Abstract: Techniques include receiving, a first image and modification data generated from a user input received at a client device, wherein the modification data describes characteristics for generating an avatar. The techniques further include using an AI model to generate the avatar based at least in part on the first image and the modification data, the AI model selected based at least in part on the user input or an avatar generation context, wherein the avatar is configured for use in a virtual environment, and wherein the AI model is configured to generate the avatar having an avatar style consistent with a style of the avatar generation context. The techniques further include applying the avatar to the virtual environment.

Abstract: A method for image generation. The method including identifying a plurality of features of an image. The method including classifying each of the plurality of features using an artificial intelligence (AI) model trained to identify features in a plurality of images, wherein the plurality of features is classified as a plurality of labels, wherein the image is provided as input to the AI model. The method including receiving feedback for a label, wherein the feedback is associated with a user. The method including modifying a label based on the feedback. The method including updating the plurality of labels with the label that is modified. The method including providing as input the plurality of labels that is updated into an image generation artificial intelligence system configured for implementing latent diffusion to generate an updated image.

Abstract: A method for generating a moment asset to represent interactive activity that occurred during a session of gameplay includes executing an instance of a game for a user, with the executing generating state data descriptive of interactive activity occurring during the session, and examining the state data by a machine learning process, which extracts features for classification and input to a moment model. The method also includes accessing user profile data, which includes labeled user profile feature data that identifies characteristics of playing the game by the user and is input to the moment model. The method further includes outputting, by the moment model, two or more images and at least one text descriptor of interactive activities that occurred during the session, and inputting the images and text descriptor to an image generation artificial intelligence process with priority data to influence a layout of image content for the moment asset.

Abstract: A method for generating an avatar for a video game is provided, including: receiving, over a network from a client device, a captured image of a user and modification data, the modification data being generated from user input received at the client device, the modification data describing characteristics for generating an avatar for the user; using an image generation artificial intelligence (AI) to generate the avatar based on the image of the user and the modification data; wherein the avatar is configured for use in a video game, and wherein the image generation AI is configured to generate the avatar having a style consistent with a style of the video game in which the avatar will be used; applying the avatar to a session of the video game.

Abstract: A method for image generation. The method including identifying a plurality of features of an image. The method including classifying each of the plurality of features using an artificial intelligence (AI) model trained to identify features in a plurality of images, wherein the plurality of features is classified as a plurality of labels, wherein the image is provided as input to the AI model. The method including receiving feedback for a label, wherein the feedback is associated with a user. The method including modifying a label based on the feedback. The method including updating the plurality of labels with the label that is modified. The method including providing as input the plurality of labels that is updated into an image generation artificial intelligence system configured for implementing latent diffusion to generate an updated image.

Abstract: Systems and methods for generating images are described. A method includes receiving a textual description describing a first image. The method further includes executing an artificial intelligence (AI) model to compute a weight for each word of the textual description and to extract contextual biasing words based on the computed weights. The method further includes generating a suggestion including a proposed modification to the first image based on the contextual biasing words and receiving input data responsive to the suggestion. The method further includes generating a second image based on the suggestion and the input data and providing the second image to a client device for display.

Abstract: A method generating an image according to a style is described. The method includes receiving a textual description describing a first image. The method further includes applying an artificial intelligence (AI) model to determine the style of a second image based on the textual description, the first image, a plurality of descriptions, and a plurality of images to generate a suggestion. The style provides a context to the second image. The style is lacking in the first image. The method includes generating the second image with the suggestion according to the style and providing the second image to a client device for display.

Abstract: A method for image generation. The method including identifying a plurality of features of an image. The method including classifying each of the plurality of features using an artificial intelligence (AI) model trained to identify features in a plurality of images, wherein the plurality of features is classified as a plurality of labels, wherein the image is provided as input to the AI model. The method including receiving feedback for a label, wherein the feedback is associated with a user. The method including modifying a label based on the feedback. The method including updating the plurality of labels with the label that is modified. The method including providing as input the plurality of labels that is updated into an image generation artificial intelligence system configured for implementing latent diffusion to generate an updated image.

Abstract: A method for generating a moment asset to represent interactive activity that occurred during a session of gameplay includes executing an instance of a game for a user, with the executing generating state data descriptive of interactive activity occurring during the session, and examining the state data by a machine learning process, which extracts features for classification and input to a moment model. The method also includes accessing user profile data, which includes labeled user profile feature data that identifies characteristics of playing the game by the user and is input to the moment model. The method further includes outputting, by the moment model, two or more images and at least one text descriptor of interactive activities that occurred during the session, and inputting the images and text descriptor to an image generation artificial intelligence process with priority data to influence a layout of image content for the moment asset.

Abstract: A method for generating an avatar for a video game is provided, including: receiving, over a network from a client device, a captured image of a user and modification data, the modification data being generated from user input received at the client device, the modification data describing characteristics for generating an avatar for the user; using an image generation artificial intelligence (AI) to generate the avatar based on the image of the user and the modification data; wherein the avatar is configured for use in a video game, and wherein the image generation AI is configured to generate the avatar having a style consistent with a style of the video game in which the avatar will be used; applying the avatar to a session of the video game.

Abstract: A method is provided, including: receiving a game image, said game image being captured from gameplay of a video game and said game image depicting a scene of the video game; receiving game state data describing attributes of the scene of the video game that is depicted in the game image; receiving, over a network from a client device, modification data describing changes to the game image, the modification data defined from user input received at the client device; applying the game image, the game state data, and the user input, by an image generation artificial intelligence (AI) to generate an AI generated image; transmitting the AI generated image over the network to the client device for rendering to a display.

Abstract: A method generating an image according to a style is described. The method includes receiving a textual description describing a first image. The method further includes applying an artificial intelligence (AI) model to determine the style of a second image based on the textual description, the first image, a plurality of descriptions, and a plurality of images to generate a suggestion. The style provides a context to the second image. The style is lacking in the first image. The method includes generating the second image with the suggestion according to the style and providing the second image to a client device for display.