Combining faces from source images with target images based on search queries

A system comprising:

• at least one processor;
• and
• a memory storing instructions that, when executed by the at least one processor, cause the system to perform:
• accessing a source image depicting a face;
• determining a portion of the source image that depicts the face;
• identifying a pose attribute associated with the face depicted via the portion of the source image, wherein the pose attribute is at least one of a head tilt or a head turn;
• acquiring a search query based on user input wherein the search query specifies metadata about an appearance of a person in a target image;
• identifying a set of one or more target images having metadata that satisfies the search query;
• identifying, within each target image from the set of one or more target images, a respective location where the portion of the source image is to be rendered;
• determining that each target image from the set of one or more target images has at least a threshold confidence level of matching the pose attribute associated with the face;
• and
• rendering, for each target image from the set of one or more target images, at the respective location within each target image, the portion of the source image to produce a set of one or more combined images, wherein each combined image in the set of one or more combined images includes the portion of the source image rendered at the respective location within each target image.

A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:

• accessing a source image depicting a face;
• determining a portion of the source image that depicts the face;
• identifying a pose attribute associated with the face depicted via the portion of the source image, wherein the pose attribute is at least one of a head tilt or a head turn;
• acquiring a search query based on user input wherein the search query specifies metadata about an appearance of a person in a target image;
• identifying a set of one or more target images having metadata that satisfies the search query;
• identifying, within each target image from the set of one or more target images, a respective location where the portion of the source image is to be rendered;
• determining that each target image from the set of one or more target images has at least a threshold confidence level of matching the pose attribute associated with the face;
• and
• rendering, for each target image from the set of one or more target images, at the respective location within each target image, the portion of the source image to produce a set of one or more combined images, wherein each combined image in the set of one or more combined images includes the portion of the source image rendered at the respective location within each target image.