Upload 2 files

dc.py

@@ -360,8 +360,8 @@ class GuiSD:
             retain_task_model_in_cache=False,
             device="cpu",
         )
-        self.model.load_beta_styles()
-        #self.model.device = torch.device("cpu") #
+        #self.model.load_beta_styles()
+        self.model.device = torch.device("cpu") #
 
     def infer_short(self, model, pipe_params, progress=gr.Progress(track_tqdm=True)):
         #progress(0, desc="Start inference...")
@@ -504,7 +504,7 @@ class GuiSD:
         mode_ip2,
         scale_ip2,
         pag_scale,
-        progress=gr.Progress(track_tqdm=True),
+        #progress=gr.Progress(track_tqdm=True),
     ):
         #progress(0, desc="Preparing inference...")
         
@@ -614,15 +614,15 @@ class GuiSD:
             "high_threshold": high_threshold,
             "value_threshold": value_threshold,
             "distance_threshold": distance_threshold,
-            "lora_A": lora1 if lora1 != "None" else None,
+            "lora_A": lora1 if lora1 != "None" and lora1 != "" else None,
             "lora_scale_A": lora_scale1,
-            "lora_B": lora2 if lora2 != "None" else None,
+            "lora_B": lora2 if lora2 != "None" and lora2 != "" else None,
             "lora_scale_B": lora_scale2,
-            "lora_C": lora3 if lora3 != "None" else None,
+            "lora_C": lora3 if lora3 != "None" and lora3 != "" else None,
             "lora_scale_C": lora_scale3,
-            "lora_D": lora4 if lora4 != "None" else None,
+            "lora_D": lora4 if lora4 != "None" and lora4 != "" else None,
             "lora_scale_D": lora_scale4,
-            "lora_E": lora5 if lora5 != "None" else None,
+            "lora_E": lora5 if lora5 != "None" and lora5 != "" else None,
             "lora_scale_E": lora_scale5,
 ## BEGIN MOD
             "textual_inversion": get_embed_list(self.model.class_name) if textual_inversion else [],
@@ -672,14 +672,14 @@ class GuiSD:
         }
 
         self.model.device = torch.device("cuda:0")
-        if hasattr(self.model.pipe, "transformer") and loras_list != ["None"] * 5:
+        if hasattr(self.model.pipe, "transformer") and loras_list != ["None"] * 5 and loras_list != [""] * 5:
             self.model.pipe.transformer.to(self.model.device)
             print("transformer to cuda")
 
         #progress(1, desc="Inference preparation completed. Starting inference...")
 
         info_state = "" # for yield version
-        return self.infer_short(self.model, pipe_params, progress), info_state
+        return self.infer_short(self.model, pipe_params), info_state
 ## END MOD
 
 def dynamic_gpu_duration(func, duration, *args):
@@ -814,7 +814,7 @@ def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance
     progress(1, desc="Preparation completed. Starting inference...")
 
     progress(0, desc="Loading model...")
-    sd_gen.load_new_model(model_name, vae, TASK_MODEL_LIST[0], progress)
+    sd_gen.load_new_model(model_name, vae, TASK_MODEL_LIST[0])
     progress(1, desc="Model loaded.")
     progress(0, desc="Starting Inference...")
     images, info = sd_gen_generate_pipeline(prompt, negative_prompt, 1, num_inference_steps,

modutils.py

@@ -136,7 +136,7 @@ def save_gallery_images(images, progress=gr.Progress(track_tqdm=True)):
     dt_now = datetime.now(timezone(timedelta(hours=9)))
     basename = dt_now.strftime('%Y%m%d_%H%M%S_')
     i = 1
-    if not images: return images
+    if not images: return images, gr.update(visible=False)
     output_images = []
     output_paths = []
     for image in images:
@@ -153,7 +153,7 @@ def save_gallery_images(images, progress=gr.Progress(track_tqdm=True)):
             output_paths.append(str(newpath))
             output_images.append((str(newpath), str(filename)))
     progress(1, desc="Gallery updated.")
-    return gr.update(value=output_images), gr.update(value=output_paths), gr.update(visible=True)
+    return gr.update(value=output_images), gr.update(value=output_paths, visible=True)
 
 
 def download_private_repo(repo_id, dir_path, is_replace):