chrisxx commited on
Commit
f266945
·
1 Parent(s): 7a00178

Update keyboard instruction to only mention Up/Down arrows and W/S keys

Browse files
Files changed (1) hide show
  1. static/index.html +1 -1
static/index.html CHANGED
@@ -60,7 +60,7 @@
60
  ⏳ Another player is currently using the stream. Please wait for them to finish.
61
  </div>
62
  <div style="margin-top: 12px; padding: 8px; background: #222; border-radius: 4px; border-left: 3px solid #09f; color: #ccc; font-size: 13px;">
63
- 💡 <strong>Tip:</strong> Click anywhere on this page to enable keyboard controls. Use <strong>Arrow Keys</strong> or <strong>WASD</strong> to control the paddle.
64
  </div>
65
  <div style="margin-top: 12px; font-size: 14px; color: #aaa; line-height: 1.5;">
66
  This demo uses a small transformer model trained with rectified flow matching to simulate Pong game frames conditioned on user inputs. The model generates 24×24 pixel frames in real-time using diffusion sampling with configurable steps. Performance targets ~16 FPS with 4 diffusion steps on GPU hardware.
 
60
  ⏳ Another player is currently using the stream. Please wait for them to finish.
61
  </div>
62
  <div style="margin-top: 12px; padding: 8px; background: #222; border-radius: 4px; border-left: 3px solid #09f; color: #ccc; font-size: 13px;">
63
+ 💡 <strong>Tip:</strong> Click anywhere on this page to enable keyboard controls. Use <strong>↑/↓ Arrow Keys</strong> or <strong>W/S</strong> to control the paddle.
64
  </div>
65
  <div style="margin-top: 12px; font-size: 14px; color: #aaa; line-height: 1.5;">
66
  This demo uses a small transformer model trained with rectified flow matching to simulate Pong game frames conditioned on user inputs. The model generates 24×24 pixel frames in real-time using diffusion sampling with configurable steps. Performance targets ~16 FPS with 4 diffusion steps on GPU hardware.