按年被提到
20242024 · 1 次2026
视觉、语音与图像生成›超分辨率与图像压缩·arXiv:2401.11605 · cs.CV

Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers

Katherine Crowson, Stefan Andreas Baumann, Alex Birch, Tanishq Mathew Abraham, Daniel Z. Kaplan, Enrico Shippole · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-01-23 · 最近 2025-06-27
2不同的人
2活跃月份
2讨论串
11被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We present the Hourglass Diffusion Transformer (HDiT), an image generative model that exhibits linear scaling with pixel count, supporting training at high-resolution (e.g. $1024 \times 1024$) directly in pixel-space. Building on the Transformer architecture, which is known to scale to billions of parameters, it bridges the gap between the efficiency of convolutional U-Nets and the scalability of Transformers. HDiT trains successfully without typical high-resolution training techniques such as multiscale architectures, latent autoencoders or self-conditioning. We demonstrate that HDiT performs competitively with existing models on ImageNet $256^2$, and sets a new state-of-the-art for diffusion models on FFHQ-$1024^2$.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论godelski · 2025-06

“As far as I'm aware, this is the largest Normalizing Flow that exists, and I think they undermined their work by not mentioning this... Their ImageNet model (4_1024_8_8_0.05[0]) is ~820M while AFHQ is ~472M. Prior to that there is DenseFlow[1] and MaCow[2], which are both <200M parameters. For more comparison, that makes DenseFlow and MaCow smaller than …”

Normalizing Flows Are Capable Generative Models原评论 ↗
被提交为 story · 1 次