LumiCtrl : Learning Illuminant Prompts for Lighting Control in Personalized Text-to-Image Models
This addresses a crucial need for content designers to manipulate lighting for mood and aesthetics in generated images, though it is an incremental improvement over existing personalization methods.
The paper tackles the problem of precise illuminant control in text-to-image models by introducing LumiCtrl, which learns illuminant prompts from a single object image, resulting in significantly better illuminant fidelity, aesthetic quality, and scene coherence compared to baselines, with strong user preference in studies.
Current text-to-image (T2I) models have demonstrated remarkable progress in creative image generation, yet they still lack precise control over scene illuminants, which is a crucial factor for content designers aiming to manipulate the mood, atmosphere, and visual aesthetics of generated images. In this paper, we present an illuminant personalization method named LumiCtrl that learns an illuminant prompt given a single image of an object. LumiCtrl consists of three basic components: given an image of the object, our method applies (a) physics-based illuminant augmentation along the Planckian locus to create fine-tuning variants under standard illuminants; (b) edge-guided prompt disentanglement using a frozen ControlNet to ensure prompts focus on illumination rather than structure; and (c) a masked reconstruction loss that focuses learning on the foreground object while allowing the background to adapt contextually, enabling what we call contextual light adaptation. We qualitatively and quantitatively compare LumiCtrl against other T2I customization methods. The results show that our method achieves significantly better illuminant fidelity, aesthetic quality, and scene coherence compared to existing personalization baselines. A human preference study further confirms strong user preference for LumiCtrl outputs. The code and data will be released upon publication.