We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution (SR). Specifically, by employing our time-aware encoder, we can achieve promising restoration results without altering the pre-trained synthesis model, thereby preserving the generative prior and minimizing training cost. To remedy the loss of fidelity caused by the inherent stochasticity of diffusion models, we introduce a controllable feature wrapping module that allows users to balance quality and fidelity by simply adjusting a scalar value during the inference process. Moreover, we develop a progressive aggregation sampling strategy to overcome the fixed-size constraints of pre-trained diffusion models, enabling adaptation to resolutions of any size. A comprehensive evaluation of our method using both synthetic and real-world benchmarks demonstrates its superiority over current state-of-the-art approaches.

翻译：我们提出了一种新颖的方法，利用预训练文本到图像扩散模型中蕴含的先验知识进行盲超分辨率（SR）。具体而言，通过采用我们的时间感知编码器，我们无需修改预训练合成模型即可实现令人满意的复原结果，从而保留了生成先验并最大限度地降低了训练成本。为了解决扩散模型固有随机性导致的重建保真度损失，我们引入了一个可控特征包裹模块，使用户能够在推理过程中仅通过调整一个标量值来平衡质量与保真度。此外，我们开发了一种渐进式聚合采样策略，以克服预训练扩散模型的固定尺寸限制，使其能够适应任意分辨率的图像。通过使用合成基准和真实世界基准对我们的方法进行全面评估，证明了其相较于当前最先进方法的优越性。