ar

app.py

@@ -121,13 +121,13 @@ state_dict = torch.load(checkpoint_path, map_location=device)
 nnet_1.load_state_dict(state_dict)
 nnet_1.eval()
 
-filename = "pretrained_models/t2i_512px_clip_dimr.pth"
-checkpoint_path = hf_hub_download(repo_id=repo_id, filename=filename)
-nnet_2 = utils.get_nnet(**config_2.nnet)
-nnet_2 = nnet_2.to(device)
-state_dict = torch.load(checkpoint_path, map_location=device)
-nnet_2.load_state_dict(state_dict)
-nnet_2.eval()
+# filename = "pretrained_models/t2i_512px_clip_dimr.pth"
+# checkpoint_path = hf_hub_download(repo_id=repo_id, filename=filename)
+# nnet_2 = utils.get_nnet(**config_2.nnet)
+# nnet_2 = nnet_2.to(device)
+# state_dict = torch.load(checkpoint_path, map_location=device)
+# nnet_2.load_state_dict(state_dict)
+# nnet_2.eval()
 
 # Initialize text model.
 llm = "clip"
@@ -181,10 +181,11 @@ def infer(
     else:
         assert num_of_interpolation == 3, "For arithmetic, please sample three images."
 
-    if num_of_interpolation == 3:
-        nnet = nnet_2
-    else:
-        nnet = nnet_1
+    # if num_of_interpolation == 3:
+    #     nnet = nnet_2
+    # else:
+    #     nnet = nnet_1
+    nnet = nnet_1
     
     # Get text embeddings and tokens.
     _context, _token_mask, _token, _caption = get_caption(
@@ -301,7 +302,7 @@ examples_1 = [
 ]
 
 examples_2 = [
-    ["A corgi in the park", "red hat"],
+    ["A dog wearing sunglasses", "red hat"],
 ]
 
 css = """