World models equip agents with a deep understanding of the world and the ability to predict the future. However, previous world models have been unable to accurately predict object interactions in complex environents. We present Dreamer 4, a scalable agent that learns to solve control tasks by imagination training inside of a fast and accurate world model. Through a new objective and architecture, the world model simulates complex object interactions while achieving real-time interactive inference. By training inside of its world model, Dreamer 4 is the first agent to obtain diamonds in Minecraft purely from offline data, aligning it with applications such as robotics where online interaction is often impractical.