Abstract: One or more aspects of the method, apparatus, and non-transitory computer readable medium include obtaining an original image, a scene graph describing elements of the original image, and a description of a modification to the original image. The one or more aspects further include updating the scene graph based on the description of the modification. The one or more aspects further include generating a modified image using an image generation neural network based on the updated scene graph, wherein the modified image incorporates content based on the original image and the description of the modification.

Abstract: A method includes receiving an input including a target style and a glyph. The method further includes masking the glyph. The method further includes generating a stylized glyph by a glyph generative model using the masked glyph. The method further includes rendering the stylized glyph as a unicode stylized glyph.

Abstract: A method includes receiving a natural language description of an image to be generated using a machine learning model. The method further includes extracting, from the natural language description of the image to be generated, a control element and a sub-prompt. The method further includes identifying a relationship between the control element and the sub-prompt based on the natural language description of the image to be generated. The method further includes generating, by the machine learning model, an image based on the control element, the sub-prompt, and the relationship. The image includes visual elements corresponding to the control element and the sub-prompt.

Abstract: A method includes receiving a description of content to be generated using a generative model. The received description of content is associated with a user profile. The method further includes determining a semantic term based on the description of content. The method further includes generating a user-specific template including the semantic term and a user preference associated with the user profile. The method further includes generating the content using the generative model based on the user-specific template. The method further includes outputting the content for display on a target user device.

Abstract: Systems and methods seamlessly blend edited and unedited regions of an image. A computing system crops an input image around a region to be edited. The system applies an affine transformation to rotate the cropped input image. The system provides the rotated cropped input image as input to a machine learning model to generate a latent space representation of the rotated cropped input image. The system edits the latent space representation and provides the edited latent space representation to a generator neural network to generate a generated edited image. The system applies an inverse affine transformation to rotate the generated edited image and aligns an identified segment of the rotated generated edited image with an identified corresponding segment of the input image to produce an aligned rotated generated edited image. The system blends the aligned rotated generated edited image with the input image to generate an edited output image.

Abstract: Systems and methods combine an input image with an edited image generated using a generator neural network to preserve detail from the original image. A computing system provides an input image to a machine learning model to generate a latent space representation of the input image. The system provides the latent space representation to a generator neural network to generate a generated image. The system generates multiple scale representations of the input image, as well as multiple scale representations of the generated image. The system generates a first combined image based on first scale representations of the images and a first value. The system generates a second combined image based on second scale representations of the images and a second value. The system blends the first combined image with the second combined image to generate an output image.

Abstract: An illustrator system accesses a multi-element document, the multi-element document including a plurality of elements. The illustrator system determines, for each of the plurality of elements, an element-specific topic distribution comprising a ranked list of topics. The illustrator system creates a first aggregated topic distribution from the determined element-specific topic distributions. The illustrator system determines a global intent for the multi-element document, the global intent including one or more terms from the first aggregated topic distribution. The illustrator system queries a database using the global intent to retrieve a substitute element. The illustrator system generates a replacement multi-element document that includes a substitute element in place of an element in the multi-element document The at least one substitute element is different from the element in the displayed multi-element document.

Abstract: An illustrator system accesses a multi-element document including a plurality of elements. The illustrator system selects, from the plurality of elements, a selected element. The illustrator system generates a replacement multi-element document that includes a substitute element in place of the selected element in the multi-element document, wherein the substitute element is different from the selected element. The illustrator system displays, via a user interface with the multi-element document, a preview of the replacement multi-element document providing a view of the replacement multi-element document, wherein the view of the replacement multi-element document is focused to depict the substitute element.

Abstract: Various disclosed embodiments are directed to classify or determining an image style of a target image according to a consumer application based on determining a similarity score between the image style of a target image and one or more other predetermined image styles of the consumer application. Various disclosed embodiments can resolve image style transfer destructiveness functionality by making various layers of predetermined image styles modifiable. Further various embodiments resolve tedious manual user input requirements and reduce computing resource consumption, among other things.

Abstract: An illustrator system accesses a multi-element document, the multi-element document including a plurality of elements. The illustrator system determines, for each of the plurality of elements, an element-specific topic distribution comprising a ranked list of topics. The illustrator system creates a first aggregated topic distribution from the determined element-specific topic distributions. The illustrator system determines a global intent for the multi-element document, the global intent including one or more terms from the first aggregated topic distribution. The illustrator system queries a database using the global intent to retrieve a substitute element. The illustrator system generates a replacement multi-element document that includes a substitute element in place of an element in the multi-element document The at least one substitute element is different from the element in the displayed multi-element document.

Abstract: Various disclosed embodiments are directed to classify or determining an image style of a target image according to a consumer application based on determining a similarity score between the image style of a target image and one or more other predetermined image styles of the consumer application. Various disclosed embodiments can resolve image style transfer destructiveness functionality by making various layers of predetermined image styles modifiable. Further various embodiments resolve tedious manual user input requirements and reduce computing resource consumption, among other things.

Abstract: The present disclosure describes systems, non-transitory computer-readable media, and methods that intelligently sense digital user context across client devices applications utilizing a dynamic sensor graph framework and then utilize a persistent context store to generate flexible digital recommendations across digital applications. In one or more embodiments, the disclosed systems utilize triggers to select and activate one or more sensor graphs. These sensor graphs can include software sensors arranged according to an architecture of dependencies and subject to various constraints. The underlying architecture of dependencies and constraints in each sensor graph allows the disclosed systems to avoid race-conditions in persisting actionable user-context based signals, verify the validity of sensor output through the sensor graph, generate user-context based recommendations across multiple related applications, and accommodate a specific latency/refresh rate of context values.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating modified digital images by utilizing a patch match algorithm to generate nearest neighbor fields for a second digital image based on a nearest neighbor field associated with a first digital image. For example, the disclosed systems can identify a nearest neighbor field associated with a first digital image of a first resolution. Based on the nearest neighbor field of the first digital image, the disclosed systems can utilize a patch match algorithm to generate a nearest neighbor field for a second digital image of a second resolution larger than the first resolution. The disclosed systems can further generate a modified digital image by filling a target region of the second digital image utilizing the generated nearest neighbor field.

Abstract: The present disclosure describes systems, non-transitory computer-readable media, and methods that intelligently sense digital user context across client devices applications utilizing a dynamic sensor graph framework and then utilize a persistent context store to generate flexible digital recommendations across digital applications. In one or more embodiments, the disclosed systems utilize triggers to select and activate one or more sensor graphs. These sensor graphs can include software sensors arranged according to an architecture of dependencies and subject to various constraints. The underlying architecture of dependencies and constraints in each sensor graph allows the disclosed systems to avoid race-conditions in persisting actionable user-context based signals, verify the validity of sensor output through the sensor graph, generate user-context based recommendations across multiple related applications, and accommodate a specific latency/refresh rate of context values.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating modified digital images by utilizing a patch match algorithm to generate nearest neighbor fields for a second digital image based on a nearest neighbor field associated with a first digital image. For example, the disclosed systems can identify a nearest neighbor field associated with a first digital image of a first resolution. Based on the nearest neighbor field of the first digital image, the disclosed systems can utilize a patch match algorithm to generate a nearest neighbor field for a second digital image of a second resolution larger than the first resolution. The disclosed systems can further generate a modified digital image by filling a target region of the second digital image utilizing the generated nearest neighbor field.

Abstract: Systems and methods train an encoder neural network for fast and accurate projection into the latent space of a Generative Adversarial Network (GAN). The encoder is trained by providing an input training image to the encoder and producing, by the encoder, a latent space representation of the input training image. The latent space representation is provided as input to the GAN to generate a generated training image. A latent code is sampled from a latent space associated with the GAN and the sampled latent code is provided as input to the GAN. The GAN generates a synthetic training image based on the sampled latent code. The sampled latent code is provided as input to the encoder to produce a synthetic training code. The encoder is updated by minimizing a loss between the generated training image and the input training image, and the synthetic training code and the sampled latent code.

Abstract: Systems and methods combine an input image with an edited image generated using a generator neural network to preserve detail from the original image. A computing system provides an input image to a machine learning model to generate a latent space representation of the input image. The system provides the latent space representation to a generator neural network to generate a generated image. The system generates multiple scale representations of the input image, as well as multiple scale representations of the generated image. The system generates a first combined image based on first scale representations of the images and a first value. The system generates a second combined image based on second scale representations of the images and a second value. The system blends the first combined image with the second combined image to generate an output image.

Abstract: Systems and methods train and apply a specialized encoder neural network for fast and accurate projection into the latent space of a Generative Adversarial Network (GAN). The specialized encoder neural network includes an input layer, a feature extraction layer, and a bottleneck layer positioned after the feature extraction layer. The projection process includes providing an input image to the encoder and producing, by the encoder, a latent space representation of the input image. Producing the latent space representation includes extracting a feature vector from the feature extraction layer, providing the feature vector to the bottleneck layer as input, and producing the latent space representation as output. The latent space representation produced by the encoder is provided as input to the GAN, which generates an output image based upon the latent space representation. The encoder is trained using specialized loss functions including a segmentation loss and a mean latent loss.

Abstract: Systems and methods seamlessly blend edited and unedited regions of an image. A computing system crops an input image around a region to be edited. The system applies an affine transformation to rotate the cropped input image. The system provides the rotated cropped input image as input to a machine learning model to generate a latent space representation of the rotated cropped input image. The system edits the latent space representation and provides the edited latent space representation to a generator neural network to generate a generated edited image. The system applies an inverse affine transformation to rotate the generated edited image and aligns an identified segment of the rotated generated edited image with an identified corresponding segment of the input image to produce an aligned rotated generated edited image. The system blends the aligned rotated generated edited image with the input image to generate an edited output image.

Abstract: In implementations of systems for generating suggestions with knowledge graph embedding vectors, a computing device implements a suggestion system to receive input data describing user interactions with an application for editing digital content. The suggestion system generates input embedding vectors based on the user interactions with the application and determines an item based on the input embedding vectors and knowledge graph embedding vectors generated from nodes of a knowledge graph describing a tutorial for editing digital content. The suggestion system generates an indication of the item for display in a user interface of a display device.