Add files using upload-large-folder tool

README.md

@@ -1,6 +1,7 @@
 ---
 library_name: pytorch
 pipeline_tag: image-to-video
+license: apache-2.0
 base_model: Wan-AI/Wan2.2-I2V-A14B
 tags:
   - video-generation
@@ -10,14 +11,23 @@ tags:
   - safetensors
 ---
 
-# SCoPE for Wan2.2-I2V-A14B
+# SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers
 
-SCoPE generates camera-controlled videos from a first frame, a text prompt, and a camera
-trajectory. It represents each video token with both its spatial-temporal position and its camera
-sightline, enabling direct control over camera motion in Wan2.2-I2V-A14B.
+Minghao Yin · Jiahao Lu · Wenbo Hu · Wang Zhao · Ying Shan · Kai Han
+
+[![Project Page](https://img.shields.io/badge/Project%20Page-visual--ai.github.io%2Fscope-1E90FF)](https://visual-ai.github.io/scope/)
+[![arXiv](https://img.shields.io/badge/arXiv-2606.27345-B31B1B?logo=arxiv)](https://arxiv.org/abs/2606.27345)
+[![GitHub](https://img.shields.io/badge/GitHub-SCoPE-181717?logo=github)](https://github.com/TencentARC/SCoPE)
+[![License](https://img.shields.io/badge/License-Apache%202.0-green)](https://github.com/TencentARC/SCoPE/blob/main/LICENSE.txt)
 
 ![SCoPE teaser](assets/teaser.png)
 
+SCoPE adds camera sightlines as positional coordinates to a pretrained video diffusion
+transformer. Given a first frame, a text prompt, and a camera trajectory, it generates a video
+that follows the requested camera motion while preserving the original image-to-video prior. This
+repository is a self-contained release for **Wan2.2-I2V-A14B**: it contains everything required for
+inference, so a separate Wan2.2 checkpoint download is not needed.
+
 ## Download
 
 ```bash
@@ -25,17 +35,20 @@ pip install -U huggingface_hub
 hf download TencentARC/SCoPE --local-dir checkpoints/SCoPE
 ```
 
-The model repository is self-contained for inference; a separate Wan2.2 model download is not
-required.
+The checkpoint is approximately 67 GB. Keep both the checkpoint and the Hugging Face cache on local
+storage.
 
 ## Usage
 
-Install the SCoPE code:
+Install the SCoPE code. The released weights were trained and evaluated with **PyTorch 2.9.1
+(CUDA 12.8)**; because changing the PyTorch version can change the numerical output, we recommend
+reproducing this exact environment with [uv](https://docs.astral.sh/uv/):
 
 ```bash
 git clone https://github.com/TencentARC/SCoPE.git
 cd SCoPE
-pip install -e .
+uv sync
+source .venv/bin/activate
 ```
 
 Generate a video with an example camera trajectory:
@@ -61,21 +74,23 @@ python inference.py \
 ```
 
 Camera poses use OpenCV camera-to-world coordinates and must have shape `[81, 3, 4]` or
-`[81, 4, 4]`. `x_fov` is the horizontal field of view in radians; pinhole cameras use `xi=0`.
+`[81, 4, 4]`. `x_fov` is the horizontal field of view in radians; pinhole cameras use `xi=0`. See
+the [GitHub repository](https://github.com/TencentARC/SCoPE) for the full documentation, options,
+and demos.
 
 ## Training data
 
 SCoPE is trained with RealEstate10K, DL3DV, PanShot, and OmniWorld. The datasets use a common
 camera protocol: poses are expressed relative to the first camera and translation is normalized
-with per-clip near depth. Users are responsible for following the licenses and terms of the
-corresponding datasets.
+with per-clip near depth, while absolute scale is handled inside the model by a learned scale gate.
+Users are responsible for following the licenses and terms of the corresponding datasets.
 
 ## Intended use and limitations
 
 This model is intended for research on image-to-video generation and controllable camera motion.
 It inherits the visual capabilities, biases, safety limitations, and computational requirements of
-Wan2.2. Results may degrade for inaccurate camera poses or intrinsics, trajectories far outside
-the training distribution, large occlusions, or unusually fast camera motion.
+Wan2.2. Results may degrade for inaccurate camera poses or intrinsics, trajectories far outside the
+training distribution, large occlusions, or unusually fast camera motion.
 
 ## Citation
 
@@ -86,3 +101,13 @@ the training distribution, large occlusions, or unusually fast camera motion.
   year={2026}
 }
 ```
+
+## Acknowledgements
+
+SCoPE is built on [Wan2.2](https://github.com/Wan-Video/Wan2.2) and
+[DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio). We thank the authors and
+contributors of these projects.
+
+## License
+
+SCoPE is released under the [Apache-2.0 License](https://github.com/TencentARC/SCoPE/blob/main/LICENSE.txt).