Research map / Image generation / Text-to-image diffusion
AutoStory: Generating Diverse Storytelling Images with Minimal Human Efforts
Wen Wang, Canyu Zhao, Hao Chen, Zhekai Chen, Kecheng Zheng, Chunhua Shen
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 |
|---|---|---|---|
| use AutoStory instead of Custom Diffusion | story visualization · 10 stories, 71 prompts | CLIP text-image similarity: 0.7332 -> 0.7721 | Improved |
| use AutoStory instead of Custom Diffusion | story visualization · 10 stories, 71 prompts | CLIP image-image similarity: 0.6402 -> 0.6748 | Improved |
| use AutoStory instead of Paint-by-Example | story visualization · 10 stories, 71 prompts | CLIP text-image similarity: 0.7172 -> 0.7721 | Improved |
| use AutoStory instead of Custom Diffusion | story visualization · User study | Correspondence: 2.19 -> 4.31 | Improved |
| use AutoStory instead of Custom Diffusion | story visualization · User study | Coherence: 2.64 -> 4.16 | Improved |
| use AutoStory instead of Custom Diffusion | story visualization · User study | Quality: 2.65 -> 4.08 | Improved |
| add layout control (boxes and local prompts) to no-control generation (ablation) | AutoStory · Control-signal ablation | qualitative | Improved |
| add dense condition control (sketch/keypoint) alone (ablation) | AutoStory · Control-signal ablation | qualitative | Mixed |
| combine layout and dense control (ablation) | AutoStory · Control-signal ablation | qualitative | Improved |
| add extended self-attention to pure Stable Diffusion character data (ablation) | character data generation · Dog character data | identity consistency | Improved |
| generate multi-view images with One-2-3-45 only (ablation) | character data generation · Dog character data | diversity | Mixed |
| combine extended self-attention with One-2-3-45 sketches (ablation) | character data generation · Dog character data | consistency and diversity | Improved |
Closest papers by meaning
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.90)
- ViStoryBench: Comprehensive Benchmark Suite for Story Visualization (CVPR 2026 · similarity 0.89)
- StoryWeaver: A Unified World Model for Knowledge-Enhanced Story Character Customization (AAAI 2025 · similarity 0.89)
- StoryGPT-V: Large Language Models as Consistent Story Visualizers (CVPR 2025 · similarity 0.89)
- DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation (CVPR 2025 · similarity 0.89)
- ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Context (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.
