Image-to-Video
NV-MedTech
custom
simulation
surgical-robotics
video-generation
real-time
interactive
autoregressive
policy-evaluation
vla-evaluation
healthcare-robotics
world-model
Instructions to use nvidia/Cosmos-H-Dreams with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NV-MedTech
How to use nvidia/Cosmos-H-Dreams with NV-MedTech:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse filesAdd link to newest version of model
README.md
CHANGED
|
@@ -39,6 +39,8 @@ library_name: nv-medtech
|
|
| 39 |
|
| 40 |
# Cosmos-H-Dreams
|
| 41 |
|
|
|
|
|
|
|
| 42 |
## Description
|
| 43 |
Cosmos-H-Dreams is a real-time, action-conditioned generative surgical world model that lets a human operator or a learned surgical-robotics policy act inside a synthesized surgical scene and observe the interactions live. Given a surgical context frame and a stream of robot kinematic actions, the model autoregressively generates the resulting future video in short blocks, streaming interactively on a single GPU.
|
| 44 |
|
|
|
|
| 39 |
|
| 40 |
# Cosmos-H-Dreams
|
| 41 |
|
| 42 |
+
Please see https://huggingface.co/nvidia/Cosmos3-H-Dreams to see the latest version of this model.
|
| 43 |
+
|
| 44 |
## Description
|
| 45 |
Cosmos-H-Dreams is a real-time, action-conditioned generative surgical world model that lets a human operator or a learned surgical-robotics policy act inside a synthesized surgical scene and observe the interactions live. Given a surgical context frame and a stream of robot kinematic actions, the model autoregressively generates the resulting future video in short blocks, streaming interactively on a single GPU.
|
| 46 |
|