Research map / Image generation / Text-to-image diffusion
DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusion
Huiguo He, Huan Yang, Zixi Tuo, Yuan Zhou, Qiuyue Wang, Yuhang Zhang, Zeyu Liu, Wenhao Huang, Hongyang Chao, Jian Ping Yin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add MMCA (masked mutual cross-attention) (ablation) | Playground baseline · DS-500 2-Subject | D&C-DS: 0.3996 -> 0.5301 | Improved |
| add MMSA (masked mutual self-attention) (ablation) | Playground baseline · DS-500 2-Subject | D&C-DS: 0.3996 -> 0.4233 | Improved |
| add MMSA to MMCA (ablation) | Playground + MMCA · DS-500 2-Subject | D&C-DS: 0.5301 -> 0.5444 | Improved |
| add MMSA to MMCA (ablation) | Playground + MMCA · DS-500 3-Subject | D&C-DS: 0.2186 -> 0.2335 | Improved |
| add MSD modules to Playground (ablation) | Playground · DS-500 2-Subject | CLIP-T: 0.3818 -> 0.3779 | Hurt |
| add MSD modules to SDXL | SDXL · DS-500 2-Subject | DS: 0.5045 -> 0.6048 | Improved |
| add MSD modules to SDXL | SDXL · DS-500 3-Subject | D&C-DS: 0.1241 -> 0.1778 | Improved |
| use Playground instead of SDXL as backbone (ablation) | DreamStory · DS-500 2-Subject | D&C-DS: 0.3848 -> 0.5444 | Improved |
| use DreamStory instead of MuDI | MuDI · DS-500 2-Subject | D&C-DS: 0.4410 -> 0.5444 | Improved |
| use ChatGPT4 instead of LLaMA3-1B for subject annotation (ablation) | LLM story director · DS-500 3-Subject | annotation accuracy (%): 80.13 -> 91.28 | Improved |
| use smaller MobileSAM instead of Grounded-SAM (ablation) | DreamStory · DS-500 2-Subject | D&C-DS: 0.5444 -> 0.5386 | No clear effect |
| apply MMSA to decoder layers instead of encoder layers (ablation) | DreamStory · qualitative | appearance consistency | Improved |
Closest papers by meaning
- StoryGPT-V: Large Language Models as Consistent Story Visualizers (CVPR 2025 · similarity 0.90)
- ViStoryBench: Comprehensive Benchmark Suite for Story Visualization (CVPR 2026 · similarity 0.89)
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.88)
- Storybooth: Training-Free Multi-Subject Consistency for Improved Visual Storytelling (ICLR 2025 · similarity 0.88)
- Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models (AAAI 2025 · similarity 0.88)
- LogiStory: A Logic-Aware Framework for Multi-Image Story Visualization (ICLR 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
