org/abs/2604.17850 · HTML: https://mlsanity.com/paper/2604.17850/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 45 of its 53 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 30 of 45)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [StyTr2: Image Style Transfer with Transformers](https://mlsanity.com/paper/2105.14576/) (2021)
- [Measuring Style Similarity in Diffusion Models](https://mlsanity.com/paper/2404.01292/) (2024)
- [PixelDiT: Pixel Diffusion Transformers for Image Generation](https://mlsanity.com/paper/2511.20645/) (2025)
- [CSGO: Content-Style Composition in Text-to-Image Generation](https://mlsanity.com/paper/2408.16766/) (2024)
- [Ovis-U1 Technical Report](https://mlsanity.com/paper/2506.23044/) (2025)
- [DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation](https://mlsanity.com/paper/2511.19365/) (2025)
- [DiP: Taming Diffusion Models in Pixel Space](https://mlsanity.com/paper/2511.18822/) (2025)
- [ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding](https://mlsanity.com/paper/2507.14533/) (2025)
- [StyleAdapter: A Unified Stylized Image Generation Model](https://mlsanity.com/paper/2309.01770/) (2023)
- [DreamOmni2: Multimodal Instruction-based Editing and Generation](https://mlsanity.com/paper/2510.06679/) (2025)
- [OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data](https://mlsanity.com/paper/2505.18445/) (2025)
- [Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis](https://mlsanity.com/paper/2603.06507/) (2026)
- [OmniStyle: Filtering High Quality Style Transfer Data at Scale](https://mlsanity.com/paper/2505.14028/) (2025)
- [Towards Scalable Pre-training of Visual Tokenizers for Generation](https://mlsanity.com/paper/2512.13687/) (2025)
- [USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning](https://mlsanity.com/paper/2508.18966/) (2025)
- [Forgedit: Text Guided Image Editing via Learning and Forgetting](https://mlsanity.com/paper/2309.10556/) (2023)

## Abstract (arXiv)

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.