InterDyn: Controllable Interactive Dynamics with Video Diffusion Models
Paper • 2412.11785 • Published
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("rickakkerman/InterDyn", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]
Rick Akkerman1,2*,
Haiwen Feng1*†,
Michael J. Black1,
Dimitrios Tzionas2,
Victoria Fernández Abrevaya1
1 Max Planck Institute for Intelligent Systems, Tübingen, Germany
2 University of Amsterdam, the Netherlands
* equal contribution † project lead
CVPR 2025
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support