A user may use a client device to create a draft document by interacting with a server. The user provides an image in a message (e.g., a multimedia messaging service (MMS) message) from a different device. The server receives the image and modifies the draft (e.g., by updating a web page being displayed on the client device). This process allows the user to type text for a draft using a client device that includes a keyboard (e.g., a desktop or laptop computer) and to add an image to the draft using a second device that includes a camera (e.g., a mobile phone or tablet computer) without having to transfer the image from the second device to the first device.