Video-Content System with Narrative-Based Video Content Generation Feature

A non-transitory computer-readable medium having stored thereon program instructions that upon execution by a computing system, cause performance of a set of acts comprising:

• obtaining input data, wherein the input data includes story description text;
• providing the obtained input data to a narration model and responsively receiving generated narrative text;
• identifying, from among the generated narrative text, a subset of text, wherein identifying, from among the generated narrative text, the subset of text comprises identifying, from among the generated narrative text, the subset of text based on the identified subset of text satisfying one or more conditions of a condition set, wherein a condition in the condition set is a condition that the subset of text itself has a predefined characteristic, wherein the condition set includes a condition that the subset of text includes a person's name, a proper noun, a location, an activity, an object, an animal, or an instance of punctuation;
• providing the identified subset of text to an image generation model and responsively receiving generated images from the image generation model, wherein the image generation model uses at least the identified subset of text to generate the generated images, such that the image generation model generates the generated images after receiving the identified subset of text;
• providing the generated images to an animation model and responsively receiving generated video segments;
• combining at least the generated video segments to generate video content;
• and
• outputting for presentation, the generated video content.

A computing system configured for performing a set of acts comprising:

• obtaining input data, wherein the input data includes story description text;
• providing the obtained input data to a narration model and responsively receiving generated narrative text;
• identifying, from among the generated narrative text, a subset of text, wherein identifying, from among the generated narrative text, the subset of text comprises identifying, from among the generated narrative text, the subset of text based on the identified subset of text satisfying one or more conditions of a condition set, wherein a condition in the condition set is a condition that the subset of text itself has a predefined characteristic, wherein the condition set includes a condition that the subset of text includes a person's name, a proper noun, a location, an activity, an object, an animal, or an instance of punctuation;
• providing the identified subset of text to an image generation model and responsively receiving generated images from the image generation model, wherein the image generation model uses at least the identified subset of text to generate the generated images, such that the image generation model generates the generated images after receiving the identified subset of text;
• providing the generated images to an animation model and responsively receiving generated video segments;
• combining at least the generated video segments to generate video content;
• and
• outputting for presentation, the generated video content.