Research map / Image generation / Text-to-image diffusion
StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion
Ming Tao, Bingkun Bao, Hao Tang, Yaowei Wang, Changsheng Xu
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 Contextual Feature Extractor to baseline (ablation) | SD with Target-Mask · Pororo-SV story visualization | FID: 21.14 -> 18.02 | Improved |
| add Frame-Story Cross Attention Module on top of Contextual-FE (ablation) | SD with Target-Mask + Contextual-FE · Pororo-SV story visualization | FSD: 36.34 -> 28.13 | Improved |
| add Frame-Story CAM on top of Contextual-FE (ablation) | SD with Target-Mask + Contextual-FE · Flintstones-SV story completion | FID: 21.82 -> 18.11 | Improved |
| add Contextual-FE to baseline (ablation) | SD with Target-Mask · Flintstones-SV story completion | FSD: 41.15 -> 37.88 | Improved |
| replace autoregressive AR-LDM with storyboard-based unified model | StoryImager vs AR-LDM · Pororo-SV inference | inference time: 14.5s -> 8.0s | Improved |
| replace two separate AR-LDM models with one unified model | StoryImager vs AR-LDM · Pororo-SV training | training time / GPU memory: 52h+52h -> 30h; 38G+38G -> 12G | Improved |
| use StoryImager instead of AR-LDM for story visualization | StoryImager · Pororo-SV story visualization | FSD: 35.33 -> 28.13 | Improved |
| use StoryImager instead of AR-LDM | StoryImager · Pororo-SV human eval, visualization, visual consistency | VC rank (lower better): 1.92 -> 1.45 | Improved |
Closest papers by meaning
- StoryGPT-V: Large Language Models as Consistent Story Visualizers (CVPR 2025 · similarity 0.90)
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.90)
- ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Context (AAAI 2025 · similarity 0.90)
- ViStoryBench: Comprehensive Benchmark Suite for Story Visualization (CVPR 2026 · similarity 0.90)
- LogiStory: A Logic-Aware Framework for Multi-Image Story Visualization (ICLR 2026 · similarity 0.89)
- Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models (AAAI 2025 · similarity 0.88)
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.
