Story visualization requires generating sequential imagery that aligns semantically with evolving narratives while maintaining rigorous consistency in character identity and visual style. However, existing methodologies often struggle with subject inconsistency and identity drift, particularly when depicting complex interactions or extended narrative arcs. To address these challenges, we propose a cohesive two-stage framework designed for robust and consistent story generation. First, we introduce Group-Shared Attention (GSA), a mechanism that fosters intrinsic consistency by enabling lossless cross-sample information flow within attention layers. This allows the model to structurally encode identity correspondence across frames without relying on external encoders. Second, we leverage Direct Preference Optimization (DPO) to align generated outputs with human aesthetic and narrative standards. Unlike conventional methods that rely on conflicting auxiliary losses, our approach simultaneously enhances visual fidelity and identity preservation by learning from holistic preference data. Extensive evaluations on the ViStoryBench benchmark demonstrate that our method establishes a new state-of-the-art, significantly outperforming strong baselines with gains of +10.0 in Character Identity (CIDS) and +18.7 in Style Consistency (CSD), all while preserving high-fidelity generation.
Figures & tables
Figure 1: Visual showcase of consistent character generation. The leftmost column displays the reference input. Subsequent columns demonstrate our model’s capability to synthesize the same character in various complex scenarios, maintaining strictly consistent identity and style.
Figure 2: Illustration of the data construction process. The pipeline transforms raw data from storybooks and films into character-consistent sequences.
Figure 3: The pipeline of our two-stage approach. Stage 1 performs Consistency Pre-training by injecting Group-Shared Attention (GSA) into the adapter Φc . Stage 2 executes Preference Alignment via DPO (adapter Φd ) to mitigate semantic drift and enhance fidelity.
Method
CSD (Style) ↑
CIDS (Identity) ↑
OCCM
Alignment
Cross
Self
Cross
Self
Score
Score
StoryGen
37.1
53.1
37.1
51.2
80.3
41.4
StoryDiffusion
34.0
54.7
39.8
58.1
84.9
67.4
StoryAdapter
45.6
54.8
43.0
60.5
86.3
67.7
UNO
39.1
60.2
45.7
60.9
89.5
79.6
Ours
57.8
61.8
55.7
63.3
89.6
76.9
Table 1: Quantitative comparison on ViStoryBench. Our method demonstrates significant improvements in identity and style consistency metrics compared to the best baseline.
Figure 4: Qualitative comparison on ViStoryBench. Left: A narrative in Flat 2D Illustration style. Right: A narrative in Western Animation style. Unlike baselines that suffer from severe style drift, our method (Bottom Row) faithfully preserves both the artistic style and character identity.
Figure 5: User Study Results on a 5-point Likert Scale. We compare human preference scores across Character Consistency (CC), Style Consistency (SC), and Subjective Aesthetics (SA). Our method (Red) consistently outperforms all baselines by a significant margin, particularly in identity preservation.
Method
CIDS (Identity) ↑
CSD (Style) ↑
Cross
Self
Cross
Self
w/o GSA
34.4
53.6
29.6
60.6
w/o DPO
46.4
58.2
46.7
56.6
Full Method
55.7
63.3
57.8
61.8
Table 2: Ablation study of key components on ViStoryBench. We quantitatively evaluate the specific contributions of Group-Shared Attention (GSA) and DPO refinement to identity (CIDS) and style (CSD) preservation.
Figure 6: Visual ablation study. Top (w/o GSA): Removing GSA causes severe drift in both style and identity. Middle (w/o DPO): Removing DPO results in lower fidelity and anatomical artifacts. Bottom (Full Method):Our approach achieves the best consistency and detail sharpness.
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 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 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.
Sibo Dong, Ismail Shaheen, Sarah Adel Bargal
Department of Computer Science, Georgetown University
Visual storytelling with diffusion models has made impressive strides in maintaining character consistency across narrative scenes. However, a critical gap remains: while these methods ensure a character remains consistent across scenes, they provide no systematic method to ensure if fine-grained attributes such as color and textures of clothing, accessories are faithfully rendered in the generated images. Towards this goal, we introduce AttriStory, a benchmark enabling attribute realization in visual storytelling. We curate 200 multi-scene stories across 10 distinct artistic styles using Large Language Model. Each scene is constructed with detailed attribute specifications to enable rich visual narratives. Further, to address attribute realization, we propose a plug-and-play latent optimization module that operates during early denoising steps, when the model establishes structural and semantic content. We achieve this through AttriLoss objective designed to maximize alignment between the cross-attention maps for desired attribute-object pairs while suppressing spurious associations, guiding models to localize attributes correctly. This approach operates orthogonally to existing consistency mechanisms, integrating seamlessly with current story generation pipelines without requiring architectural modifications. Our experiments demonstrate consistent improvements on incorporating AttriLoss across all baselines. This work positions attribute realization as a distinct, complementary dimension of visual storytelling, alongside character consistency, advancing the field toward fine-grained attribute-controlled story generation. Project-page:https://manogna-s.github.io/attristory/
Recent advancements in diffusion models have significantly improved text-to-image generation, enabling their application to visual storytelling, where coherent image sequences are generated from narrative prompts. However, existing methods primarily focus on identity preservation and often fail to adapt to diverse scene variations, resulting in semantic misalignment and structural inflexibility. We propose EOS-Story, a training-free framework that harmonizes identity consistency with scene-specific adaptation across text and vision spaces. In the text space, we decouple the narrative into identity and scene sub-prompts to prevent information dilution, but this leaves the scene without access to appearance cues. To bridge this gap, we introduce Cross-Contextual Bridging, which softly injects a phrase-level appearance residual into the scene's <EOS> embedding. In the vision space, we find that scale mismatch between identity and scene subjects causes a few identity tokens to be repeatedly transferred, producing structural artifacts. We address this with Adaptive Identity Preservation, which anchors identity features at the scene-specific scale (Identity Anchoring) and integrates them via Identity-Aware Self-Attention. To evaluate performance under varied spatial compositions, we extend the Consistory+ benchmark with diverse framing scenarios (Consistory+_+). Extensive experiments show that EOS-Story achieves competitive or superior performance on both benchmarks.