Update ldm/modules/encoders/modules.py

ldm/modules/encoders/modules.py

@@ -151,7 +151,6 @@ class FrozenOpenCLIPEmbedder(AbstractEncoder):
         )
 
         self.model = open_clip.create_model(arch, pretrained=pretrained_path)
-        self.tokenizer = open_clip.tokenizer.SimpleTokenizer()
 
         if hasattr(self.model, "visual"):
             delattr(self.model, "visual")
@@ -174,8 +173,9 @@ class FrozenOpenCLIPEmbedder(AbstractEncoder):
             param.requires_grad = False
 
     def forward(self, text):
-        tokens = [self.tokenizer.encode(t) for t in text]
-        tokens = torch.tensor(tokens).to(self.device)
+        tokens = open_clip.tokenize(text, context_length=self.max_length).to(self.device)
+            if tokens.dim() == 1:
+                tokens = tokens.unsqueeze(0)
         z = self.encode_with_transformer(tokens)
         return z
 
@@ -217,6 +217,4 @@ class FrozenCLIPT5Encoder(AbstractEncoder):
     def forward(self, text):
         clip_z = self.clip_encoder.encode(text)
         t5_z = self.t5_encoder.encode(text)
-        return [clip_z, t5_z]
-
-
+        return [clip_z, t5_z]