VPO: Aligning Text-to-Video Generation Models with Prompt Optimization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914014797234176 |
|---|---|
| author | Cheng, Jiale Lyu, Ruiliang Gu, Xiaotao Liu, Xiao Xu, Jiazheng Lu, Yida Teng, Jiayan Yang, Zhuoyi Dong, Yuxiao Tang, Jie Wang, Hongning Huang, Minlie |
| author_facet | Cheng, Jiale Lyu, Ruiliang Gu, Xiaotao Liu, Xiao Xu, Jiazheng Lu, Yida Teng, Jiayan Yang, Zhuoyi Dong, Yuxiao Tang, Jie Wang, Hongning Huang, Minlie |
| contents | Video generation models have achieved remarkable progress in text-to-video tasks. These models are typically trained on text-video pairs with highly detailed and carefully crafted descriptions, while real-world user inputs during inference are often concise, vague, or poorly structured. This gap makes prompt optimization crucial for generating high-quality videos. Current methods often rely on large language models (LLMs) to refine prompts through in-context learning, but suffer from several limitations: they may distort user intent, omit critical details, or introduce safety risks. Moreover, they optimize prompts without considering the impact on the final video quality, which can lead to suboptimal results. To address these issues, we introduce VPO, a principled framework that optimizes prompts based on three core principles: harmlessness, accuracy, and helpfulness. The generated prompts faithfully preserve user intents and, more importantly, enhance the safety and quality of generated videos. To achieve this, VPO employs a two-stage optimization approach. First, we construct and refine a supervised fine-tuning (SFT) dataset based on principles of safety and alignment. Second, we introduce both text-level and video-level feedback to further optimize the SFT model with preference learning. Our extensive experiments demonstrate that VPO significantly improves safety, alignment, and video quality compared to baseline methods. Moreover, VPO shows strong generalization across video generation models. Furthermore, we demonstrate that VPO could outperform and be combined with RLHF methods on video generation models, underscoring the effectiveness of VPO in aligning video generation models. Our code and data are publicly available at https://github.com/thu-coai/VPO. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20491 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VPO: Aligning Text-to-Video Generation Models with Prompt Optimization Cheng, Jiale Lyu, Ruiliang Gu, Xiaotao Liu, Xiao Xu, Jiazheng Lu, Yida Teng, Jiayan Yang, Zhuoyi Dong, Yuxiao Tang, Jie Wang, Hongning Huang, Minlie Computer Vision and Pattern Recognition Computation and Language Machine Learning Video generation models have achieved remarkable progress in text-to-video tasks. These models are typically trained on text-video pairs with highly detailed and carefully crafted descriptions, while real-world user inputs during inference are often concise, vague, or poorly structured. This gap makes prompt optimization crucial for generating high-quality videos. Current methods often rely on large language models (LLMs) to refine prompts through in-context learning, but suffer from several limitations: they may distort user intent, omit critical details, or introduce safety risks. Moreover, they optimize prompts without considering the impact on the final video quality, which can lead to suboptimal results. To address these issues, we introduce VPO, a principled framework that optimizes prompts based on three core principles: harmlessness, accuracy, and helpfulness. The generated prompts faithfully preserve user intents and, more importantly, enhance the safety and quality of generated videos. To achieve this, VPO employs a two-stage optimization approach. First, we construct and refine a supervised fine-tuning (SFT) dataset based on principles of safety and alignment. Second, we introduce both text-level and video-level feedback to further optimize the SFT model with preference learning. Our extensive experiments demonstrate that VPO significantly improves safety, alignment, and video quality compared to baseline methods. Moreover, VPO shows strong generalization across video generation models. Furthermore, we demonstrate that VPO could outperform and be combined with RLHF methods on video generation models, underscoring the effectiveness of VPO in aligning video generation models. Our code and data are publicly available at https://github.com/thu-coai/VPO. |
| title | VPO: Aligning Text-to-Video Generation Models with Prompt Optimization |
| topic | Computer Vision and Pattern Recognition Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2503.20491 |