Self-Reasoning Agentic Framework for Narrative Product Grid-Collage Generation

TL;DR

This paper introduces a self-reasoning agentic framework for generating narrative product grid collages that ensure visual consistency, storytelling coherence, and aesthetic harmony through explicit planning and iterative refinement.

Contribution

It presents a novel framework that constructs a product narrative, generates coordinated collages with shared style, and employs self-evaluation and refinement for improved quality.

Findings

Framework improves aesthetic quality over baselines

Enhances narrative richness and visual coherence

Iterative self-refinement leads to better results

Abstract

Narrative-driven product photography has become a prevalent paradigm in modern marketing, as coherent visual storytelling helps convey product value and establishes emotional engagement with consumers. However, existing image generation methods do not support structured narrative planning or cross-panel coordination, often resulting in weak storytelling and visual incoherence. In practice, narrative product photography is commonly presented as multi-grid collages, where multiple views or scenes jointly communicate a product narrative. To ensure visual consistency across grids and aesthetic harmony of the overall composition, we generate the collage as a single unified image rather than composing independently synthesized panels. We propose a self-reasoning agentic framework for narrative product grid collage generation. Given a product packshot and its name, the system first constructs a Product Narrative Framework that explicitly represents the product's identity, usage context, and situational environment, and translates it into complementary grids governed by a shared visual style. Constraint-aware prompts are then compiled and fed to a generation model that synthesizes the collage jointly. The generated output is evaluated on both content validity and photography quality, with explicit gates determining whether to proceed or refine. When evaluation fails, the system performs failure attribution and applies targeted refinement, enabling progressive improvement through iterative self-reflection. Experiments demonstrate that our framework consistently improves aesthetic quality, narrative richness, and visual coherence, compared to direct prompting baselines.