ClickDiffusion: Harnessing LLMs for Interactive Precise Image Editing
This addresses the challenge of precise image manipulation for users who need to edit specific objects in complex scenes, representing an incremental improvement over existing text-based methods.
The paper tackles the problem of precisely specifying image transformations with natural language alone, which is difficult for tasks like changing a specific object among similar ones, and proposes ClickDiffusion, a system that combines natural language with visual feedback to enable precise image editing using LLMs.
Recently, researchers have proposed powerful systems for generating and manipulating images using natural language instructions. However, it is difficult to precisely specify many common classes of image transformations with text alone. For example, a user may wish to change the location and breed of a particular dog in an image with several similar dogs. This task is quite difficult with natural language alone, and would require a user to write a laboriously complex prompt that both disambiguates the target dog and describes the destination. We propose ClickDiffusion, a system for precise image manipulation and generation that combines natural language instructions with visual feedback provided by the user through a direct manipulation interface. We demonstrate that by serializing both an image and a multi-modal instruction into a textual representation it is possible to leverage LLMs to perform precise transformations of the layout and appearance of an image. Code available at https://github.com/poloclub/ClickDiffusion.