

Animegamer
Overview :
AnimeGamer is built based on a multi-modal large language model (MLLM) that can generate dynamic animation shots and character status updates, providing users with an endless anime life experience. It allows users to interact with anime characters through open-ended language instructions, creating unique adventure stories. The main advantages of this product include: dynamically generating animations for character interactions, enabling interactions between different anime, and rich game state prediction.
Target Users :
This product is suitable for anime enthusiasts and game developers who wish to experience limitless adventures in the anime world. Using AnimeGamer, users can create interactions with their favorite anime characters, expanding their imagination and creativity.
Use Cases
Users can simulate interactions between Qiqi and Pazu, creating new storylines.
Users can interact between different anime characters, such as letting Sosuke meet other anime characters.
Developers can utilize AnimeGamer's technology to create new anime games and applications.
Features
Interact with anime characters through open-ended language instructions
Generate dynamic animation shots, showcasing character movements
Update character status, including stamina, social, and entertainment values
Predict the next game state, maintaining contextual consistency
Allow users to create unique interactions across anime characters
Provide inference code for low VRAM environments
Support custom game instructions
Suitable for various anime characters
How to Use
Access the GitHub page and clone the repository: git clone https://github.com/TencentARC/AnimeGamer.git
Enter the AnimeGamer directory and create a Python environment: conda create -n animegamer python==3.10 -y
Activate the environment: conda activate animegamer
Install the required dependencies: pip install -r requirements.txt
Download the required model checkpoints and place them in the ./checkpoints directory.
Run the inference decoder to generate animation shots: python inference_Decoder.py
Modify the instructions in ./game_demo as needed to customize the game experience.
Featured AI Tools

Spawn
Spawn is an AI-driven online tool that can generate characters, opponents, and campaigns for D&D games in just one minute. Users can create a character sheet including stats, equipment, and appearance with the tool. It also offers a diverse combination of characters from various races and classes. This tool allows D&D players to quickly jump into the game without the hassle of designing characters. It also assists game masters in quickly creating NPCs and monsters. Overall, Spawn simplifies D&D preparation significantly via AI generation, enabling players to focus on role-play and combat.
Game Generation
116.2K
Fresh Picks

Index 1.9B Character
Index-1.9B-Character is a large language model independently developed by the Index team, focusing on the field of role-playing. It has a parameter scale of 1.9 billion. The model supports users to quickly customize roles through uploading roleplay dialogue data, and has high role consistency, dialogue ability, and role-playing attractiveness. In the authoritative benchmark CharacterEval evaluation, it ranked ninth overall, outperforming models of the same scale.
AI Character Generation
84.2K