Tencent's ARC Lab, in collaboration with City University of Hong Kong, recently unveiled a groundbreaking research project called "AnimeGamer." This innovative tool allows for infinite anime life simulation and boasts the impressive ability to predict the next game state. This means users can immerse themselves in their favorite anime worlds like never before, interacting with dynamic environments in real-time through open-ended natural language commands.

QQ_1744006054969.png

Become an Anime Protagonist and Enjoy Limitless Interaction

AnimeGamer's most striking feature is its ability to generate consistently themed, infinitely long animation videos, also assigning attributes like stamina and mood to the characters. Users can not only play as iconic anime characters, such as Sosuke from Ponyo, but also interact with the surrounding world using simple verbal commands.

Even more exciting is AnimeGamer's ability to break down the dimensional walls, enabling a dreamlike collaboration between characters from different anime series.

Imagine Kiki from Kiki's Delivery Service meeting Pazu from Laputa: Castle in the Sky, with Kiki teaching Pazu her flying skills. Such scenarios become reality in AnimeGamer. This tool showcases its powerful generalization capabilities, understanding and executing interactions between different anime characters and actions, opening up limitless creative possibilities for users.

Technological Breakthrough: Multimodal Large Language Model Drives Immersive Experience

AnimeGamer's powerful functionality is driven by its core technology: an advanced multimodal large language model (MLLM). This model is responsible for generating each frame of the game state, including vivid character animations and updates to character stats.

AnimeGamer's training process involves three key stages: first, a multimodal data encoder models data containing motion information, and a diffusion model-based decoder is trained to reconstruct videos, with motion range information representing motion intensity also being input; second, an MLLM is trained, taking the user's historical commands and the current game state as input to predict various aspects of the next game state; finally, an optimization stage fine-tunes the decoder using the MLLM's predictions to further enhance the quality of the generated animation.

The advent of AnimeGamer undoubtedly injects new vitality into the anime culture and artificial intelligence research fields. Its core functions, infinite anime life simulation driven by natural language interaction and prediction of future game states, fully demonstrate the immense potential of multimodal large language models in creative content generation. As more features are unlocked and refined, AnimeGamer is poised to become an anime interaction platform brimming with endless possibilities and surprises.

Project Access: https://top.aibase.com/tool/animegamer