slvDev
Featured
esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It addresses a key limitation of video generation models by enforcing mechanics-consistent gameplay through explicit state prediction, a novel approach beyond pixel-level realism.
Who it is for
- Researchers in video generation and world models
- Game AI developers
- Computer vision scientists
- Machine learning engineers working on simulation
Use cases
- Generating consistent gameplay videos for prototyping
- Simulating game scenarios for AI agent training
- Data augmentation for game testing and validation
Strengths
- Open-source code, model weights, and dataset available on GitHub and HuggingFace
- Bundled examples and scripts enable quick reproduction and inference
- Built on top of the powerful Wan2.2 video generation backbone
- Dual-branch architecture with joint attention enables joint state and video prediction
Considerations
- Requires high-end GPU with bfloat16 support and CUDA, limiting accessibility
- Currently demonstrated only on SF3 dataset with five normalized game states, generalizability unknown
- Training requires downloading multiple large model components (Wan2.2 VAE, T5, DiT shards) which adds setup complexity
README quick start
Installation
Description
StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation
Related repositories
Similar projects matched by category, topics, and programming language.
gavamedia
Featured
deltafin
Deltafin is a research project that runs the 2.8-trillion-parameter Mixture-of-Experts model Kimi K3 on a single Apple Silicon Mac (e.g., M1 Max with 64 GB) at about 16 seconds per token, using exact, reproducible inference with local or streaming expert loading.
jamesob
Featured
local-llm
A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.