AI RESEARCH
AceTone: Bridging Words and Colors for Conditional Image Grading
arXiv CS.CV
•
ArXi:2604.00530v1 Announce Type: new Color affects how we interpret image style and emotion. Previous color grading methods rely on patch-wise recoloring or fixed filter banks, struggling to generalize across creative intents or align with human aesthetic preferences. In this study, we propose AceTone, the first approach that s multimodal conditioned color grading within a unified framework. AceTone formulates grading as a generative color transformation task, where a model directly produces 3D-LUTs conditioned on text prompts or reference images.