Force Prompting: Video Generation Models Can Learn And Generalize Physics-based Control Signals

Nate Gillman, Charles Herrmann, Michael Freeman, Daksh Aggarwal, Evan Luo, Deqing Sun, Chen Sun

Keywords: controllable video generation, physical forces, synthetic data

TL;DR: Video generalization models can learn physics-based controls from synthetic data and generalize this control across diverse geometries, settings, and materials.

Abstract:

Recent advances in video generation models have sparked interest in world models capable of simulating realistic environments.
While navigation has been well-explored, physically meaningful interactions that mimic real-world forces remain largely understudied.
In this work, we investigate using physical forces as a control signal for video generation and propose force prompts which enable users to interact with images through both localized point forces, such as poking a plant, and global wind force fields, such as wind blowing on fabric. We demonstrate that these force prompts can enable videos to respond realistically to physical control signals by leveraging the physical prior in the original pretrained model, without using any 3D asset or physics simulator at inference. The primary challenge of force prompting is the difficulty in obtaining high quality paired force-video training data, both in the real world due to the difficulty of obtaining force signals, and in synthetic data due to limitations in the visual quality and domain diversity of physics simulators. Our key finding is that video generation models can *generalize* remarkably well when adapted to follow physical force conditioning from videos synthesized by Blender, even with limited demonstrations of few objects (e.g., flying flags, rolling balls, etc.). Our method can generate videos which simulate forces across diverse geometries, settings, and materials. We also try to understand the source of this generalization and perform ablations on the training data that reveal two key elements: visual diversity and the use of specific text keywords during training. Our approach is trained on only around 15k training examples for a single day on four A100 GPUs, and outperforms existing methods on force adherence and physics realism, bringing world models closer to real-world physics interactions. All datasets, code, and model weights will be open-sourced. Video examples can be found at https://sites.google.com/view/force-prompting-neurips2025

Primary Area: Deep learning (e.g., architectures, generative models, optimization for deep networks, foundation models, LLMs)

Submission Number: 3817