Upload README.md with huggingface_hub

README.md

@@ -4,19 +4,25 @@ language:
 library_name: diffsynth
 license: cc-by-4.0
 pipeline_tag: image-to-video
+base_model:
+- Wan-AI/Wan2.1-T2V-1.3B
+arxiv: 2606.09803
 tags:
 - video-generation
 - world-model
 - memory
 - action-conditioned
 - wan
+- image-to-video
 ---
 
 # Echo-Memory — Wan 2.1 1.3B memory checkpoints
 
 Validated **30,000-step** fine-tunes for [Echo-Memory](https://github.com/Echo-Team-Joy-Future-Academy-JD/Echo-Memory), built on [Wan-AI/Wan2.1-T2V-1.3B](https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B).
 
-[Paper](https://huggingface.co/papers/2606.09803) | [Project page](https://echo-team-joy-future-academy-jd.github.io/Echo-Memory/) | [Training and inference code](https://github.com/Echo-Team-Joy-Future-Academy-JD/Echo-Memory)
+[Paper](https://huggingface.co/papers/2606.09803) · [Project page](https://echo-team-joy-future-academy-jd.github.io/Echo-Memory/) · [Code](https://github.com/Echo-Team-Joy-Future-Academy-JD/Echo-Memory) · [**Interactive demo**](https://huggingface.co/spaces/hugging-apps/echo-memory) · [Dataset](https://huggingface.co/datasets/Echo-Team/Echo-Memory-Data)
+
+Try the model in the browser (ZeroGPU, no local GPU): **[hugging-apps/echo-memory](https://huggingface.co/spaces/hugging-apps/echo-memory)**
 
 ## Available checkpoints