Sync model card with public code release layout

README.md

@@ -25,7 +25,7 @@ tags:
 
 **Sipeng He · Jialei Chen · Zhen Fang · Dongchun Ren · Feng Zhao**
 
-[Paper](https://arxiv.org/abs/2609.06948) · [Code](https://github.com/Pre-cici/cosmos)
+[Paper](https://arxiv.org/abs/2609.06948) · [Code](https://github.com/Pre-cici/PRG-Fusion)
 
 </div>
 
@@ -60,16 +60,17 @@ Download the checkpoint directly into the layout expected by the PRG-Fusion code
 ```bash
 hf download Post-pone/PRG-Fusion \
   --include '.metadata' '*.distcp' \
-  --local-dir checkpoints/omnire/iter_000001000/model
+  --local-dir checkpoints/PRG-Fusion/model
 ```
 
 The complete checkpoint is approximately 15.95 GB:
 
 ```text
-checkpoints/omnire/iter_000001000/model/
-├── .metadata
-├── __0_0.distcp
-└── __1_0.distcp
+checkpoints/PRG-Fusion/
+├── model/
+│   ├── .metadata
+│   ├── __0_0.distcp
+│   └── __1_0.distcp
 ```
 
 All three files are required. Keep the original filenames because `.metadata` references the two DCP shards.
@@ -79,14 +80,15 @@ All three files are required. Keep the original filenames because `.metadata` re
 Clone and install the [PRG-Fusion code](https://github.com/Pre-cici/cosmos) on a Linux NVIDIA GPU host:
 
 ```bash
-git clone https://github.com/Pre-cici/cosmos.git
-cd cosmos
+git clone https://github.com/Pre-cici/PRG-Fusion.git
+cd PRG-Fusion
 
+uv venv --python 3.10
 uv sync --extra cu130
 uv run --extra cu130 python examples/check_environment.py
 ```
 
-Use `cu128` instead of `cu130` on a CUDA 12.8 system. Follow the repository's [checkpoint guide](https://github.com/Pre-cici/cosmos/blob/main/docs/checkpoints.md) to download the remaining Cosmos tokenizer and text-conditioning components.
+Use `cu128` instead of `cu130` on a CUDA 12.8 system. Follow the repository's [checkpoint guide](https://github.com/Pre-cici/PRG-Fusion/blob/main/docs/checkpoints.md) to download the remaining Cosmos tokenizer and text-conditioning components.
 
 Prepare an aligned pair of target-trajectory control videos:
 
@@ -135,6 +137,3 @@ PRG-Fusion is a derivative of NVIDIA Cosmos-Transfer2.5-2B and is released under
 }
 ```
 
-## Acknowledgements
-
-**Built on NVIDIA Cosmos.** We thank the NVIDIA Cosmos team and the open-source community for making this work possible.