Research map / Image generation / Text-to-image diffusion
Word-Level Fine-Grained Story Visualization
Bowen Li
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 new sentence representation with story-wide word information (ablation) | Ours · Pororo-SV | FID: 68.48 -> 56.08 | Improved |
| add new sentence representation with story-wide word information (ablation) | Ours · Pororo-SV | Cosine: 2.24 -> 2.98 | Improved |
| add discriminator with fusion features (replacing standard discriminator) (ablation) | Ours · Pororo-SV | FID: 62.23 -> 56.08 | Improved |
| add extended spatial attention (ablation) | Ours · Pororo-SV | FID: 83.66 -> 56.08 | Improved |
| use extended spatial attention instead of word-level spatial attention (ablation) | Ours · Pororo-SV | FSD: 63.39 -> 52.50 | Improved |
| use pretrained BERT instead of LSTM text encoder (ablation) | Ours · Pororo-SV | FID: 56.08 -> 52.38 | Improved |
| finetune BERT on Pororo-SV instead of LSTM text encoder (ablation) | Ours · Pororo-SV | FID: 56.08 -> 50.96 | Improved |
| use BERT trained from scratch instead of LSTM (ablation) | Ours · Pororo-SV | FID: 56.08 -> 55.78 | No clear effect |
| add new sentence representation | StoryGAN · Pororo-SV | FID: 78.64 -> 72.81 | Improved |
| add new sentence representation | CP-CSV · Pororo-SV | FID: 67.76 -> 63.12 | Improved |
| add new sentence representation | DUCO · Pororo-SV | FID: 95.17 -> 87.82 | Improved |
| add new sentence representation | VLC · Pororo-SV | FID: 94.30 -> 82.19 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- StoryGAN — StoryGAN: A Sequential Conditional GAN for Story Visualization (CVPR 2019) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- StoryGPT-V: Large Language Models as Consistent Story Visualizers (CVPR 2025 · similarity 0.89)
- ViStoryBench: Comprehensive Benchmark Suite for Story Visualization (CVPR 2026 · similarity 0.88)
- ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Context (AAAI 2025 · similarity 0.87)
- Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models (AAAI 2025 · similarity 0.87)
- Storybooth: Training-Free Multi-Subject Consistency for Improved Visual Storytelling (ICLR 2025 · similarity 0.87)
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.86)
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.
