jjf233 commited on
Commit
792b373
·
verified ·
1 Parent(s): 6d7b331

Add model-tree figure to Description

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -53,6 +53,8 @@ Cosmos3-Edge-Policy-DROID is a robot-manipulation policy in the compact 4B Cosmo
53
  - **Example usage and output:** See the [Usage](https://huggingface.co/nvidia/Cosmos3-Edge-Policy-DROID#usage) / Quickstart section.
54
  - **Hardware:** The compact 4B size is intended for efficient single-GPU deployment; see [Usage](https://huggingface.co/nvidia/Cosmos3-Edge-Policy-DROID#usage).
55
 
 
 
56
  Cosmos3-Edge-Policy-DROID was developed by NVIDIA as a part of Cosmos3.
57
 
58
  Cosmos3 is a collection of Omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands from combinations of text, image, video, and action trajectory inputs. It serves as a foundational building block for a broad range of Physical AI applications and research spanning world understanding, world generation, simulation, and embodied policy learning.
 
53
  - **Example usage and output:** See the [Usage](https://huggingface.co/nvidia/Cosmos3-Edge-Policy-DROID#usage) / Quickstart section.
54
  - **Hardware:** The compact 4B size is intended for efficient single-GPU deployment; see [Usage](https://huggingface.co/nvidia/Cosmos3-Edge-Policy-DROID#usage).
55
 
56
+ ![Cosmos3 model family tree](assets/cosmos3_model_tree_edge_policy.png)
57
+
58
  Cosmos3-Edge-Policy-DROID was developed by NVIDIA as a part of Cosmos3.
59
 
60
  Cosmos3 is a collection of Omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands from combinations of text, image, video, and action trajectory inputs. It serves as a foundational building block for a broad range of Physical AI applications and research spanning world understanding, world generation, simulation, and embodied policy learning.