On August 21st, Jinshi data reported that NVIDIA released a game demo, in which players can interact with NPCs through voice dialogue, understand level objectives, optimize equipment configurations, and then adjust weapon colors to start fighting. NVIDIA ACE is a platform that allows developers to create intelligent game NPCs through generative AI. In short, ACE can create unprecedented fully-voiced, fully dynamic video game characters.

Ultiverse announced the development of an AI-native game engine, targeting NPC, scene production, and content generation, providing various AI graphics, animation, music, and other capabilities to help developers improve content generation efficiency. Ultiverse is an AI-based metaverse VR game platform, currently supporting integration of over 300 games and around 10,000 content creators.

Meta recently unveiled an AI framework called audio2photoreal, which is capable of generating a series of realistic NPC character models and automatically "lip-syncing" and "posing" the character models with the help of existing voice-over files. The official research report pointed out that after receiving the dubbing file, the Audio2 photoreal framework will first generate a series of NPC models, and then use quantization technology and diffusion algorithm to generate model actions, in which quantization technology provides action sample reference for the framework and diffusion Algorithm is used to improve the effect of character actions generated by the frame. Forty-three percent of the evaluators in the controlled experiment were "strongly satisfied" with the character dialogue scenes generated by the frame, so the researchers felt that the Audio2 photoreal framework was able to generate "more dynamic and expressive" movements than competing products in the industry. It is reported that the research team has now made the relevant code and dataset public on GitHub.

According to Pinplay, Meta recently announced an AI framework called audio2photoreal, which is capable of generating a series of realistic NPC character models, and automatically "lip-syncing" and "posing" the character models with the help of existing dubbing files. The official research report pointed out that after receiving the dubbing file, the Audio2 photoreal framework will first generate a series of NPC models, and then use quantization technology and diffusion algorithm to generate model actions, in which quantization technology provides action sample reference for the framework and diffusion Algorithm is used to improve the effect of character actions generated by the frame. Forty-three percent of the evaluators in the controlled experiment were "strongly satisfied" with the character dialogue scenes generated by the frame, so the researchers felt that the Audio2 photoreal framework was able to generate "more dynamic and expressive" movements than competing products in the industry. It is reported that the research team has now made the relevant code and dataset public on GitHub.