# StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis

arXiv: https://arxiv.org/abs/2203.15799 · HTML: https://mlsanity.com/paper/2203.15799/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 75 references that are in the map.
- First posted on arXiv 29 Mar 2022.

## Builds on (most cited first, 30 of 54)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks](https://mlsanity.com/paper/1711.10485/) (2017)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs](https://mlsanity.com/paper/2005.09635/) (2020)
- [Panoptic-DeepLab](https://mlsanity.com/paper/1910.04751/) (2019)

## Built on by (most cited first, 30 of 33)

- [T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation](https://mlsanity.com/paper/2307.06350/) (2023)
- [T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation](https://mlsanity.com/paper/2407.14505/) (2024)
- [CREPE: Can Vision-Language Foundation Models Reason Compositionally?](https://mlsanity.com/paper/2212.07796/) (2022)
- [Conditional Image-to-Video Generation with Latent Flow Diffusion Models](https://mlsanity.com/paper/2303.13744/) (2023)
- [Collaborative Diffusion for Multi-Modal Face Generation and Editing](https://mlsanity.com/paper/2304.10530/) (2023)
- [LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation](https://mlsanity.com/paper/2305.11116/) (2023)
- [VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation](https://mlsanity.com/paper/2309.00398/) (2023)
- [Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2304.01816/) (2023)
- [Effective pruning of web-scale datasets based on complexity of concept clusters](https://mlsanity.com/paper/2401.04578/) (2024)
- [Attention Calibration for Disentangled Text-to-Image Personalization](https://mlsanity.com/paper/2403.18551/) (2024)
- [DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation](https://mlsanity.com/paper/2303.06285/) (2023)
- [ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations](https://mlsanity.com/paper/2312.04655/) (2023)
- [Attribute-Centric Compositional Text-to-Image Generation](https://mlsanity.com/paper/2301.01413/) (2023)
- [Not Only Generative Art: Stable Diffusion for Content-Style Disentanglement in Art Analysis](https://mlsanity.com/paper/2304.10278/) (2023)
- [A Survey on Quality Metrics for Text-to-Image Generation](https://mlsanity.com/paper/2403.11821/) (2024)
- [TP2O: Creative Text Pair-to-Object Generation using Balance Swap-Sampling](https://mlsanity.com/paper/2310.01819/) (2023)
- [Reason out Your Layout: Evoking the Layout Master from Large Language Models for Text-to-Image Synthesis](https://mlsanity.com/paper/2311.17126/) (2023)
- [MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations](https://mlsanity.com/paper/2503.01019/) (2025)
- [Conditioning Diffusion Models via Attributes and Semantic Masks for Face Generation](https://mlsanity.com/paper/2306.00914/) (2023)
- [Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images](https://mlsanity.com/paper/2404.13784/) (2024)
- [Vision + Language Applications: A Survey](https://mlsanity.com/paper/2305.14598/) (2023)
- [Efficient Text-Guided 3D-Aware Portrait Generation with Score Distillation Sampling on Distribution](https://mlsanity.com/paper/2306.02083/) (2023)
- [DeltaSpace: A Semantic-aligned Feature Space for Flexible Text-guided Image Editing](https://mlsanity.com/paper/2310.08785/) (2023)
- [SAIR: Learning Semantic-aware Implicit Representation](https://mlsanity.com/paper/2310.09285/) (2023)
- [CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image Generation](https://mlsanity.com/paper/2509.01028/) (2025)
- [Text-Free Learning of a Natural Language Interface for Pretrained Face Generators](https://mlsanity.com/paper/2209.03953/) (2022)
- [MODIFY: Model-driven Face Stylization without Style Images](https://mlsanity.com/paper/2303.09831/) (2023)
- [FacEnhance: Facial Expression Enhancing with Recurrent DDPMs](https://mlsanity.com/paper/2406.09040/) (2024)
- [Recurrent Transformer Variational Autoencoders for Multi-Action Motion Synthesis](https://mlsanity.com/paper/2206.06741/) (2022)
- [ABHINAW: A method for Automatic Evaluation of Typography within AI-Generated Images](https://mlsanity.com/paper/2409.11874/) (2024)

## Abstract (arXiv)

Although progress has been made for text-to-image synthesis, previous methods fall short of generalizing to unseen or underrepresented attribute compositions in the input text. Lacking compositionality could have severe implications for robustness and fairness, e.g., inability to synthesize the face images of underrepresented demographic groups. In this paper, we introduce a new framework, StyleT2I, to improve the compositionality of text-to-image synthesis. Specifically, we propose a CLIP-guided Contrastive Loss to better distinguish different compositions among different sentences. To further improve the compositionality, we design a novel Semantic Matching Loss and a Spatial Constraint to identify attributes' latent directions for intended spatial region manipulations, leading to better disentangled latent representations of attributes. Based on the identified latent directions of attributes, we propose Compositional Attribute Adjustment to adjust the latent code, resulting in better compositionality of image synthesis. In addition, we leverage the ℓ2-norm regularization of identified latent directions (norm penalty) to strike a nice balance between image-text alignment and image fidelity. In the experiments, we devise a new dataset split and an evaluation metric to evaluate the compositionality of text-to-image synthesis models. The results show that StyleT2I outperforms previous approaches in terms of the consistency between the input text and synthesized images and achieves higher fidelity.