DreamForge-World 0.1 Preview

What is a real-time world model?

A world model is a neural network that learns the dynamics of an environment well enough to generate what happens next. DreamForge runs this loop in real time: you provide input — move forward, turn, look around — and the model generates the next moments of the world directly, frame by frame. Nothing in the scene is a pre-built mesh, sprite, or level. The world itself is the model's output.

Our approach

DF-World 0.1 is a 1.5B-parameter model built on open research: LongLive (autoregressive finetune of Wan 2.1 1.3B DiT) as the video backbone, Matrix-Game 2’s residual action module adapted for first- and third-person keyboard and mouse control, a custom causal runtime on top, zero-shot multimodal conditioning, and heavy optimization for local inference on consumer GPUs.

How the model works

Multimodal input initializes a world; live keyboard and mouse control — first- or third-person — drives real-time frame generation. Reprompting can change the world mid-stream.

Prototype performance & setup

Observed ranges for the current prototype — they will change as the model and serving stack evolve. DreamForge-World 0.1 generates at 480 × 832 (480p). In fp8 with real-time control on a single RTX 4090, we observe roughly 10–12 FPS at about 4 GB VRAM. Standard bf16 inference needs roughly 8 GB. On one H100, up to about 14–15 FPS with real-time control. The model runs fully locally — including on RTX 2060-class laptop GPUs with the quantized build. Rollouts extend beyond a minute of continuous generation. Spatial world memory is not present yet.

Comparison with recent interactive world models

How DreamForge-World 0.1 compares on core capabilities against other publicly discussed interactive world model projects.

DF-World 0.1 column highlights DreamForge-World 0.1 Preview against publicly discussed interactive world model projects.

Where it stands today

DreamForge-World 0.1 is an early but working real-time world model — a controllable, fully generated environment you can step inside and drive. Here is what the current preview delivers and what we are still building toward.

Currently works

• Real-time generation of navigable worlds
• Multimodal world initialization
• Real-time world state reprompting
• Long-horizon generation
• First- and third-person control

Known limitations

• No persistent world memory
• Visual error accumulation over long sessions
• Noticeable control latency
• No sound generation
• Limited action diversity

How this differs from AI game-assembly tools

Many "AI game" products procedurally assemble games from pre-made assets with agentic helpers — effectively orchestrating existing pieces into a playable layout, often limited to a single camera or genre. DreamForge takes the opposite path: the model generates the world itself — open-ended, multimodal, and controllable in real time. That is the generative path to living, interactive worlds.

What's next

We are building DF-World 0.5 now and plan to open-source it once it is ready. Near term: control that feels more natural, sound and richer detail so worlds feel alive, worlds that respond more intelligently to what you do, and spatial memory so places stay consistent as you revisit them.