# Structure-Semantic Co-optimized Latent Diffusion Model for Fast Visual Anagram Synthesis

arXiv: https://arxiv.org/abs/2606.16241 · HTML: https://mlsanity.com/paper/2606.16241/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 6 of its 89 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 6 of 6)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Conditional Image Generation with Score-Based Diffusion Models](https://mlsanity.com/paper/2111.13606/) (2021)
- [SyncTweedies: A General Generative Framework Based on Synchronized Diffusions](https://mlsanity.com/paper/2403.14370/) (2024)
- [Diffusion-based Aesthetic QR Code Generation via Scanning-Robust Perceptual Guidance](https://mlsanity.com/paper/2403.15878/) (2024)
- [FBSDiff++: Improved Frequency Band Substitution of Diffusion Features for Efficient and Highly Controllable Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2601.19115/) (2026)

## Abstract (arXiv)

Visual anagram is an intriguing form of art creation wherein a single image presents different conceptual interpretations under transformations such as flipping or rotation. Recent work has achieved visual anagram synthesis by leveraging pretrained text-to-image (T2I) diffusion models, yet still suffers from several key limitations including computational inefficiency, suboptimal aesthetic quality, and weak semantic fidelity and expressiveness. This work focuses on generating visual anagrams with substantially improved visual quality at minimal computational cost, thereby advancing intelligent creation of illusionary digital art. To increase image resolution while reducing time overhead, we adapt the cutting-edge parallel denoising algorithm from pixel-based T2I model to the adversarially distilled latent-based one, and accordingly propose a structure-semantic co-optimization (S2CO) framework to counteract the consequent visual degradation. As the core of our approach, S2CO framework comprises three key innovations: (romannumeral1) null-text structure alignment optimization; (romannumeral2) semantic enhancement optimization; (romannumeral3) attention-guided noise fusion. Building upon these components, our method dubbed S2CO-Anagram is able to generate higher-resolution anagram images with noticeably superior visual harmony and semantic faithfulness than related SOTA approaches, all while achieving substantially faster inference speed. Code will be publicly available.