In this work, we propose a novel framework to enable diffusion models to adapt their generation quality based on real-time network bandwidth constraints. Traditional diffusion models produce high-fidelity images by performing a fixed number of denoising steps, regardless of downstream transmission limitations. However, in practical cloud-to-device scenarios, limited bandwidth often necessitates heavy compression, leading to loss of fine textures and wasted computation. To address this, we introduce a joint end-to-end training strategy where the diffusion model is conditioned on a target quality level derived from the available bandwidth. During training, the model learns to adaptively modulate the denoising process, enabling early-stop sampling that maintains perceptual quality appropriate to the target transmission condition. Our method requires minimal architectural changes and leverages a lightweight quality embedding to guide the denoising trajectory. Experimental results demonstrate that our approach significantly improves the visual fidelity of bandwidth-adapted generations compared to naive early-stopping, offering a promising solution for efficient image delivery in bandwidth-constrained environments. Code is available at: https://github.com/xzhang9308/BADiff.

翻译：本文提出了一种新颖的框架，使扩散模型能够根据实时网络带宽约束自适应地调整生成质量。传统的扩散模型通过执行固定次数的去噪步骤来生成高保真度图像，而忽略了下游传输限制。然而，在实际的云到设备场景中，有限的带宽通常需要大幅压缩，导致精细纹理丢失和计算资源浪费。为解决此问题，我们引入了一种联合端到端训练策略，其中扩散模型以从可用带宽推导出的目标质量级别为条件。在训练过程中，模型学习自适应地调制去噪过程，从而实现提前停止采样，保持与目标传输条件相适配的感知质量。我们的方法仅需最小的架构改动，并利用轻量级质量嵌入来引导去噪轨迹。实验结果表明，与简单的提前停止方法相比，我们的方法显著提高了带宽自适应生成结果的视觉保真度，为带宽受限环境中的高效图像传输提供了一个有前景的解决方案。代码发布于：https://github.com/xzhang9308/BADiff。