update

ldm/modules/encoders/modules.py

@@ -13,6 +13,13 @@ from ldm.util import default, instantiate_from_config
 from ldm.modules.diffusionmodules.util import make_beta_schedule, extract_into_tensor, noise_like
 import clip
 
+if torch.cuda.is_available():
+  _device = "cuda"
+elif torch.backends.mps.is_available():
+  _device = "mps"
+else:
+  _device = "cpu"
+
 class AbstractEncoder(nn.Module):
     def __init__(self):
         super().__init__()
@@ -30,7 +37,8 @@ def disabled_train(self, mode=True):
 
 class FrozenCLIPEmbedder(AbstractEncoder):
     """Uses the CLIP transformer encoder for text (from huggingface)"""
-    def __init__(self, version="openai/clip-vit-large-patch14", device="cuda", max_length=77):  # clip-vit-base-patch32
+    #def __init__(self, version="openai/clip-vit-large-patch14", device="cuda", max_length=77):  # clip-vit-base-patch32
+    def __init__(self, version="openai/clip-vit-large-patch14", device=_device, max_length=77):  # clip-vit-base-patch32
         super().__init__()
         self.tokenizer = CLIPTokenizer.from_pretrained(version)
         self.transformer = CLIPTextModel.from_pretrained(version)