Merge pull request #1851 from C43H66N12O12S2/flash

xformers attention

1 files changed, 2 insertions, 1 deletions

diff --git a/modules/shared.py b/modules/shared.py
index 475d7e52..d68df751 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -43,6 +43,7 @@ parser.add_argument("--realesrgan-models-path", type=str, help="Path to director
 parser.add_argument("--scunet-models-path", type=str, help="Path to directory with ScuNET model file(s).", default=os.path.join(models_path, 'ScuNET'))

 parser.add_argument("--swinir-models-path", type=str, help="Path to directory with SwinIR model file(s).", default=os.path.join(models_path, 'SwinIR'))

 parser.add_argument("--ldsr-models-path", type=str, help="Path to directory with LDSR model file(s).", default=os.path.join(models_path, 'LDSR'))

+parser.add_argument("--disable-opt-xformers-attention", action='store_true', help="force-disables xformers attention optimization")

 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")

@@ -73,7 +74,7 @@ device = devices.device
 

 batch_cond_uncond = cmd_opts.always_batch_cond_uncond or not (cmd_opts.lowvram or cmd_opts.medvram)

 parallel_processing_allowed = not cmd_opts.lowvram and not cmd_opts.medvram

-

+xformers_available = False

 config_filename = cmd_opts.ui_settings_file

 

 hypernetworks = hypernetwork.load_hypernetworks(os.path.join(models_path, 'hypernetworks'))