A method, a system, and a computer program product code for generating a series of still images from an input video file are provided. The series of still images may include, but are not limited to, a comic strip and a storyboard. The method includes extracting audio and visual frames from the video file. Thereafter, basic units of the video file are identified. The basic units are exposition (beginning), conflict (middle), and resolution (end). Thereafter, key frames are extracted from the basic units based on at least one of audio frames, visual frames, and a combination of the visual frames and the audio frames. Then, the extracted key frames are manipulated to output a series of still images. Subsequently, narration in the form of audio or text is attached to the still images to generate at least one of comic strips and storyboards.