Xformers is now properly disabled when --cpu used.

Added --windows-standalone-build option, currently it only opens
makes the code open up comfyui in the browser.

comfy/ldm/modules/attention.py

@@ -14,9 +14,8 @@ import model_management
 try:
     import xformers
     import xformers.ops
-    XFORMERS_IS_AVAILBLE = True
 except:
-    XFORMERS_IS_AVAILBLE = False
+    pass
 
 # CrossAttn precision handling
 import os
@@ -481,7 +480,7 @@ class CrossAttentionPytorch(nn.Module):
         return self.to_out(out)
 
 import sys
-if XFORMERS_IS_AVAILBLE == False or "--disable-xformers" in sys.argv:
+if model_management.xformers_enabled() == False:
     if "--use-split-cross-attention" in sys.argv:
         print("Using split optimization for cross attention")
         CrossAttention = CrossAttentionDoggettx

comfy/ldm/modules/diffusionmodules/model.py

@@ -12,10 +12,8 @@ import model_management
 try:
     import xformers
     import xformers.ops
-    XFORMERS_IS_AVAILBLE = True
 except:
-    XFORMERS_IS_AVAILBLE = False
-    print("No module 'xformers'. Proceeding without it.")
+    pass
 
 try:
     OOM_EXCEPTION = torch.cuda.OutOfMemoryError
@@ -315,7 +313,7 @@ class MemoryEfficientCrossAttentionWrapper(MemoryEfficientCrossAttention):
 
 def make_attn(in_channels, attn_type="vanilla", attn_kwargs=None):
     assert attn_type in ["vanilla", "vanilla-xformers", "memory-efficient-cross-attn", "linear", "none"], f'attn_type {attn_type} unknown'
-    if XFORMERS_IS_AVAILBLE and attn_type == "vanilla":
+    if model_management.xformers_enabled() and attn_type == "vanilla":
         attn_type = "vanilla-xformers"
     print(f"making attention of type '{attn_type}' with {in_channels} in_channels")
     if attn_type == "vanilla":

comfy/model_management.py

@@ -31,6 +31,16 @@ try:
 except:
     pass
 
+try:
+    import xformers
+    import xformers.ops
+    XFORMERS_IS_AVAILBLE = True
+except:
+    XFORMERS_IS_AVAILBLE = False
+
+if "--disable-xformers" in sys.argv:
+    XFORMERS_IS_AVAILBLE = False
+
 if "--cpu" in sys.argv:
     vram_state = CPU
 if "--lowvram" in sys.argv:
@@ -159,6 +169,11 @@ def get_autocast_device(dev):
         return dev.type
     return "cuda"
 
+def xformers_enabled():
+    if vram_state == CPU:
+        return False
+    return XFORMERS_IS_AVAILBLE
+
 def get_free_memory(dev=None, torch_free_too=False):
     if dev is None:
         dev = get_torch_device()