We address the long-standing problem of how to learn effective pixel-based
image diffusion models at scale, introducing a remarkably simple greedy growing
method for stable training of large-scale, high-resolution models. without the
needs for cascaded super-resolution components. The key insight stems from
careful pre-training of core components, namely, those responsible for
text-to-image alignment {\it vs.} high-resolution rendering. We first
demonstrate the benefits of scaling a {\it Shallow UNet}, with no
down(up)-sampling enc(dec)oder. Scaling its deep core layers is shown to
improve alignment, object structure, and composition. Building on this core
model, we propose a greedy algorithm that grows the architecture into
high-resolution end-to-end models, while preserving the integrity of the
pre-trained representation, stabilizing training, and reducing the need for
large high-resolution datasets. This enables a single stage model capable of
generating high-resolution images without the need of a super-resolution
cascade. Our key results rely on public datasets and show that we are able to
train non-cascaded models up to 8B parameters with no further regularization
schemes. Vermeer, our full pipeline model trained with internal datasets to
produce 1024x1024 images, without cascades, is preferred by 44.0% vs. 21.4%
human evaluators over SDXL.

我们提出了一种非常简单的贪婪生长方法，用于稳定训练大规模、高分辨率模型的像素级图像扩散模型，避免了级联超分辨率组件的需求。实现这一目标的关键在于仔细预训练核心组件，即负责文本到图像对齐和高分辨率渲染的组件。在利用核心模型进行扩展的基础上，我们提出了一种贪婪算法，将架构扩展到高分辨率端到端模型，同时保持预训练表示的完整性，稳定训练过程，并减少对大规模高分辨率数据集的需求。这使得我们能够生成高分辨率图像的单阶段模型，而无需超分辨率级联。我们的主要结果基于公共数据集，表明我们能够训练出高达 80 亿参数的非级联模型，而无需进一步的正则化方案。Vermeer 是我们的完整管道模型，使用内部数据集训练以生成 1024x1024 图像，在 SDXL 上，相较于人类评估者的 21.4％，它被 44.0％的评估者选择。