Stable-worldmodel is a research framework for goal-conditioned world models in reinforcement learning, providing a full pipeline from data collection and storage to model training and planning-based evaluation. The codebase is primarily a research platform with strong software engineering practices—pluggable data formats (Lance, HDF5, video, folder), a command-line interface (swm), and a Hydra-based configuration system for reproducible experiments. It includes implementations of multiple world model architectures (LeWM, PLDM, PreJEPA/DINO-WM, TD-MPC2, GCRL), planning solvers (CEM, MPPI, iCEM, gradient-based, Lagrangian), and environment wrappers with domain randomization across 30+ tasks (DeepMind Control, Gymnasium, PushT, OGBench, Craftax, robotics). The repository demonstrates high craftsmanship in its data engineering: the data format registry extends cleanly, the Lance format supports cloud-native streaming from Hugging Face Buckets, and utilities like GoalDataset, HistoryBuffer, and ReplayBuffer solve recurring RL data management problems. The project is actively maintained with extensive test coverage, comprehensive documentation, and a scalable training pipeline using stable-pretraining and Lightning. While the primary goal is research (testing hypotheses about world model generalization under variation), the codebase includes application-level production quality—CI/CD, CLI, checkpoint management, and robust error handling—making it a rare hybrid that serves both researchers and engineers.
DreamDojo is an application repository for training and deploying world foundation models, particularly focused on robotics applications. The system provides end-to-end capabilities for training Cosmos Predict2 models, generating text/video-to-video outputs, action-conditioned video generation for robot control, and model distillation for efficient inference. It features a modular architecture with Hydra-based configuration, distributed training support (FSDP, tensor parallelism, context parallelism), and interactive Gradio demonstrations. The codebase includes sophisticated safety filtering mechanisms and is designed for deployment via Docker containers.
Helios is a real-time long video generation system that implements text-to-video (T2V), image-to-video (I2V), and video-to-video (V2V) generation using a 3D transformer architecture. The system features a modular design with specialized optimizations for performance including Ahead-of-Time Compilation (AOTI), group offloading for VRAM reduction, context parallelism (Ulysses/Ring attention), and Flash Attention kernel optimizations. It employs a multi-stage training pipeline (Base → Mid → Distilled) to balance quality and sampling speed. The repository includes a Gradio web interface (app.py) for interactive generation, command-line inference scripts, training utilities, and a comprehensive evaluation suite measuring video quality across aesthetic, motion, semantic, and naturalness dimensions. While containing research elements for ablation studies and benchmarking, its primary function is as a deployable video generation application.
QwenLM/Qwen-AgentWorld is a research benchmark evaluation toolkit for Language World Models (LWMs). The repository contains the AgentWorldBench evaluation infrastructure: a standalone CLI script (`eval/eval.py`) that orchestrates a two-stage evaluation pipeline — first calling an OpenAI-compatible inference endpoint to generate environment predictions from a world model, then using an LLM judge (e.g., GPT) to score the predictions across five dimensions (format, factuality, consistency, realism, quality). The code covers seven agent domains (MCP, Search, Terminal, SWE, Android, Web, OS) through per-domain prompt templates and task configurations. The repository is not a model serving system or training framework; it is a reproducible evaluation harness published alongside the Qwen-AgentWorld model weights and benchmark dataset (hosted separately on Hugging Face). The core value is in the robust parsing utilities for extracting structured output from LLM responses, including sophisticated handling of think/response tag removal and multi-strategy JSON extraction from judge outputs.
The repository provides a comprehensive framework for generative AI models, particularly focused on image and video generation. It integrates various diffusion-based architectures (Stable Diffusion, Stable Diffusion XL, Hunyuan DiT, Wan, etc.) and offers utilities for model loading, prompt engineering, and post-processing. The system supports text-to-image, text-to-video, image-to-video, and video-to-video generation, along with editing capabilities via ControlNet and LoRA. The architecture is modular, with core components for model management, prompting, and VRAM optimization, though it exhibits some duplication across model-specific pipelines.