tidy the Space README

README.md

@@ -39,25 +39,24 @@ continues instead of cutting.
 `wan21_patches/` here are copies of the GitHub repo's; the Wan2.1 reference code is
 cloned and patched at startup exactly as `setup.sh` does.
 
-Two differences from running it locally, both forced by ZeroGPU:
+**Steering is a schedule, not a button.** This is the one real difference from the
+local demo. A GPU worker is forked per request and cannot be steered from outside
+while it runs, so the swap is given up front — "switch to this at t = N seconds" —
+rather than clicked mid-stream. The swap itself is the live one: `Engine.steer`
+replaces the cross-attention conditioning and leaves the K/V cache in place.
 
-- **Steering is a schedule, not a button.** A GPU worker is forked per request and
-  cannot be steered from outside while it runs, so the demo takes the swap up front
-  ("switch to this prompt at t = N seconds"). The swap itself is the live one:
-  `Engine.steer` replaces the cross-attention conditioning and leaves the cache in
-  place.
-Free-text steers work here: umt5-xxl is downloaded and loaded at module scope so
-ZeroGPU packs it with the rest of the weights rather than making every cold worker
-pay for a lazy 11 GB load. That is most of why this Space pulls 29 GB at startup.
-Free text is not numerically comparable to the 96-prompt bank, though — umt5
-embeddings differ slightly by hardware, so the same string encoded on the training
-box is a slightly different tensor.
+Steers can come from the 96-prompt bank or from free text. umt5-xxl is downloaded
+and loaded at module scope, so ZeroGPU packs it with the rest of the weights instead
+of making every cold worker pay for a lazy 11 GB load; it is most of why this Space
+pulls 29 GB at startup. Free text is not numerically comparable to the bank, though
+— umt5 embeddings differ slightly by hardware, so the same string encoded on the
+training box is a slightly different tensor.
 
-`torch.compile` of the VAE decoder is also off, since it cannot run in a ZeroGPU
-worker, and that is what keeps this Space below real time. Measured here: 386 ms to
-generate a block and 631 ms to decode it, against a 750 ms budget — **0.74× real
-time**. Decoding is the whole of the gap; locally, with the decoder compiled, it
-takes 343 ms and the same checkpoint sustains about 2.7× real time.
+`torch.compile` of the VAE decoder is off, since it cannot run in a ZeroGPU worker,
+and that is what keeps this Space below real time. Measured here: 386 ms to generate
+a block and 631 ms to decode it, against a 750 ms budget — **0.74× real time**.
+Decoding is the whole of the gap; locally, with the decoder compiled, it takes
+343 ms and the same checkpoint sustains about 2.7× real time.
 
 Two more things this port had to work around, both specific to running inside a
 forked ZeroGPU worker: