Abstract: A computerized method is provided including displaying a chat interface configured to receive natural language user input, executing a language model agent configured to interface with a generative language model to obtain game parameter values based on the natural language user input, and executing a diffusion model agent configured to interface with a diffusion model to obtain an image based on the game parameter values. The diffusion model includes one or a plurality of finetuning models that have been trained to achieve visual consistency in one or more visual characteristics of the generated image. The method further includes generating a game application including code and the image as a game asset, executing the generated code, and displaying a game interface of the game application. Code and images for the game application can be regenerated based on user input. The finetuning models can be LoRA models, for example.

Abstract: A computing system executing a game maker model receives a user query including a description of the 3D object, generates an input prompt based on the user query, encodes the input prompt into embeddings, inputs the embeddings into a control network to generate latent features, inputs the latent features and the embeddings into a diffusion model to generate a 2D image, and generates and outputs the 3D object based on the 2D image.

Abstract: Embodiments of the disclosure relate to an interaction method, apparatus, device and storage medium. The method proposed herein includes: in response to receiving a sharing request for an avatar created by a user, presenting a sharing window, wherein the sharing window includes a message editing component, the message editing component includes a text region and a resource region, and at least one of the text region or the resource region is an editable region supporting content editing; generating a target message based on an input content of the message editing component, wherein the target message includes a text content in the text region and at least one interaction resource in the resource region; and sending the target message to a session associated with at least one object to be shared.

Abstract: Embodiments of the disclosure relate to an interaction method, device and apparatus, and a storage medium. The method provided herein includes: displaying a setting interface for a user, the setting interface displaying a set of static representations corresponding to a set of avatars in a first region, the set of avatars being generated based on obtained image of the user; based on a selection of a target static representation in the set of static representations, displaying a target dynamic representation corresponding to the target static representation in a second region of a setting interface, wherein the target static representation and the target dynamic representation are associated with a target avatar; and associating the target avatar to the user.

Abstract: A server device provides a social media platform. The server device includes one or more processors configured to execute instructions stored in associated memory to send instructions to a client device to cause the client device to display a graphical user interface (GUI) of the social media platform, receive at least one image of a face of a user of the client device and a selection of at least one predetermined style via the GUI, using the at least one image and the at least one predetermined style as input, generate a plurality of artificial intelligence (AI) profile pictures via an AI model, and send the plurality of AI profile pictures to the client device.