Abstract: The technology described herein is directed to spatial interface for multi-modal input to artificial intelligence (AI) powered tools. The interface allows for a first mode of input, such as selection of one or more objects using a movable window that can be resized and reshaped by a user. In addition, the interface allows for a second mode of input, such as text or voice commands. The AI powered tools accept the inputs from the first and second modes and dynamically generates a response.

Abstract: Implementations relate to display and update of panoramic image montages. In some implementations, a computer-implemented method includes causing one or more view portions of a panoramic image montage to be displayed in a display view of a display device. First user input is received at a first time while at least one of the one or more view portions of the panoramic image montage is displayed. In response to the first user input, an image feed is caused to be displayed, the image feed including a plurality of image frames captured by a camera. Second user input is received at a second time later than the first time while a particular view portion of the panoramic image montage is displayed in the display view. In response to the second user input, the particular view portion is updated based on the image feed.