Uncovers an emergent Hue-Saturation-Lightness (HSL) subspace in FLUX.1's VAE latent space, allowing for precise, training-free color control.
arXiv · March 13, 2026 · 2603.12261
Why it matters
It proves that advanced text-to-image models develop human-interpretable internal representations of color. This discovery enables a fully closed-form, training-free method to manipulate image color without the need for LoRAs or additional adapters.
From the abstract
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 explic