Systems and methods for generating videos based on selecting media content items and moods

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:
• acquiring a set of media content items;
• acquiring a mood indication;
• identifying a soundtrack based on the mood indication;
• determining one or more visual presentation features for the set of media content items based on the mood indication, the one or more visual presentation features including at least one of a zooming operation or a panning operation;
• utilizing a face detection process to identify one or more locations within one or more media content items, out of the set of media content items, at which one or more faces are depicted;
• applying one or more visual effects based on the one or more locations at which one or more faces are depicted;
• and
• dynamically generating a video content item in real-time based on the set of media content items, the one or more visual presentation features, the one or more visual effects, and the mood indication, the video content item including the soundtrack.

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:

• acquiring a set of media content items;
• acquiring a mood indication;
• identifying a soundtrack based on the mood indication;
• determining one or more visual presentation features for the set of media content items based on the mood indication, the one or more visual presentation features including at least one of a zooming operation or a panning operation;
• utilizing a face detection process to identify one or more locations within one or more media content items, out of the set of media content items, at which one or more faces are depicted;
• applying one or more visual effects based on the one or more locations at which one or more faces are depicted;
• and
• dynamically generating a video content item in real-time based on the set of media content items, the one or more visual presentation features, the one or more visual effects, and the mood indication, the video content item including the soundtrack.