diff --git a/models/ModelBase.py b/models/ModelBase.py
index 5c0c129..3cb88c5 100644
--- a/models/ModelBase.py
+++ b/models/ModelBase.py
@@ -132,6 +132,7 @@ class ModelBase(object):
 
         self.iter = 0
         self.options = {}
+        self.options_show_override = {}
         self.loss_history = []
         self.sample_for_preview = None
         self.choosed_gpu_indexes = None
@@ -532,10 +533,13 @@ class ModelBase(object):
         return self.get_strpath_storage_for_file('summary.txt')
 
     def get_summary_text(self):
+        visible_options = self.options.copy()
+        visible_options.update(self.options_show_override)
+        
         ###Generate text summary of model hyperparameters
         #Find the longest key name and value string. Used as column widths.
-        width_name = max([len(k) for k in self.options.keys()] + [17]) + 1 # Single space buffer to left edge. Minimum of 17, the length of the longest static string used "Current iteration"
-        width_value = max([len(str(x)) for x in self.options.values()] + [len(str(self.get_iter())), len(self.get_model_name())]) + 1 # Single space buffer to right edge
+        width_name = max([len(k) for k in visible_options.keys()] + [17]) + 1 # Single space buffer to left edge. Minimum of 17, the length of the longest static string used "Current iteration"
+        width_value = max([len(str(x)) for x in visible_options.values()] + [len(str(self.get_iter())), len(self.get_model_name())]) + 1 # Single space buffer to right edge
         if len(self.device_config.devices) != 0: #Check length of GPU names
             width_value = max([len(device.name)+1 for device in self.device_config.devices] + [width_value])
         width_total = width_name + width_value + 2 #Plus 2 for ": "
@@ -550,8 +554,8 @@ class ModelBase(object):
 
         summary_text += [f'=={" Model Options ":-^{width_total}}=='] # Model options
         summary_text += [f'=={" "*width_total}==']
-        for key in self.options.keys():
-            summary_text += [f'=={key: >{width_name}}: {str(self.options[key]): <{width_value}}=='] # self.options key/value pairs
+        for key in visible_options.keys():
+            summary_text += [f'=={key: >{width_name}}: {str(visible_options[key]): <{width_value}}=='] # visible_options key/value pairs
         summary_text += [f'=={" "*width_total}==']
 
         summary_text += [f'=={" Running On ":-^{width_total}}=='] # Training hardware info
diff --git a/models/Model_SAEHD/Model.py b/models/Model_SAEHD/Model.py
index 24058b1..3803504 100644
--- a/models/Model_SAEHD/Model.py
+++ b/models/Model_SAEHD/Model.py
@@ -175,7 +175,7 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
                           'head' : FaceType.HEAD}[ self.options['face_type'] ]
 
         eyes_prio = self.options['eyes_prio']
-        
+
         archi_split = self.options['archi'].split('-')
 
         if len(archi_split) == 2:
@@ -191,9 +191,17 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
         if self.pretrain_just_disabled:
             self.set_iter(0)
 
-        self.gan_power = gan_power = self.options['gan_power'] if not self.pretrain else 0.0
+        self.gan_power = gan_power = 0.0 if self.pretrain else self.options['gan_power']
         random_warp = False if self.pretrain else self.options['random_warp']
 
+        if self.pretrain:
+            self.options_show_override['gan_power'] = 0.0
+            self.options_show_override['random_warp'] = False
+            self.options_show_override['lr_dropout'] = 'n'
+            self.options_show_override['face_style_power'] = 0.0
+            self.options_show_override['bg_style_power'] = 0.0
+            self.options_show_override['uniform_yaw'] = True
+
         masked_training = self.options['masked_training']
         ct_mode = self.options['ct_mode']
         if ct_mode == 'none':
@@ -454,7 +462,7 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
                                               DLoss(gpu_pred_src_src_d_zeros   , gpu_pred_src_src_d) ) * 0.5 + \
                                              (DLoss(gpu_target_src_d2_ones      , gpu_target_src_d2) + \
                                               DLoss(gpu_pred_src_src_d2_zeros   , gpu_pred_src_src_d2) ) * 0.5
-                            
+
                         gpu_D_src_dst_loss_gvs += [ nn.gradients (gpu_D_src_dst_loss, self.D_src.get_weights() ) ]#+self.D_src_x2.get_weights()
 
                         gpu_G_loss += gan_power*(DLoss(gpu_pred_src_src_d_ones, gpu_pred_src_src_d)  + \