Video generating method and device

A system, comprising:

• at least one processor;
• and
• at least one memory communicatively coupled to the at least one processor and comprising computer-readable instructions that upon execution by the at least one processor cause the at least one processor to perform operations comprising:
• acquiring a target video frame among a plurality of frames of a target video;
• acquiring at least one comment file corresponding to the target video frame, wherein the at least one comment file comprises a plurality of pieces of comment data;
• determining a mask file corresponding to the target video frame, wherein the mask file is generated based on recognizing a target object in the target video frame;
• determining a display coordinate of each of the plurality of pieces of comment data in the target video frame;
• determining each of the plurality of pieces of comment data is hidden or rendered into the target video frame based on the mask file and the display coordinate of each of the plurality of pieces of comment data;
• and
• generating a new frame corresponding to the target frame, wherein the new frame comprises content of the target frame and at least one subset of the plurality of pieces of comment data embedded in the target frame.

A non-transitory computer-readable storage medium, storing computer-readable instructions that upon execution by a processor cause the processor to implement operations comprising:

• acquiring a target video frame among a plurality of frames of a target video;
• acquiring at least one comment file corresponding to the target video frame, wherein the at least one comment file comprises a plurality of pieces of comment data;
• determining a mask file corresponding to the target video frame, wherein the mask file is generated based on recognizing a target object in the target video frame;
• determining a display coordinate of each of the plurality of pieces of comment data in the target video frame;
• determining each of the plurality of pieces of comment data is hidden or rendered into the target video frame based on the mask file and the display coordinate of each of the plurality of pieces of comment data;
• and
• generating a new frame corresponding to the target frame, wherein the new frame comprises content of the target frame and at least one subset of the plurality of pieces of comment data embedded in the target frame.