EOS-Story is a training‑free framework that improves visual storytelling by balancing identity consistency with scene‑specific adaptation. It separates narrative prompts into identity and scene sub‑prompts, then uses Cross‑Contextual Bridging to inject appearance cues into the scene embedding. In the vision space, Adaptive Identity Preservation aligns identity features to the scene scale and employs Identity‑Aware Self‑Attention to avoid structural artifacts, achieving strong results on the Consistory+_+ benchmark.
arXiv:2512.23245v3 Announce Type: replace
Abstract: Recent text-to-image diffusion models have significantly improved visual quality and text alignment. However, generating a sequence of images while...
By Shin Seong Kim, Minjung Shin, Hyunin Cho, Youngjung Uh
arXiv:2608.28699v1 Announce Type: new
Abstract: Understanding long-form video remains a fundamental challenge for multimodal large language models (MLLMs). Sparse frame sampling fails to capture fine...
By Dong-Hee Kim, Seonwoo Choi, Changbeen Kim, Jungmyung Wi, Juyeon Ko, Youngju Choi, Il Hyeon Mun, Hyunwoo J. Kim, Donghyun Kim
arXiv:2606. 26171v1 Announce Type: cross Abstract: Recent image generation models achieve impressive quality in single-image synthesis, but often fail to maintain consistency across sequential outputs, as required in comics, storyboards, and visual narratives.
By Zihao Wang, Yijia Xu, Haoze Zheng, Xuran Ma, Haokun Gui, Harry Yang
arXiv:2607. 06481v1 Announce Type: cross Abstract: We present PACR-Video, a parameter-efficient framework for multi-shot long video extrapolation that preserves recurring entities, scene structure, visual style, and causal progression without full generator fine-tuning.
By Anna C\'ordoba, Adam Puente Tercero, Nerea Angulo Hijo, Mar Linares Tercero, Julia Barrientos, Ainhoa Miranda, Jes\'us Olivera
Short-drama generation has grown into a large, industrialized pipeline, and as it scales from isolated shots to the episode level, visual continuity has become a critical bottleneck. Current agent fra...
arXiv:2609.37407v1 Announce Type: new
Abstract: While recent video foundation models excel at generating high-quality short videos, long-form video generation remains a critical challenge, where a ma...
By Xianghan Wei, Xiaoda Yang, Zhi Wang, An Pan, Daoan Zhang, Huayi Zhang, Yan Zhang, Wei Xu, Zishun Liao, Jianwen Lou
arXiv:2608.22725v1 Announce Type: new
Abstract: Short-drama generation has grown into a large, industrialized pipeline, and as it scales from isolated shots to the episode level, visual continuity ha...
By Jiaqi Liu, Maolin Ran, Xiaoyang Lu, Jian Wang, Weiwen Liu, Jianghao Lin, Yong Yu, Weinan Zhang
Sidecar is a plug‑and‑play semantic augmentation module that preserves entity‑level information from a character’s initial description and injects missing semantics into later prompt embeddings, enabling training‑free character consistency in free‑form visual storytelling. It works with existing diffusion models without architectural changes and incurs negligible computational overhead. Experiments on FreeStoryBench demonstrate consistent improvements in prompt‑image alignment and character consistency across SDXL and FLUX baselines.
By Sibo Dong, Sarah Adel Bargal
arXiv:2601.01352v2 Announce Type: replace
Abstract: Human identity-preserving text-to-video generation remains challenging under large changes in viewpoint, facial expression, illumination, and motio...
By Yixuan Lai, He Wang, Kun Zhou, Tianjia Shao
Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Models introduces the VIG‑Sampler, a method that prioritizes tokens for decoding based on their attention to image tokens and penalizes redundancy in image‑attention distributions. The approach aims to improve the quality of multimodal generation by selecting more informative tokens during diffusion decoding. Experiments on seven captioning and VQA benchmarks with three open‑source dMLLMs show that VIG‑Sampler outperforms the Info‑Gain Sampler by an average of 19.3 CIDEr points and achieves better COCO Caption results using only half as many decoding steps.
By Insu Lee, Wooje Park, Wonseok Shin, Jinwoo Son, Byonghyo Shim
arXiv:2607. 24017v1 Announce Type: cross Abstract: The empirical success of attention mechanism in Multimodal Large Language Models (MLLMs) often obscures its inherent, subtle flaws.
By Pengkun Jiao, Bin Zhu, Jingjing Chen, Yu-gang Jiang