Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.04201 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909825596653568 |
|---|---|
| author | Son, Moo Hyun Oh, Jintaek Mun, Sun Bin Roh, Jaechul Choi, Sehyun |
| author_facet | Son, Moo Hyun Oh, Jintaek Mun, Sun Bin Roh, Jaechul Choi, Sehyun |
| contents | While text-to-image (T2I) models can synthesize high-quality images, their performance degrades significantly when prompted with novel or out-of-distribution (OOD) entities due to inherent knowledge cutoffs. We introduce World-To-Image, a novel framework that bridges this gap by empowering T2I generation with agent-driven world knowledge. We design an agent that dynamically searches the web to retrieve images for concepts unknown to the base model. This information is then used to perform multimodal prompt optimization, steering powerful generative backbones toward an accurate synthesis. Critically, our evaluation goes beyond traditional metrics, utilizing modern assessments like LLMGrader and ImageReward to measure true semantic fidelity. Our experiments show that World-To-Image substantially outperforms state-of-the-art methods in both semantic alignment and visual aesthetics, achieving +8.1% improvement in accuracy-to-prompt on our curated NICE benchmark. Our framework achieves these results with high efficiency in less than three iterations, paving the way for T2I systems that can better reflect the ever-changing real world. Our demo code is available here\footnote{https://github.com/mhson-kyle/World-To-Image}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04201 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | World-To-Image: Grounding Text-to-Image Generation with Agent-Driven World Knowledge Son, Moo Hyun Oh, Jintaek Mun, Sun Bin Roh, Jaechul Choi, Sehyun Computer Vision and Pattern Recognition Artificial Intelligence While text-to-image (T2I) models can synthesize high-quality images, their performance degrades significantly when prompted with novel or out-of-distribution (OOD) entities due to inherent knowledge cutoffs. We introduce World-To-Image, a novel framework that bridges this gap by empowering T2I generation with agent-driven world knowledge. We design an agent that dynamically searches the web to retrieve images for concepts unknown to the base model. This information is then used to perform multimodal prompt optimization, steering powerful generative backbones toward an accurate synthesis. Critically, our evaluation goes beyond traditional metrics, utilizing modern assessments like LLMGrader and ImageReward to measure true semantic fidelity. Our experiments show that World-To-Image substantially outperforms state-of-the-art methods in both semantic alignment and visual aesthetics, achieving +8.1% improvement in accuracy-to-prompt on our curated NICE benchmark. Our framework achieves these results with high efficiency in less than three iterations, paving the way for T2I systems that can better reflect the ever-changing real world. Our demo code is available here\footnote{https://github.com/mhson-kyle/World-To-Image}. |
| title | World-To-Image: Grounding Text-to-Image Generation with Agent-Driven World Knowledge |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2510.04201 |