Team Ai
Apppublic

Wayne-King/echo-memory

sourceHugging Faceupdated 3mo agoView on Hugging Face
0likes
App README

Echo-Memory: Action-Conditioned World Model Demo

Generate a video from an initial frame, a text prompt, and a camera rotation action using the Echo-Memory model.

Model: Echo-Team/Echo-Memory (Wan 2.1 1.3B backbone, context_k1 memory) Paper: Echo-Memory: A Controlled Study of Memory in Action World Models Code: GitHub

How it works

  1. 1.Upload an initial frame (or use one of the provided examples)
  2. 2.Enter a text prompt describing the scene
  3. 3.Choose a camera rotation direction and angle
  4. 4.Click "Generate Video" to produce a 5-second video clip at 640×352 resolution