As recent advancements in large-scale Text-to-Image (T2I) diffusion models have yielded remarkable high-quality image generation, diverse downstream Image-to-Image (I2I) applications have emerged. Despite the impressive results achieved by these I2I models, their practical utility is hampered by their large model size and the computational burden of the iterative denoising process. In this paper, we explore the compression potential of these I2I models in a task-oriented manner and introduce a novel method for reducing both model size and the number of timesteps. Through extensive experiments, we observe key insights and use our empirical knowledge to develop practical solutions that aim for near-optimal results with minimal exploration costs. We validate the effectiveness of our method by applying it to InstructPix2Pix for image editing and StableSR for image restoration. Our approach achieves satisfactory output quality with 39.2% and 56.4% reduction in model footprint and 81.4% and 68.7% decrease in latency to InstructPix2Pix and StableSR, respectively.

翻译：随着近期大规模文本到图像（T2I）扩散模型的进展，已实现显著的高质量图像生成，由此涌现出多种下游图像到图像（I2I）应用。尽管这些I2I模型取得了令人印象深刻的结果，但其实际应用受限于庞大的模型尺寸和迭代去噪过程的计算负担。本文以面向任务的方式探索这些I2I模型的压缩潜力，并提出一种减少模型尺寸和时间步数量的新方法。通过大量实验，我们观察到关键洞见，并利用经验知识开发出旨在以最小探索成本实现近最优结果的实用解决方案。我们将该方法应用于InstructPix2Pix进行图像编辑以及StableSR进行图像恢复，验证了其有效性。我们的方法在模型体积上分别减少39.2%和56.4%，延迟分别降低81.4%和68.7%，同时保持了令人满意的输出质量。