Polish model details and organize model card assets

Replace internal checkpoint naming with public model specifications and move the pipeline figure under assets/.

README.md

@@ -31,7 +31,7 @@ tags:
 
 PRG-Fusion synthesizes photorealistic driving videos along novel trajectories by combining reconstruction evidence with generative video priors. It uses dense 3D Gaussian Splatting (3DGS) renderings for appearance control and sparse LiDAR projections for geometric control.
 
-![PRG-Fusion pipeline](pipeline.png)
+![PRG-Fusion pipeline](assets/pipeline.png)
 
 PRG-Fusion converts region-wise reconstruction degradation evidence into **Preserve, Repair, and Generate (PRG)** labels. These labels route information across the video diffusion model:
 
@@ -45,11 +45,11 @@ The model follows a two-stage training strategy: geometric control is first lear
 
 | | |
 | --- | --- |
+| **Model** | PRG-Fusion |
 | **Base model** | [NVIDIA Cosmos-Transfer2.5-2B](https://huggingface.co/nvidia/Cosmos-Transfer2.5-2B) |
-| **Checkpoint** | PRG-Fusion V6 Stage 2 |
-| **Control branches** | 3DGS appearance + LiDAR geometry |
+| **Conditioning** | Dense 3DGS renderings and sparse LiDAR projections |
 | **Checkpoint format** | PyTorch Distributed Checkpoint (DCP) |
-| **Input** | Text prompt, aligned 3DGS rendering video, and LiDAR projection video |
+| **Input** | Text prompt and aligned target-trajectory control videos |
 | **Output** | Novel-trajectory driving video |
 | **Evaluation domain** | Waymo driving scenes |