按年被提到
20232023 · 1 次2026
视觉、语音与图像生成›扩散模型·arXiv:2307.01952 · cs.CV

SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas Müller, Joe Penna, Robin Rombach · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-12-25 · 最近 2024-09-20
2不同的人
2活跃月份
2讨论串
1,222被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We present SDXL, a latent diffusion model for text-to-image synthesis. Compared to previous versions of Stable Diffusion, SDXL leverages a three times larger UNet backbone: The increase of model parameters is mainly due to more attention blocks and a larger cross-attention context as SDXL uses a second text encoder. We design multiple novel conditioning schemes and train SDXL on multiple aspect ratios. We also introduce a refinement model which is used to improve the visual fidelity of samples generated by SDXL using a post-hoc image-to-image technique. We demonstrate that SDXL shows drastically improved performance compared the previous versions of Stable Diffusion and achieves results competitive with those of black-box state-of-the-art image generators. In the spirit of promoting open research and fostering transparency in large model training and evaluation, we provide access to code and model weights at https://github.com/Stability-AI/generative-models

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gwern · 2024-09

“It was also solved by the even easier approach of aspect ratio conditioning, where you just pass in the dimensions of the crop to the NN like SDXL: https://arxiv.org/pdf/2307.01952#page=3&org=stability”

New AI diffusion model approach solves the aspect ratio problem原评论 ↗
被提交为 story · 1 次