In this report, I present an inpainting framework named \textit{ControlFill}, which involves training two distinct prompts: one for generating plausible objects within a designated mask (\textit{creation}) and another for filling the region by extending the background (\textit{removal}). During the inference stage, these learned embeddings guide a diffusion network that operates without requiring heavy text encoders. By adjusting the relative significance of the two prompts and employing classifier-free guidance, users can control the intensity of removal or creation. Furthermore, I introduce a method to spatially vary the intensity of guidance by assigning different scales to individual pixels.
View on arXiv@article{jeon2025_2503.04268,
title={ ControlFill: Spatially Adjustable Image Inpainting from Prompt Learning },
author={ Boseong Jeon },
journal={arXiv preprint arXiv:2503.04268},
year={ 2025 }
}