diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py
index bd1a0936..62ba9101 100644
--- a/modules/sd_hijack.py
+++ b/modules/sd_hijack.py
@@ -245,7 +245,7 @@ class StableDiffusionModelHijack:
 
         if cmd_opts.opt_split_attention_v1:
             ldm.modules.attention.CrossAttention.forward = split_cross_attention_forward_v1
-        elif not cmd_opts.disable_opt_split_attention:
+        elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention or torch.cuda.is_available()):
             ldm.modules.attention.CrossAttention.forward = split_cross_attention_forward
             ldm.modules.diffusionmodules.model.nonlinearity = nonlinearity_hijack
             ldm.modules.diffusionmodules.model.AttnBlock.forward = cross_attention_attnblock_forward
diff --git a/modules/shared.py b/modules/shared.py
index d04147ad..9e802c92 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -36,8 +36,8 @@ parser.add_argument("--precision", type=str, help="evaluate at this precision",
 parser.add_argument("--share", action='store_true', help="use share=True for gradio and make the UI accessible through their site (doesn't work for me but you might have better luck)")
 parser.add_argument("--esrgan-models-path", type=str, help="path to directory with ESRGAN models", default=os.path.join(script_path, 'ESRGAN'))
 parser.add_argument("--swinir-models-path", type=str, help="path to directory with SwinIR models", default=os.path.join(script_path, 'SwinIR'))
-parser.add_argument("--opt-split-attention", action='store_true', help="does not do anything")
-parser.add_argument("--disable-opt-split-attention", action='store_true', help="disable an optimization that reduces vram usage by a lot")
+parser.add_argument("--opt-split-attention", action='store_true', help="force-enables cross-attention layer optimization. By default, it's on for torch.cuda and off for other torch devices.")
+parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
 parser.add_argument("--opt-split-attention-v1", action='store_true', help="enable older version of split attention optimization that does not consume all the VRAM it can find")
 parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
 parser.add_argument("--port", type=int, help="launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available", default=None)
@@ -54,9 +54,6 @@ parser.add_argument("--use-textbox-seed", action='store_true', help="use textbox
 
 cmd_opts = parser.parse_args()
 
-if cmd_opts.opt_split_attention:
-    print("Information: --opt-split-attention is now the default. To remove this message, remove --opt-split-attention from command line arguments. To disable the optimization, use --disable-opt-split-attention")
-
 device = get_optimal_device()
 
 batch_cond_uncond = cmd_opts.always_batch_cond_uncond or not (cmd_opts.lowvram or cmd_opts.medvram)