Research map / Large language models / AI and society
CogCartoon: Towards Practical Story Visualization
Zhongyang Zhu, Jie Tang
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 character-plugin generation and plugin-guided inference (CogCartoon) instead of Cones 2 | Stable Diffusion v2.1 · story 1 (girl) | image alignment (IA): 0.695 -> 0.722 | Improved |
| use CogCartoon instead of Cones 2 on a three-character story | Stable Diffusion v2.1 · story 7 (girl&boy&dog) | image alignment (IA): 0.656 -> 0.659 | Improved |
| use CogCartoon instead of Cones 2 for text alignment on the boy story | Stable Diffusion v2.1 · story 2 (boy) | text alignment (TA): 0.319 -> 0.317 | Hurt |
| use CogCartoon instead of Cones 2 for text alignment on the boy&dog story | Stable Diffusion v2.1 · story 6 (boy&dog) | text alignment (TA): 0.340 -> 0.335 | Hurt |
| use CogCartoon instead of Cones 2 on human correspondence, single-character story | Stable Diffusion v2.1 · story 1 (girl) human eval | human correspondence (COR): 1.31 -> 2.87 | Improved |
| use CogCartoon instead of Cones 2 on human correspondence, three-character story | Stable Diffusion v2.1 · story 7 (girl&boy&dog) human eval | human correspondence (COR): 0.53 -> 1.73 | Improved |
| use CogCartoon instead of Cones 2 on human coherence, two-character story | Stable Diffusion v2.1 · story 4 (girl&boy) human eval | human coherence (COH): 0.23 -> 2.40 | Improved |
| use CogCartoon instead of Cones 2 on human quality, two-character story | Stable Diffusion v2.1 · story 4 (girl&boy) human eval | human quality (QUA): 0.10 -> 2.32 | Improved |
| add data augmentation (augmented images) to character-plugin training (ablation) | CogCartoon · qualitative story generation | visual quality (qualitative) | Improved |
| vary the number of augmented images (ablation) | CogCartoon · qualitative story generation | visual quality (qualitative) | No clear effect |
| use character-plugin instead of Residual Token Embedding (RTE) to represent characters (ablation) | CogCartoon · qualitative story generation | character fidelity (qualitative) | Improved |
Closest papers by meaning
- StoryGPT-V: Large Language Models as Consistent Story Visualizers (CVPR 2025 · similarity 0.87)
- StoryWeaver: A Unified World Model for Knowledge-Enhanced Story Character Customization (AAAI 2025 · similarity 0.87)
- ViStoryBench: Comprehensive Benchmark Suite for Story Visualization (CVPR 2026 · similarity 0.87)
- DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation (CVPR 2025 · similarity 0.86)
- Consistent Story Generation: Unlocking the Potential of Zigzag Sampling (NeurIPS 2025 · similarity 0.86)
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.85)
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.
