Diffusion-based generative models excel in perceptually impressive synthesis but face challenges in interpretability. This paper introduces ToddlerDiffusion, an interpretable 2D diffusion image-synthesis framework inspired by the human generation system. Unlike traditional diffusion models with opaque denoising steps, our approach decomposes the generation process into simpler, interpretable stages; generating contours, a palette, and a detailed colored image. This not only enhances overall performance but also enables robust editing and interaction capabilities. Each stage is meticulously formulated for efficiency and accuracy, surpassing Stable-Diffusion (LDM). Extensive experiments on datasets like LSUN-Churches and COCO validate our approach, consistently outperforming existing methods. ToddlerDiffusion achieves notable efficiency, matching LDM performance on LSUN-Churches while operating three times faster with a 3.76 times smaller architecture. Our source code is provided in the supplementary material and will be publicly accessible.

ToddlerDiffusion是一种可解释的2D扩散图像合成框架，受到人类生成系统的启发，它将生成过程分解成简单且可解释的阶段，生成轮廓、调色板和详细彩色图像，不仅提高了整体性能，还实现了强大的编辑和交互能力。通过在像LSUN-Churches和COCO这样的数据集上进行广泛实验验证，我们的方法始终优于现有方法。ToddlerDiffusion在LSUN-Churches上与LDM性能相匹配，同时以三倍速且架构大小减少3.76倍的速度运行。附加材料中提供了我们的源代码，并将公开访问。

幼儿扩散：快速可解释可控扩散模型