# Sidecar: Training-Free Semantic Reuse for Character-Consistent Free-form Visual Storytelling

arXiv: https://arxiv.org/abs/2608.27280 · HTML: https://mlsanity.com/paper/2608.27280/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 27 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Builds on (most cited first, 24 of 24)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [Training-Free Consistent Text-to-Image Generation](https://mlsanity.com/paper/2402.03286/) (2024)
- [Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models](https://mlsanity.com/paper/2306.00973/) (2023)
- [Make-A-Story: Visual Memory Conditioned Consistent Story Generation](https://mlsanity.com/paper/2211.13319/) (2022)
- [TaleCrafter: Interactive Story Visualization with Multiple Characters](https://mlsanity.com/paper/2305.18247/) (2023)
- [Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models](https://mlsanity.com/paper/2211.10950/) (2022)
- [The Chosen One: Consistent Characters in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2311.10093/) (2023)
- [One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt](https://mlsanity.com/paper/2501.13554/) (2025)
- [DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusion](https://mlsanity.com/paper/2407.12899/) (2024)
- [StoryGPT-V: Large Language Models as Consistent Story Visualizers](https://mlsanity.com/paper/2312.02252/) (2023)
- [Improved Visual Story Generation with Adaptive Context Modeling](https://mlsanity.com/paper/2305.16811/) (2023)
- [StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion](https://mlsanity.com/paper/2404.05979/) (2024)
- [CharaConsist: Fine-Grained Consistent Character Generation](https://mlsanity.com/paper/2507.11533/) (2025)
- [Causal-Story: Local Causal Attention Utilizing Parameter-Efficient Tuning For Visual Story Synthesis](https://mlsanity.com/paper/2309.09553/) (2023)
- [CogCartoon: Towards Practical Story Visualization](https://mlsanity.com/paper/2312.10718/) (2023)
- [ViSTA: Visual Storytelling using Multi-modal Adapters for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2506.12198/) (2025)
- [Infinite-Story: A Training-Free Consistent Text-to-Image Generation](https://mlsanity.com/paper/2511.13002/) (2025)
- [FreeStory: Training-Free Character Consistency for Free-Form Visual Storytelling](https://mlsanity.com/paper/2606.25079/) (2026)

## Abstract (arXiv)

Visual storytelling requires generating images that follow a narrative while preserving consistent character identities across frames. In free-form story generation, a character is fully described only when first introduced and is later referred to by a type-level mention or pronoun. Although this setting better reflects natural storytelling, later prompts may omit important identity-related semantics, making character consistency more difficult to maintain. We propose Sidecar, a plug-and-play semantic augmentation module that preserves entity-level information from the initial description and injects the missing semantics into later prompt embeddings. Sidecar requires no additional training and does not modify the architecture of the base diffusion model. Experiments on FreeStoryBench show that Sidecar consistently improves prompt-image alignment and character consistency across multiple SDXL- and FLUX-based baselines, with negligible computational overhead.