Update default FPS to 16 for better GPU

README.md

@@ -17,7 +17,7 @@ A real-time Pong game where frames are generated by a diffusion model trained wi
 - **Real-time frame generation**: Uses a frame-autoregressive transformer with diffusion sampling
 - **Interactive gameplay**: Control the paddle with keyboard inputs
 - **Configurable parameters**: Adjust FPS and diffusion steps
-- **Low-latency streaming**: Achieves ~12 FPS with 4 diffusion steps
+- **Low-latency streaming**: Achieves ~16 FPS with 4 diffusion steps
 
 ## How to Play
 
@@ -31,7 +31,7 @@ A real-time Pong game where frames are generated by a diffusion model trained wi
 
 ## Technical Details
 
-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 ~12 FPS with 4 diffusion steps on GPU hardware.
+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.
 
 ## Model Architecture
 

static/index.html

@@ -37,7 +37,7 @@
       <h1>Pong</h1>
       <div style="margin-bottom: 12px;">
         <label style="display: block; margin-bottom: 8px;">
-          FPS: <input type="number" id="fpsInput" value="12" min="1" max="30" step="1" style="width: 60px; padding: 4px; margin-left: 8px;" />
+          FPS: <input type="number" id="fpsInput" value="16" min="1" max="30" step="1" style="width: 60px; padding: 4px; margin-left: 8px;" />
           <span style="color: #aaa; font-size: 12px; margin-left: 8px;">frames per second</span>
         </label>
         <label style="display: block; margin-bottom: 8px;">
@@ -60,7 +60,7 @@
         ⏳ Another player is currently using the stream. Please wait for them to finish.
       </div>
       <div style="margin-top: 12px; font-size: 14px; color: #aaa; line-height: 1.5;">
-        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 ~12 FPS with 4 diffusion steps on GPU hardware.
+        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.
       </div>
     </div>
 
@@ -107,7 +107,7 @@
 
       // Start/stop controls
       startBtn.addEventListener('click', () => {
-        const fps = parseInt(document.getElementById('fpsInput').value) || 12;
+        const fps = parseInt(document.getElementById('fpsInput').value) || 16;
         const n_steps = parseInt(document.getElementById('stepsInput').value) || 1;
         socket.emit('start_stream', { n_steps: n_steps, cfg: 0.0, fps: fps, clamp: true });
       });