LooseControl: Lifting ControlNet for Generalized Depth Conditioning

1 KAUST 2 University College London, Adobe Research


We present LooseControl to allow generalized depth conditioning for diffusion-based image generation. ControlNet, the SOTA for depth-conditioned image generation, produces remarkable results but relies on having access to detailed depth maps for guidance. Creating such exact depth maps, in many scenarios, is challenging. This paper introduces a generalized version of depth conditioning that enables many new content-creation workflows. Specifically, we allow (C1) scene boundary control for loosely specifying scenes with only boundary conditions, and (C2) 3D box control for specifying layout locations of the target objects rather than the exact shape and appearance of the objects. Using LooseControl, along with text guidance, users can create complex environments (e.g., rooms, street views, etc.) by specifying only scene boundaries and locations of primary objects. Further, we provide two editing mechanisms to refine the results: (E1) 3D box editing enables the user to refine images by changing, adding, or removing boxes while freezing the style of the image. This yields minimal changes apart from changes induced by the edited boxes. (E2) Attribute editing proposes possible editing directions to change one particular aspect of the scene, such as the overall object density or a particular object. Extensive tests and comparisons with baselines demonstrate the generality of our method. We believe that LooseControl can become an important design tool for easily creating complex environments and be extended to other forms of guidance channels.

3D Box Editing

Our 3D Box Editing allows users to interactively edit the 3D boxes representing objects in the scene. Users can change the position, size, and orientation of 3D boxes as well as modify their shape by splitting, sculpting etc. Our UI (to-be-released) is designed to be intuitive and easy to use, allowing users to quickly create and edit the scenes to their liking.

Interactive 3D Box Editing

Source Image

Interactive Image

Scene Boundary Control