CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912417829617664 |
|---|---|
| author | Fu, Minghao Wang, Guo-Hua Cao, Liangfu Chen, Qing-Guo Xu, Zhao Luo, Weihua Zhang, Kaifu |
| author_facet | Fu, Minghao Wang, Guo-Hua Cao, Liangfu Chen, Qing-Guo Xu, Zhao Luo, Weihua Zhang, Kaifu |
| contents | Diffusion models have emerged as a dominant approach for text-to-image generation. Key components such as the human preference alignment and classifier-free guidance play a crucial role in ensuring generation quality. However, their independent application in current text-to-image models continues to face significant challenges in achieving strong text-image alignment, high generation quality, and consistency with human aesthetic standards. In this work, we for the first time, explore facilitating the collaboration of human performance alignment and test-time sampling to unlock the potential of text-to-image models. Consequently, we introduce CHATS (Combining Human-Aligned optimization and Test-time Sampling), a novel generative framework that separately models the preferred and dispreferred distributions and employs a proxy-prompt-based sampling strategy to utilize the useful information contained in both distributions. We observe that CHATS exhibits exceptional data efficiency, achieving strong performance with only a small, high-quality funetuning dataset. Extensive experiments demonstrate that CHATS surpasses traditional preference alignment methods, setting new state-of-the-art across various standard benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12579 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation Fu, Minghao Wang, Guo-Hua Cao, Liangfu Chen, Qing-Guo Xu, Zhao Luo, Weihua Zhang, Kaifu Computer Vision and Pattern Recognition Diffusion models have emerged as a dominant approach for text-to-image generation. Key components such as the human preference alignment and classifier-free guidance play a crucial role in ensuring generation quality. However, their independent application in current text-to-image models continues to face significant challenges in achieving strong text-image alignment, high generation quality, and consistency with human aesthetic standards. In this work, we for the first time, explore facilitating the collaboration of human performance alignment and test-time sampling to unlock the potential of text-to-image models. Consequently, we introduce CHATS (Combining Human-Aligned optimization and Test-time Sampling), a novel generative framework that separately models the preferred and dispreferred distributions and employs a proxy-prompt-based sampling strategy to utilize the useful information contained in both distributions. We observe that CHATS exhibits exceptional data efficiency, achieving strong performance with only a small, high-quality funetuning dataset. Extensive experiments demonstrate that CHATS surpasses traditional preference alignment methods, setting new state-of-the-art across various standard benchmarks. |
| title | CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.12579 |