Add live Breakout demo GIF
Browse files- .gitattributes +1 -0
- README.md +2 -2
- demo.gif +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
demo.gif filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -15,7 +15,7 @@ tags:
|
|
| 15 |
|
| 16 |
An action-conditioned Breakout world model. Hold **A / D** (or the arrow keys) and the model generates the next frame.
|
| 17 |
|
| 18 |
-
![
|
| 19 |
|
| 20 |
128x128 at 6 FPS with 12 frames of latent history. The model has about 70M parameters and uses the frozen SDXL VAE from `madebyollin/sdxl-vae-fp16-fix`.
|
| 21 |
|
|
@@ -54,6 +54,6 @@ Click the window for focus. **A / Left** moves left; **D / Right** moves right.
|
|
| 54 |
| `ema.safetensors` | action-conditioned EMA weights |
|
| 55 |
| `config.json` | model, video, codec, and training settings |
|
| 56 |
| `live_infer.py` | single-file live inference |
|
| 57 |
-
| `
|
| 58 |
|
| 59 |
Actions are encoded as `[left, right]`.
|
|
|
|
| 15 |
|
| 16 |
An action-conditioned Breakout world model. Hold **A / D** (or the arrow keys) and the model generates the next frame.
|
| 17 |
|
| 18 |
+

|
| 19 |
|
| 20 |
128x128 at 6 FPS with 12 frames of latent history. The model has about 70M parameters and uses the frozen SDXL VAE from `madebyollin/sdxl-vae-fp16-fix`.
|
| 21 |
|
|
|
|
| 54 |
| `ema.safetensors` | action-conditioned EMA weights |
|
| 55 |
| `config.json` | model, video, codec, and training settings |
|
| 56 |
| `live_infer.py` | single-file live inference |
|
| 57 |
+
| `demo.gif` | live rollout |
|
| 58 |
|
| 59 |
Actions are encoded as `[left, right]`.
|
demo.gif
ADDED
|
Git LFS Details
|