FreeStory: Training-Free Character Consistency for Free-Form Visual Storytelling

Researchers propose FreeStory, a training-free framework for visual storytelling that maintains character consistency across images under free-form narrative prompts, where characters are introduced once and later referred to by pronouns. The method uses entity-grounded feature reuse with dynamic masks and attention blending, outperforming existing training-free approaches on both structured and free-form benchmarks including the new FreeStoryBench dataset.

arXiv:2606.25079v1 Announce Type: new Abstract: Visual storytelling aims to generate image sequences that are both aligned with narrative prompts and consistent in character appearance across images. Recent training-free methods improve character consistency by reusing attention features, but rely on structured prompts where full character descriptions are repeated in every prompt. This assumption simplifies the task but deviates from natural storytelling, where characters are typically introduced once and later referred to using pronouns or type-based expressions. We propose \textbf{FreeStory}, a training-free framework that reformulates character consistency under free-form prompts as entity-grounded feature reuse. Our method associates reference mentions with their corresponding character descriptions and combines dynamic character masks, correspondence-aware feature matching, key-value injection, and query blending to preserve identity while retaining generation diversity. We also introduce \textbf{FreeStoryBench}, a benchmark for this setting that includes both single- and multi-character stories. Experiments show that FreeStory achieves state-of-the-art performance among training-free methods on structured benchmarks and stronger overall consistency over baselines under free-form prompts.