README: low_vram switch + VRAM notes (ComfyUI node v1.2.2, issue #4)

README.md

@@ -62,6 +62,11 @@ at 4 steps and it breaks.
   **and the pruned/curve variants** (`pruned_int8`, `pruned_fp8`); the ComfyUI
   node auto-detects a pruned base and re-injects the time-conditioning at run
   time, so one LoRA covers every base.
+- **`low_vram`** (node switch): off by default (applies the LoRA at run time —
+  sharpest, some extra peak VRAM). Turn it **on** if you run out of memory: it
+  merges the LoRA into the weights for the lowest peak VRAM, at the cost of a
+  **softer result on quantized (`int8` / `fp8` / pruned) bases**. Lowering the
+  resolution or frame count also helps.
 
 ## Weights
 
@@ -111,7 +116,9 @@ python generate.py \
 - **Resolution / duration**: width/height are multiples of 32; the short edge is
   typically 768. Frame count is at 24 fps and snaps to the model's 17·k+5 grid
   (124 ≈ 5 s). Validated range ~124–362 frames (~5–15 s).
-- **VRAM**: the base model is large (~33 B); an 80 GB GPU is comfortable
-  (`--offload-adaln` in the standalone script trades ~13 GB of VRAM for CPU RAM).
+- **VRAM**: the base model is large (~33 B); an 80 GB GPU is comfortable at the
+  largest resolutions. The ComfyUI node streams the base and adds a `low_vram`
+  switch (see above), so it runs on much smaller GPUs. In the standalone script,
+  `--offload-adaln` trades ~13 GB of VRAM for CPU RAM.
 - **Audio**: 32 kHz stereo, aligned to the video; the two streams ride different
   flow schedules and are integrated each on its own clock.