Fix model card image and video links to original model assets

README.md

@@ -275,11 +275,11 @@ For detailed evaluations of the base model, see our [technical paper](https://re
 The table below summarizes Cosmos3-Edge-FP8 across reasoning and generation. Each reasoning column (General, Robotics, Smart Infrastructure, Driving) reports the average score over that capability's benchmarks. For generation, **Image2Video** is the PAIBench overall score and **Policy: Robot** is the RoboLab success rate. In each column, the best result is in **bold** and the second-best is <u>underlined</u>.
 \* denotes post-trained Cosmos3 variants: [Cosmos3-Nano-Policy-DROID](https://huggingface.co/nvidia/Cosmos3-Nano-Policy-DROID) and [Cosmos3-Edge-Policy-DROID](https://huggingface.co/nvidia/Cosmos3-Edge-Policy-DROID#robolab).
 
-![Overall benchmark results](assets/benchmark-overall.png)
+![Overall benchmark results](https://huggingface.co/nvidia/Cosmos3-Edge/resolve/main/assets/benchmark-overall.png)
 
 ### Reasoning Benchmarks
 
-![Reasoning benchmarks](images/benchmark-reasoning.png)
+![Reasoning benchmarks](https://huggingface.co/nvidia/Cosmos3-Edge/resolve/main/images/benchmark-reasoning.png)
 
 ### Generation Benchmarks
 
@@ -287,7 +287,7 @@ The table below summarizes Cosmos3-Edge-FP8 across reasoning and generation. Eac
 
 All models are evaluated on image-to-video generation at **480p, 24 fps**. Throughput is the number of frames generated per second, measured in eager mode on a single **NVIDIA H100** GPU. Cosmos3-Edge-FP8 delivers the highest generation throughput while achieving competitive quality across PAIBench, RBench, and PhysicsIQ.
 
-![Image-to-Video benchmark results](assets/benchmark-image2video.png)
+![Image-to-Video benchmark results](https://huggingface.co/nvidia/Cosmos3-Edge/resolve/main/assets/benchmark-image2video.png)
 
 
 #### Action
@@ -564,7 +564,7 @@ print(f"Saved video to {output_path}")
 
 Example output:
 
-<video controls width="832" height="480" src="https://huggingface.co/nvidia/Cosmos3-Edge-FP8/resolve/main/assets/edge_i2v_output.mp4"></video>
+<video controls width="832" height="480" src="https://huggingface.co/nvidia/Cosmos3-Edge/resolve/main/assets/edge_i2v_output.mp4"></video>
 
 ---
 
@@ -665,7 +665,7 @@ print("stitched resolution:", f"{input_width}x{input_height}")
 
 Example output:
 
-<video width="512" controls src="https://huggingface.co/nvidia/Cosmos3-Edge-FP8/resolve/main/assets/edge_action_fd_umi_2chunk_output.mp4"></video>
+<video width="512" controls src="https://huggingface.co/nvidia/Cosmos3-Edge/resolve/main/assets/edge_action_fd_umi_2chunk_output.mp4"></video>
 
 ###### Action inverse dynamics
 
@@ -738,9 +738,9 @@ Example outputs:
 - [av_inverse_0 predicted action JSON](https://huggingface.co/nvidia/Cosmos3-Edge-FP8/blob/main/assets/edge_action_id_av_0_output.json)
 - [av_inverse_1 predicted action JSON](https://huggingface.co/nvidia/Cosmos3-Edge-FP8/blob/main/assets/edge_action_id_av_1_output.json)
 
-<img width="1280" src="https://huggingface.co/nvidia/Cosmos3-Edge-FP8/resolve/main/assets/edge_action_id_av_0_output.png">
+<img width="1280" src="https://huggingface.co/nvidia/Cosmos3-Edge/resolve/main/assets/edge_action_id_av_0_output.png">
 
-<img width="1280" src="https://huggingface.co/nvidia/Cosmos3-Edge-FP8/resolve/main/assets/edge_action_id_av_1_output.png">
+<img width="1280" src="https://huggingface.co/nvidia/Cosmos3-Edge/resolve/main/assets/edge_action_id_av_1_output.png">
 
 ### Diffusers
 
@@ -819,7 +819,7 @@ print(f"Saved video to {output_path}")
 
 Example output:
 
-<video controls width="832" height="480" src="https://huggingface.co/nvidia/Cosmos3-Edge-FP8/resolve/main/assets/diffusers_outputs/edge_i2v_diffusers.mp4"></video>
+<video controls width="832" height="480" src="https://huggingface.co/nvidia/Cosmos3-Edge/resolve/main/assets/diffusers_outputs/edge_i2v_diffusers.mp4"></video>
 
 ---
 
@@ -894,7 +894,7 @@ print("Saved stitched rollout:", stitched_path)
 
 Example output:
 
-<video controls width="256" height="256" src="https://huggingface.co/nvidia/Cosmos3-Edge-FP8/resolve/main/assets/diffusers_outputs/edge_action_fd_umi_2chunk_diffusers.mp4"></video>
+<video controls width="256" height="256" src="https://huggingface.co/nvidia/Cosmos3-Edge/resolve/main/assets/diffusers_outputs/edge_action_fd_umi_2chunk_diffusers.mp4"></video>
 
 ###### Action inverse dynamics
 
@@ -998,7 +998,7 @@ vllm serve nvidia/Cosmos3-Edge-FP8 \
 
 Image input:
 
-<img src="assets/example_reasoning_input.png" alt="Reasoning example input showing a tabletop robot-manipulation scene" width="640">
+<img src="https://huggingface.co/nvidia/Cosmos3-Edge/resolve/main/assets/example_reasoning_input.png" alt="Reasoning example input showing a tabletop robot-manipulation scene" width="640">
 
 User prompt: