Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2505.14254 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909617470046208 |
|---|---|
| author | Chang, Yuanyuan Yao, Yinghua Qin, Tao Wang, Mengmeng Tsang, Ivor Dai, Guang |
| author_facet | Chang, Yuanyuan Yao, Yinghua Qin, Tao Wang, Mengmeng Tsang, Ivor Dai, Guang |
| contents | Text-to-image diffusion models have emerged as powerful tools for high-quality image generation and editing. Many existing approaches rely on text prompts as editing guidance. However, these methods are constrained by the need for manual prompt crafting, which can be time-consuming, introduce irrelevant details, and significantly limit editing performance. In this work, we propose optimizing semantic embeddings guided by attribute classifiers to steer text-to-image models toward desired edits, without relying on text prompts or requiring any training or fine-tuning of the diffusion model. We utilize classifiers to learn precise semantic embeddings at the dataset level. The learned embeddings are theoretically justified as the optimal representation of attribute semantics, enabling disentangled and accurate edits. Experiments further demonstrate that our method achieves high levels of disentanglement and strong generalization across different domains of data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_14254 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Instructing Text-to-Image Diffusion Models via Classifier-Guided Semantic Optimization Chang, Yuanyuan Yao, Yinghua Qin, Tao Wang, Mengmeng Tsang, Ivor Dai, Guang Computer Vision and Pattern Recognition Text-to-image diffusion models have emerged as powerful tools for high-quality image generation and editing. Many existing approaches rely on text prompts as editing guidance. However, these methods are constrained by the need for manual prompt crafting, which can be time-consuming, introduce irrelevant details, and significantly limit editing performance. In this work, we propose optimizing semantic embeddings guided by attribute classifiers to steer text-to-image models toward desired edits, without relying on text prompts or requiring any training or fine-tuning of the diffusion model. We utilize classifiers to learn precise semantic embeddings at the dataset level. The learned embeddings are theoretically justified as the optimal representation of attribute semantics, enabling disentangled and accurate edits. Experiments further demonstrate that our method achieves high levels of disentanglement and strong generalization across different domains of data. |
| title | Instructing Text-to-Image Diffusion Models via Classifier-Guided Semantic Optimization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.14254 |