Optimizing Negative Prompts for Enhanced Aesthetics and Fidelity in Text-To-Image Generation (2403.07605v3)
Abstract: In text-to-image generation, using negative prompts, which describe undesirable image characteristics, can significantly boost image quality. However, producing good negative prompts is manual and tedious. To address this, we propose NegOpt, a novel method for optimizing negative prompt generation toward enhanced image generation, using supervised fine-tuning and reinforcement learning. Our combined approach results in a substantial increase of 25% in Inception Score compared to other approaches and surpasses ground-truth negative prompts from the test set. Furthermore, with NegOpt we can preferentially optimize the metrics most important to us. Finally, we construct Negative Prompts DB (https://huggingface.co/datasets/mikeogezi/negopt_full), a publicly available dataset of negative prompts.
- Rlprompt: Optimizing discrete text prompts with reinforcement learning. arXiv preprint arXiv:2205.12548.
- Optimizing prompts for text-to-image generation. arXiv preprint arXiv:2212.09611.
- Clipscore: A reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718.
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
- The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691.
- Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190.
- Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM Computing Surveys, 55(9):1–35.
- P-tuning: Prompt tuning can be comparable to fine-tuning across scales and tasks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 61–68, Dublin, Ireland. Association for Computational Linguistics.
- Guanghui Qin and Jason Eisner. 2021. Learning how to ask: Querying lms with mixtures of soft prompts. arXiv preprint arXiv:2104.06599.
- Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748–8763. PMLR.
- Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research, 21(1):5485–5551.
- Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125.
- High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10684–10695.
- Improved techniques for training gans. Advances in neural information processing systems, 29.
- Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347.
- Sequence to sequence learning with neural networks. Advances in neural information processing systems, 27.
- Andrew Wong. 2023. How to use negative prompts?
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.