Research map / Image generation / Text-to-image diffusion
Plot’n Polish: Zero-Shot Story Visualization and Disentangled Editing with Text-to-Image Diffusion Models
Kiymet Akdemir, Jing Shi, Kushal Kafle, Brian L. Price, Pinar Yanardag
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 |
|---|---|---|---|
| Enlarge grid from 2x2 to 3x3 (ablation) | Plot'n Polish · Story generation (qualitative, Fig. 8) | character continuity | Improved |
| Use grid priors instead of editing each frame independently (ablation) | Plot'n Polish · Story generation (qualitative, Fig. 8) | cross-frame consistency | Improved |
| Use latent blending instead of copy-and-paste of masked regions (ablation) | Plot'n Polish · Story generation (qualitative, Fig. 8) | visual artifacts | Improved |
| Replace segmentation masks with attention-derived masks (ablation) | Plot'n Polish · Editing (qualitative, Fig. 9) | edit precision | Mixed |
| Use Plot'n Polish editing instead of InstructPix2Pix | story editing · Story editing | LPIPS: 0.21 -> 0.10 | Improved |
| Compare to ConsiStory on consistency (CLIP-I) | Plot'n Polish · Story generation | CLIP-I: 0.83 -> 0.79 | Hurt |
| Use Plot'n Polish instead of baselines for text alignment in generation | story generation · Story generation | CLIP-T: 0.34 -> 0.36 | Improved |
| Use Plot'n Polish instead of Plug-and-Play for editing speed | story editing · Story editing | Time (s): 250s -> 9s | Improved |
| Apply Plot'n Polish to SDXL and Flux base models (ablation) | Plot'n Polish · Qualitative generalization | generalization | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- InstructPix2Pix — InstructPix2Pix: Learning To Follow Image Editing Instructions (CVPR 2023) · better on 5 of 5 shared results
- LEDITS++ — LEDITS++: Limitless Image Editing using Text-to-Image Models (CVPR 2024) · better on 1 of 1 shared result
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
- Consistent Story Generation: Unlocking the Potential of Zigzag Sampling (NeurIPS 2025 · similarity 0.89)
- SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency (NeurIPS 2025 · similarity 0.88)
- Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models (AAAI 2025 · similarity 0.87)
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.87)
- ViStoryBench: Comprehensive Benchmark Suite for Story Visualization (CVPR 2026 · similarity 0.86)
- DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation (CVPR 2025 · 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.
