Add model card

README.md

@@ -2,4 +2,43 @@
 license: other
 license_name: stabilityai-ai-non-commercial
 license_link: https://huggingface.co/stabilityai/stable-virtual-camera/blob/main/LICENSE
+base_model: stabilityai/stable-virtual-camera
+pipeline_tag: image-to-video
+tags:
+- novel-view-synthesis
+- video-diffusion
+- 3d-gaussian-splatting
 ---
+
+# GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis
+
+GS-Adapter and LoRA weights for **GeoNVS**, which injects explicit 3D Gaussian
+geometry into camera-controlled video diffusion models
+([paper](https://arxiv.org/abs/2603.14965)).
+
+These weights are fine-tuned from
+[`stabilityai/stable-virtual-camera`](https://huggingface.co/stabilityai/stable-virtual-camera)
+(SEVA) and [CameraCtrl](https://github.com/hehao13/CameraCtrl) (SVD backbone),
+and **inherit the Stability AI Non-Commercial Research Community License** —
+using them requires the base models and acceptance of their licenses.
+Non-commercial research use only.
+
+## Files
+
+| Path | Backbone | Description |
+|---|---|---|
+| `eccv_gattn/checkpoint-88000/` | SEVA | Main GeoNVS model (gated-attention fusion): `gs_adapter_weights.pth` + `pytorch_lora_weights.safetensors` |
+| `eccv_camctrl/checkpoint-180000/` | CameraCtrl (SVD) | GeoNVS on CameraCtrl: adapter + LoRA |
+| `cameractrl_lora_145K/` | CameraCtrl (SVD) | LoRA-only baseline (no GS-Adapter) |
+
+## Usage
+
+Use with the GeoNVS code release — `scripts/download_weights.sh` fetches these
+files into `pretrained_weights/`, then:
+
+```bash
+python demo.py --data_path <benchmarkset>/dl3dv10 --num_inputs 3 \
+    --gs_adapter_config configs/module_config/gsadapter_eccv_gattn.yaml \
+    --gs_adapter_weight_path pretrained_weights/eccv_gattn/checkpoint-88000 \
+    --lrm_model_name vggt_iv --H=384 --W=384 --version=1.0
+```