arXiv:2603.12261cs.LGcs.AI2026-03中稿 · ICML

发现FLUX.1模型潜空间中的颜色结构,实现无需训练的颜色精准控制。

The Latent Color Subspace: Emergent Order in High-Dimensional Chaos

  • 通过解析VAE潜空间,揭示色调、饱和度、明度的显性结构。
  • 仅用闭式潜空间操作,即可准确预测并控制生成图像颜色。
  • 适合需要无训练色彩调控的生成模型研究者使用。

文本到图像生成模型发展迅速,但对生成图像进行细粒度控制仍具挑战,主要源于对语义信息编码机制理解不足。本文深入分析FLUX.1[Dev]变分自编码器(VAE)潜空间中的颜色表征,揭示其蕴含色调(Hue)、饱和度(Saturation)和明度(Lightness)的结构。通过实证验证,所提出的潜空间颜色子空间(Latent Color Subspace, LCS)可同时实现颜色预测与显式控制,提出一种完全无需训练的方法,仅依赖闭式潜空间操作。代码已开源:https://github.com/ExplainableML/LCS。

原文摘要 · Abstract (English)

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.

图像生成潜空间解析颜色控制VAE

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。