FreeStory: Training-Free Character Consistency for Free-Form Visual Storytelling
It addresses the practical problem of maintaining character appearance consistency in visual storytelling when prompts use natural language (e.g., pronouns) rather than repeated full descriptions, which is a limitation of existing training-free methods.
FreeStory achieves state-of-the-art character consistency in visual storytelling under free-form prompts without training, outperforming prior training-free methods on structured benchmarks and showing stronger overall consistency under free-form prompts.
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.