基本信息
- 来源: arxiv
- 原始来源: https://arxiv.org/abs/2603.12261v1
- 作者: Mateusz Pach, Jessica Bader, Quentin Bouniot, Serge Belongie, Zeynep Akata
- 分类: cs.LG
- 论文时间: 2026-03-12T17:59:48Z
- 论文 PDF: https://arxiv.org/pdf/2603.12261v1.pdf
来源摘要/节选
Text-to-image generation models have advanced rapidly, yet achieving fine-grained control over generated images remains difficult, largely due to limited understanding of how semantic information is encoded. We develop an interpretation of the color representation in the Variational Autoencoder latent space of FLUX.1 [Dev], revealing a structure reflecting Hue, Saturation, and Lightness. We verify our Latent Color Subspace (LCS) interpretation by demonstrating that it can both predict and explicitly control color, introducing a fully training-free method in FLUX based solely on closed-form latent-space manipulation. Code is available at https://github.com/ExplainableML/LCS .
来源说明
当前只保存了官方论文摘要，不代表论文全文。请以原始来源为准。
本页只呈现已做哈希绑定的来源证据，不包含基于旧正文或缺失原文的扩展推断。