AirScape: An Aerial Generative World Model with Motion Controllability
Paper • 2507.08885 • Published
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("EmbodiedCity/Airscape", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Airscape Model Weights
This repository contains the Phase1 & Phase2 weights of the model introduced in the paper:
[AirScape:An Aerial Generative World Model with Motion Controllability].
For more details, please refer to the homepage:
https://embodiedcity.github.io/AirScape/.
Citation
If this work has contributed to your research, welcome to cite it:
@misc{zhao2025airscapeaerialgenerativeworld,
title={AirScape: An Aerial Generative World Model with Motion Controllability},
author={Baining Zhao and Rongze Tang and Mingyuan Jia and Ziyou Wang and Fanghang Man and Xin Zhang and Yu Shang and Weichen Zhang and Chen Gao and Wei Wu and Xin Wang and Xinlei Chen and Yong Li},
year={2025},
eprint={2507.08885},
archivePrefix={arXiv},
primaryClass={cs.RO},
url={https://arxiv.org/abs/2507.08885},
}
license: mit
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for EmbodiedCity/Airscape
Base model
zai-org/CogVideoX-5b-I2V