diff --git a/comfy/cli_args.py b/comfy/cli_args.py
index df3841871..3a14a470d 100644
--- a/comfy/cli_args.py
+++ b/comfy/cli_args.py
@@ -49,7 +49,7 @@ parser.add_argument("--temp-directory", type=str, default=None, help="Set the Co
 parser.add_argument("--input-directory", type=str, default=None, help="Set the ComfyUI input directory. Overrides --base-directory.")
 parser.add_argument("--auto-launch", action="store_true", help="Automatically launch ComfyUI in the default browser.")
 parser.add_argument("--disable-auto-launch", action="store_true", help="Disable auto launching the browser.")
-parser.add_argument("--cuda-device", type=str, default=None, metavar="DEVICE_ID", help="Set the ids of cuda devices this instance will use. All other devices will not be visible.")
+parser.add_argument("--cuda-device", type=str, default=None, metavar="DEVICE_ID", help="Set the ids of cuda devices this instance will use, as a comma-separated list (e.g. '0' or '0,1'). All other devices will not be visible.")
 parser.add_argument("--default-device", type=int, default=None, metavar="DEFAULT_DEVICE_ID", help="Set the id of the default device, all other devices will stay visible.")
 cm_group = parser.add_mutually_exclusive_group()
 cm_group.add_argument("--cuda-malloc", action="store_true", help="Enable cudaMallocAsync (enabled by default for torch 2.0 and up).")
diff --git a/comfy_extras/nodes_multigpu.py b/comfy_extras/nodes_multigpu.py
index 53b50029e..fedafef71 100644
--- a/comfy_extras/nodes_multigpu.py
+++ b/comfy_extras/nodes_multigpu.py
@@ -45,6 +45,16 @@ class MultiGPUCFGSplitNode(io.ComfyNode):
 class MultiGPUOptionsNode(io.ComfyNode):
     """
     Select the relative speed of GPUs in the special case they have significantly different performance from one another.
+
+    NOTE (not registered yet, see MultiGPUExtension.get_node_list below):
+    The output GPUOptionsGroup is plumbed through create_multigpu_deepclones() and stored on
+    model.model_options['multigpu_options'] via GPUOptionsGroup.register(), but the cond
+    scheduler in comfy/samplers.py (calc_cond_batch_outer_multigpu) does NOT yet consult
+    relative_speed when distributing conds across devices; it uses a uniform conds_per_device
+    round-robin via next_available_device(). Before re-enabling this node, wire its
+    relative_speed into the scheduler (e.g. via comfy.multigpu.load_balance_devices(),
+    which already implements the proportional split) so the input actually affects work
+    distribution.
     """
 
     @classmethod