Techniques for model-based image operation in effect creation tools
AssigneeLemon Inc.
InventorsLakshminarayanan Vijayaraghavan, Guoqiang Xie, Jason Yang, Blake Garrett Fuselier, Guan-Bai Chen
Life of this patent
Estimating the term…
Abstract
Described are examples for image operations in an effect creation tool, including receiving, via a user interface provided for the effect creation tool, a natural language string requesting an operation related to obtaining or modifying an image, providing, to a model, an input including at least a portion of the natural language string, receiving, from the model, an image result output based on the input, and importing the image result as an asset in the effect creation tool.
Claims20
A computer-implemented method for image operations in an effect creation tool, comprising:
- receiving, via a user interface provided for the effect creation tool, a natural language string requesting an operation related to obtaining or modifying an image;
- providing, to multiple models, an input including at least a portion of the natural language string;
- receiving, from the multiple models, multiple image results output based on the input;
- displaying an indication of the multiple models, and, based on selection of one of the multiple models, a portion of the multiple image results corresponding to the one of the multiple models;
- and
- importing an image result of the multiple image results as an asset in the effect creation tool.
An apparatus for image operations in an effect creation tool, the apparatus comprising one or more processors and one or more non-transitory memories with instructions thereon, wherein the instructions upon execution by the one or more processors, cause the one or more processors to:
- receive, via a user interface provided for the effect creation tool, a natural language string requesting an operation related to obtaining or modifying an image;
- provide, to multiple models, an input including at least a portion of the natural language string;
- receive, from the multiple models, multiple image results output based on the input;
- display an indication of the multiple models, and, based on selection of one of the multiple models, a portion of the multiple image results corresponding to the one of the multiple models;
- and
- import an image result of the multiple image results as an asset in the effect creation tool.
One or more non-transitory computer-readable storage media storing instructions that when executed by one or more processors cause the one or more processors to execute a method for image operations in an effect creation tool, wherein the method comprises:
- receiving, via a user interface provided for the effect creation tool, a natural language string requesting an operation related to obtaining or modifying an image;
- providing, to multiple models, an input including at least a portion of the natural language string;
- receiving, from the multiple models, multiple image results output based on the input;
- displaying an indication of the multiple models, and, based on selection of one of the multiple models, a portion of the multiple image results corresponding to the one of the multiple models;
- and
- importing an image result of the multiple image results as an asset in the effect creation tool.
Dependencies are inferred from the claim text.