视觉生成中文本条件的缩放特性研究

AI 摘要

该研究探讨了视觉生成中文本条件的缩放特性，发现扩散损失与提示中的结构化语言量相关，而非令牌数量。研究者提出了两种度量方法（GPG和ED），并据此改进了可扩散性和可提示性，通过构建结构化提示和训练提示器。最终系统在多个基准上超越了所有评估的开源模型，并在大多数评估中匹配或超过最强的闭源模型。

正文节选

Scaling Properties of Text Conditioning in Visual Generation Abstract We study empirical scaling properties for text conditioning in visual generation. Such properties have rarely been measured because diffusion loss does not scale with the number of tokens in natural-language prompts. Surprisingly, we find that the converged diffusion loss scales with the amount of structured language in the prompt. To quantify structured language, we adapt two complementary measures: a white-box likelihood met

发布时间：—

抓取时间：2026-08-03 16:12

来源机构：Hugging Face