>>105691019
heres a bunch of more recent stuff around the topics of subject consistency and story generation

>Consistent Story Generation with Asymmetry Zigzag Sampling
https://arxiv.org/abs/2506.09612

>ConsiStyle: Style Diversity in Training-Free Consistent T2I Generation
https://arxiv.org/abs/2505.20626

>STORYANCHORS: Generating Consistent Multi-Scene Story Frames for Long-Form Narratives
https://arxiv.org/abs/2505.08350

>Object Isolated Attention for Consistent Story Visualization
https://arxiv.org/abs/2503.23353

>Consistent Subject Generation via Contrastive Instantiated Concepts
https://contrastive-concept-instantiation.github.io

>VinaBench: Benchmark for Faithful and Consistent Visual Narratives
https://arxiv.org/abs/2503.20871

>ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Context
https://arxiv.org/abs/2407.09774

>DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation
https://jianzongwu.github.io/projects/diffsensei

>ViSTA: Visual Storytelling using Multi-modal Adapters for Text-to-Image Diffusion Models
https://arxiv.org/abs/2506.12198

>AniMaker: Automated Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation
https://arxiv.org/abs/2506.10540

>ViStoryBench: Comprehensive Benchmark Suite for Story Visualization
https://vistorybench.github.io

>Storybooth: Training-free Multi-Subject Consistency for Improved Visual Storytelling
https://arxiv.org/abs/2504.05800

>VisAgent: Narrative-Preserving Story Visualization Framework
https://arxiv.org/abs/2503.02399

>One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt
https://github.com/byliutao/1Prompt1Story