InnoAds-Composer: Efficient Condition Composition for E-Commerce Poster Generation

TL;DR

InnoAds-Composer is a novel single-stage framework for efficient, tri-conditional control of subject, text, and style in e-commerce poster generation, addressing fidelity and accuracy issues of prior multi-stage methods.

Contribution

It introduces importance-based routing of control tokens, a Text Feature Enhancement Module for Chinese text, and a new dataset for joint condition evaluation in poster synthesis.

Findings

Outperforms existing methods in quality metrics

Maintains low inference latency

Provides a new dataset for comprehensive evaluation

Abstract

E-commerce product poster generation aims to automatically synthesize a single image that effectively conveys product information by presenting a subject, text, and a designed style. Recent diffusion models with fine-grained and efficient controllability have advanced product poster synthesis, yet they typically rely on multi-stage pipelines, and simultaneous control over subject, text, and style remains underexplored. Such naive multi-stage pipelines also show three issues: poor subject fidelity, inaccurate text, and inconsistent style. To address these issues, we propose InnoAds-Composer, a single-stage framework that enables efficient tri-conditional control tokens over subject, glyph, and style. To alleviate the quadratic overhead introduced by naive tri-conditional token concatenation, we perform importance analysis over layers and timesteps and route each condition only to the most responsive positions, thereby shortening the active token sequence. Besides, to improve the accuracy of Chinese text rendering, we design a Text Feature Enhancement Module (TFEM) that integrates features from both glyph images and glyph crops. To support training and evaluation, we also construct a high-quality e-commerce product poster dataset and benchmark, which is the first dataset that jointly contains subject, text, and style conditions. Extensive experiments demonstrate that InnoAds-Composer significantly outperforms existing product poster methods without obviously increasing inference latency.