Metraipolis › archive › dc_a03bc460111f
Not Just a Subject: Capturing Adaptive Scene-Specific Variance for Visual Storytelling — arXiv:2610.22320
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22320
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:39:17.128Z
- SHA-256 of the archived text
ffd38306cc994cc92f9b3b532b47f61d45635744a04ded191cdbb834c2692970- Stable URL of this page
https://metraipolis.com/documento/dc_a03bc460111f
How to cite
Not Just a Subject: Capturing Adaptive Scene-Specific Variance for Visual Storytelling — arXiv:2610.22320 — arXiv (en), https://arxiv.org/abs/2610.22320 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a03bc460111f (Metraipolis archive dc_a03bc460111f, sha256 ffd38306cc994cc92f9b3b532b47f61d45635744a04ded191cdbb834c2692970)
BibTeX
@misc{dca03bc460111f,
title = {Not Just a Subject: Capturing Adaptive Scene-Specific Variance for Visual Storytelling — arXiv:2610.22320},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22320},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a03bc460111f; sha256 ffd38306cc994cc92f9b3b532b47f61d45635744a04ded191cdbb834c2692970},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22320. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.22320 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T08:52:02.738Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).