PartStickers: Generating Parts of Objects for Rapid Prototyping
This addresses a specific need in design prototyping, such as for video game development, by enabling rapid creation of object parts, though it is incremental as it builds on existing text-to-image techniques.
The paper tackles the problem of generating isolated parts of objects for design prototyping, where existing text-to-image methods only produce entire objects. It proposes a part sticker generation method that outperforms state-of-the-art baselines in realism and text alignment while maintaining object-level capabilities.
Design prototyping involves creating mockups of products or concepts to gather feedback and iterate on ideas. While prototyping often requires specific parts of objects, such as when constructing a novel creature for a video game, existing text-to-image methods tend to only generate entire objects. To address this, we propose a novel task and method of ``part sticker generation", which entails generating an isolated part of an object on a neutral background. Experiments demonstrate our method outperforms state-of-the-art baselines with respect to realism and text alignment, while preserving object-level generation capabilities. We publicly share our code and models to encourage community-wide progress on this new task: https://partsticker.github.io.