# HCMA: Hierarchical Cross-model Alignment for Grounded Text-to-Image Generation

Source: [HCMA: Hierarchical Cross-model Alignment for Grounded Text-to-Image Generation](<https://www.sota2.com/research/paper/68fa78851e209131cea78d37>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:40:15.707Z

Authors: Hang Wang, Zhi-Qi Cheng, Chenhao Lin, Chao Shen, Lei Zhang

Published: 2025-05-10T05:02:58.000Z

## Abstract

Text-to-image synthesis has progressed to the point where models can generate visually compelling images from natural language prompts. Yet, existing methods often fail to reconcile high-level semantic fidelity with explicit spatial control, particularly in scenes involving multiple objects, nuanced relations, or complex layouts. To bridge this gap, we propose a Hierarchical Cross-Modal Alignment (HCMA) framework for grounded text-to-image generation. HCMA integrates two alignment modules into each diffusion sampling step: a global module that continuously aligns latent representations with textual descriptions to ensure scene-level coherence, and a local module that employs bounding-box layouts to anchor objects at specified locations, enabling fine-grained spatial control. Extensive experiments on the MS-COCO 2014 validation set show that HCMA surpasses state-of-the-art baselines, achieving a 0.69 improvement in Frechet Inception Distance (FID) and a 0.0295 gain in CLIP Score. These results demonstrate HCMA's effectiveness in faithfully capturing intricate textual semantics while adhering to user-defined spatial constraints, offering a robust solution for semantically grounded image generation. Our code is available at https://github.com/hwang-cs-ime/HCMA.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.06512>)

[PDF](<https://arxiv.org/pdf/2505.06512.pdf>)