multimodalart's picture
multimodalart HF Staff
Upload folder using huggingface_hub
0cde9e0 verified
|
Raw
History Blame Contribute Delete
938 Bytes
---
title: Latent Dynamics Reasoning (LDR)
emoji: 🎬
colorFrom: red
colorTo: pink
sdk: gradio
sdk_version: 6.15.1
app_file: app.py
short_description: Extrapolate physical video from 3 conditioning frames
python_version: "3.10"
startup_duration_timeout: 30m
---
# Latent Dynamics Reasoning (LDR)
Extrapolative video world model that rolls out future video frames from three
initial conditioning images, reasoning about latent physical dynamics.
Upload three frames of a physical scene, pick the task type (uniform,
parabola, collision, looming, bouncing), and the model generates ~29 future
frames of predicted motion.
Based on: [Learning How the World Evolves: Extrapolative Video World Models
via Latent Dynamics Reasoning](https://lat-dyn-reason.github.io/)
- [Model](https://huggingface.co/haodongli/LDR) (Apache-2.0)
- [Code](https://github.com/Lat-Dyn-Reason/Lat-Dyn-Reason)
- [Project Page](https://lat-dyn-reason.github.io/)