Remove standalone install note

README.md

@@ -17,12 +17,10 @@ A small action-conditioned world model that learned to keep a Pong match going.
 
 ![demo](demo.gif)
 
-128×128 at 6 FPS with a 12-frame latent history. Codec is a frozen SDXL VAE (`madebyollin/sdxl-vae-fp16-fix`). Needs a CUDA GPU with BF16.
+128x128 at 6 FPS with a 12-frame latent history. Codec is a frozen SDXL VAE (`madebyollin/sdxl-vae-fp16-fix`). Needs a CUDA GPU with BF16.
 
 ## Play it
 
-`live_infer.py` is standalone — no livediffusion package install.
-
 ```bash
 pip install torch numpy pillow safetensors huggingface_hub diffusers
 
@@ -45,7 +43,7 @@ Controls: **W** up, **S** down (A/D also work). Click the window once so it has
 |---|---|
 | `ema.safetensors` | playable weights |
 | `config.json` | video / model / codec settings used at train time |
-| `live_infer.py` | standalone live play script |
+| `live_infer.py` | live play script |
 | `demo.gif` | live rollout clip |
 
 Action vector is `[W, S]` as floats in `{0,1}`. Hold both and it treats that as neutral.