← Back to all news
arXiv AI By Zhe Jin, Tat-Seng Chua

CompArt: Operationalizing Aesthetic Alignment in Text-to-Image Generation via Principles of Art

Read the original on arXiv AI →

CompArt introduces a new approach to aesthetic alignment in text-to-image generation by using the Principles of Art (PoA) such as Balance, Rhythm, and Emphasis to define explicit compositional constraints. The authors create a large dataset of 80,032 WikiArt images, each annotated with PoA analyses generated by a multimodal LLM, and present ArtDapter, a lightweight adapter that steers a pretrained diffusion model along ten PoA dimensions while preserving semantic fidelity. Experiments demonstrate that CompArt outperforms strong baselines in adhering to PoA controls under a dual evaluation protocol.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Computer Vision
Oct 16

Text-to-Image Synthesis: A Decade Survey

This survey reviews 490 papers on text‑to‑image synthesis (T2I) over the past decade, covering key model families such as GANs, autoregressive models, and diffusion models. It organizes recent research by problem areas—controllability, personalization, editing, preference alignment, efficiency, safety, and spatial consistency—rather than strictly chronologically. The paper also examines unified multimodal models, datasets, evaluation metrics, and discusses applications, challenges, and future research directions in T2I.

By Nonghai Zhang, Hao Tang
diffusionmultimodalsafety
More like this →
arXiv Computer Vision
Oct 22

T-DIG: Text-Conditioned Diversity for Image Generation

T-DIG is a text-conditioned diversity framework that enables users to generate multiple images from a single prompt and then request variations along specific axes—such as background, style, or clothing—using natural language. The system employs an LLM policy to produce K axis-conditioned prompts or edit instructions for a frozen image generator or editor, trained with GRPO and a diversity reward. T‑DIG works with open‑weight, distilled, and proprietary models, and the authors release a new dataset of human‑written axes and real user interactions to benchmark text‑conditioned diversity.

By Simran Khanuja, Rohit Gandikota, Gaurav Parmar, Graham Neubig
llmsdiffusionsafety
More like this →