Yi-Ning Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yi-Ning Huang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Hong-Han Shuai
National Yang Ming Chiao Tung University, Hsinchu, Taiwan
2 shared publications - Hongxia Xie
Jilin University, Changchun, China
2 shared publications Jhe-Hao Lin
National yang Ming Chiao Tung University
2 shared publicationsTerence Lin
National yang Ming Chiao Tung University
2 shared publications- Yi Yao
National Yang Ming Chiao Tung University, Hsinchu, Taiwan
2 shared publications Chan-Feng Hsu
National Yang Ming Chiao Tung University Taiwan
1 shared publication
Latest Publications
- 30 September 2024
- Published by Springer Nature
- p. 422-438
The Fabrication of Reality and Fantasy: Scene Generation with LLM-Assisted Prompt Interpretation
- 30 September 2024
- Published by Springer Nature
- p. 422-438
The Fabrication of Reality and Fantasy: Scene Generation with LLM-Assisted Prompt Interpretation
- Open Access
The Fabrication of Reality and Fantasy: Scene Generation with LLM-Assisted Prompt Interpretation
In spite of recent advancements in text-to-image generation, limitations persist in handling complex and imaginative prompts due to the restricted diversity and complexity of training data. This work explores how diffusion models can generate images from prompts requiring artistic creativity or specialized knowledge. We introduce the Realistic-Fantasy Benchmark (RFBench), a novel evaluation framework blending realistic and fantastical scenarios. To address these challenges, we propose the Realistic-Fantasy Network (RFNet), a training-free approach integrating diffusion models with LLMs. Extensive human evaluations and GPT-based compositional assessments demonstrate our approach's superiority over state-of-the-art methods. Our code and dataset is available at https://leo81005.github.io/Reality-and-Fantasy/.
Open AccessThe Fabrication of Reality and Fantasy: Scene Generation with LLM-Assisted Prompt Interpretation
In spite of recent advancements in text-to-image generation, limitations persist in handling complex and imaginative prompts due to the restricted diversity and complexity of training data. This work explores how diffusion models can generate images from prompts requiring artistic creativity or specialized knowledge. We introduce the Realistic-Fantasy Benchmark (RFBench), a novel evaluation framework blending realistic and fantastical scenarios. To address these challenges, we propose the Realistic-Fantasy Network (RFNet), a training-free approach integrating diffusion models with LLMs. Extensive human evaluations and GPT-based compositional assessments demonstrate our approach's superiority over state-of-the-art methods. Our code and dataset is available at https://leo81005.github.io/Reality-and-Fantasy/.