Back to results
US 12,603,112 B2Granted
Video generation method, apparatus, device, and storage medium
AssigneeBeijing Zitiao Network Technology Co., Ltd.
InventorXinwei Li
Life of this patent
Estimating the term…
Abstract
The present disclosure provides a video generation method, an apparatus, a device, a storage medium, and a program product, and the method includes: in response to a first instruction triggered for an input text, generating first video editing data based on the input text, in which the first video editing data includes a first video clip and an audio clip, a first target video clip among the first video clip is a vacant clip; displaying the first video clip and the audio clip on a video editing track of a video editor; in response to triggering a second instruction for the target video clip on the video editor, filling the first target video clip with a target video to obtain second video editing data; generating a first video based on the second video editing data.
Claims19
A method of generating videos based on input texts, comprising:
- receiving text input by a user;
- in response to a first instruction triggered for the input text, generating first video editing data based on the input text, wherein the first instruction is indicative of generating the first video editing data based on the input text only, the first video editing data comprises at least one first video clip and at least one audio clip, the at least one first video clip and the at least one audio clip respectively correspond to at least one text clip divided from the input text, a first target video clip among the at least one first video clip and a target audio clip among the at least one audio clip respectively corresponds to a target text clip among the at least one text clip, the target audio clip is configured to be filled with a reading speech that matches the target text clip divided from the input text, and the first target video clip is a vacant clip;
- importing the first video editing data in a video editor so that the at least one first video clip and an audio track associated with the at least one audio clip are displayed on a video editing track of the video editor, wherein the first target video clip has a same track timeline interval as the target audio clip;
- in response to triggering a second instruction for the first target video clip on the video editor, filling the first target video clip with a first target video to obtain second video editing data, wherein the second instruction indicates a first target image material, and the first target video is a video obtained based on the first target image material;
- and
- generating a first video based on the target audio clip filled with the reading speech and the first target video clip filled with the video obtained based on the first target image material.
3 more elements
An electronic device, comprising:
- one or more processors;
- and
- a storage apparatus, configured to store one or more programs,
- wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement a video generation method, and the method comprises:
- receiving text input by a user;
- in response to a first instruction triggered for the input text, generating first video editing data based on the input text, wherein the first instruction is indicative of generating the first video editing data based on the input text only, the first video editing data comprises at least one first video clip and at least one audio clip, the at least one first video clip and the at least one audio clip respectively correspond to at least one text clip divided from the input text, a first target video clip among the at least one first video clip and a target audio clip among the at least one audio clip respectively corresponds to a target text clip among the at least one text clip, the target audio clip is configured to be filled with a reading speech that matches the target text clip divided from the input text, and the first target video clip is a vacant clip;
- importing the first video editing data in a video editor so that the at least one first video clip and an audio track associated with the at least one audio clip are displayed on a video editing track of the video editor, wherein the first target video clip has a same track timeline interval as the target audio clip;
- in response to triggering a second instruction for the first target video clip on the video editor, filling the first target video clip with a first target video to obtain second video editing data, wherein the second instruction indicates a first target image material, and the first target video is a video obtained based on the first target image material;
- and
- generating a first video based on the target audio clip filled with the reading speech and the first target video clip filled with the video obtained based on the first target image material.
7 more elements
A non-transitory computer-readable storage medium, storing a computer program, wherein the computer program, when executed by a processor, implements operations comprising:
- receiving text input by a user;
- in response to a first instruction triggered for the input text, generating first video editing data based on the input text, wherein the first instruction is indicative of generating the first video editing data based on the input text only, the first video editing data comprises at least one first video clip and at least one audio clip, the at least one first video clip and the at least one audio clip respectively correspond to at least one text clip divided from the input text, a first target video clip among the at least one first video clip and a target audio clip among the at least one audio clip respectively corresponds to a target text clip among the at least one text clip, the target audio clip is configured to be filled with a reading speech that matches the target text clip divided from the input text, and the first target video clip is a vacant clip;
- importing the first video editing data in a video editor so that the at least one first video clip and an audio track associated with the at least one audio clip are displayed on a video editing track of the video editor, wherein the first target video clip has a same track timeline interval as the target audio clip;
- in response to triggering a second instruction for the first target video clip on the video editor, filling the first target video clip with a first target video to obtain second video editing data, wherein the second instruction indicates a first target image material, and the first target video is a video obtained based on the first target image material;
- and
- generating a first video based on the target audio clip filled with the reading speech and the first target video clip filled with the video obtained based on the first target image material.
3 more elements
Dependencies are inferred from the claim text.