Merge pull request #1185 from bmaltais/checkpoint-merger-ui-improvement

(feat): Rework Checkpoint Merger UI for better clarity and usability

modules/extras.py

@@ -140,7 +140,7 @@ def run_pnginfo(image):
     return '', geninfo, info
 
 
-def run_modelmerger(modelname_0, modelname_1, interp_method, interp_amount):
+def run_modelmerger(primary_model_name, secondary_model_name, interp_method, interp_amount):
     # Linear interpolation (https://en.wikipedia.org/wiki/Linear_interpolation)
     def weighted_sum(theta0, theta1, alpha):
         return ((1 - alpha) * theta0) + (alpha * theta1)
@@ -150,26 +150,26 @@ def run_modelmerger(modelname_0, modelname_1, interp_method, interp_amount):
         alpha = alpha * alpha * (3 - (2 * alpha))
         return theta0 + ((theta1 - theta0) * alpha)
 
-    if os.path.exists(modelname_0):
+    if os.path.exists(primary_model_name):
-        model0_filename = modelname_0
+        primary_model_filename = primary_model_name
-        modelname_0 = os.path.splitext(os.path.basename(modelname_0))[0]
+        primary_model_name = os.path.splitext(os.path.basename(primary_model_name))[0]
     else:
-        model0_filename = 'models/' + modelname_0 + '.ckpt'
+        primary_model_filename = 'models/' + primary_model_name + '.ckpt'
 
-    if os.path.exists(modelname_1):
+    if os.path.exists(secondary_model_name):
-        model1_filename = modelname_1
+        secondary_model_filename = secondary_model_name
-        modelname_1 = os.path.splitext(os.path.basename(modelname_1))[0]
+        secondary_model_name = os.path.splitext(os.path.basename(secondary_model_name))[0]
     else:
-        model1_filename = 'models/' + modelname_1 + '.ckpt'
+        secondary_model_filename = 'models/' + secondary_model_name + '.ckpt'
 
-    print(f"Loading {model0_filename}...")
+    print(f"Loading {primary_model_filename}...")
-    model_0 = torch.load(model0_filename, map_location='cpu')
+    primary_model = torch.load(primary_model_filename, map_location='cpu')
 
-    print(f"Loading {model1_filename}...")
+    print(f"Loading {secondary_model_filename}...")
-    model_1 = torch.load(model1_filename, map_location='cpu')
+    secondary_model = torch.load(secondary_model_filename, map_location='cpu')
    
-    theta_0 = model_0['state_dict']
+    theta_0 = primary_model['state_dict']
-    theta_1 = model_1['state_dict']
+    theta_1 = secondary_model['state_dict']
 
     theta_funcs = {
         "Weighted Sum": weighted_sum,
@@ -180,15 +180,15 @@ def run_modelmerger(modelname_0, modelname_1, interp_method, interp_amount):
     print(f"Merging...")
     for key in tqdm.tqdm(theta_0.keys()):
         if 'model' in key and key in theta_1:
-            theta_0[key] = theta_func(theta_0[key], theta_1[key], interp_amount)
+            theta_0[key] = theta_func(theta_0[key], theta_1[key], (float(1.0) - interp_amount)) # Need to reverse the interp_amount to match the desired mix ration in the merged checkpoint
     
     for key in theta_1.keys():
         if 'model' in key and key not in theta_0:
             theta_0[key] = theta_1[key]
 
-    output_modelname = 'models/' + modelname_0 + '-' + modelname_1 + '-' + interp_method.replace(" ", "_") + '-' + str(interp_amount) + '-merged.ckpt'
+    output_modelname = 'models/' + primary_model_name + '_' + str(round(interp_amount,2)) + '-' + secondary_model_name + '_' + str(round((float(1.0) - interp_amount),2)) + '-' + interp_method.replace(" ", "_") + '-merged.ckpt'
     print(f"Saving to {output_modelname}...")
-    torch.save(model_0, output_modelname)
+    torch.save(primary_model, output_modelname)
 
     print(f"Checkpoint saved.")
     return "Checkpoint saved to " + output_modelname

modules/sd_models.py

@@ -10,7 +10,7 @@ from ldm.util import instantiate_from_config
 
 from modules import shared
 
-CheckpointInfo = namedtuple("CheckpointInfo", ['filename', 'title', 'hash'])
+CheckpointInfo = namedtuple("CheckpointInfo", ['filename', 'title', 'hash', 'model_name'])
 checkpoints_list = {}
 
 try:
@@ -45,7 +45,8 @@ def list_models():
     if os.path.exists(cmd_ckpt):
         h = model_hash(cmd_ckpt)
         title = modeltitle(cmd_ckpt, h)
-        checkpoints_list[title] = CheckpointInfo(cmd_ckpt, title, h)
+        model_name = title.rsplit(".",1)[0] # remove extension if present
+        checkpoints_list[title] = CheckpointInfo(cmd_ckpt, title, h, model_name)
     elif cmd_ckpt is not None and cmd_ckpt != shared.default_sd_model_file:
         print(f"Checkpoint in --ckpt argument not found: {cmd_ckpt}", file=sys.stderr)
 
@@ -53,7 +54,8 @@ def list_models():
         for filename in glob.glob(model_dir + '/**/*.ckpt', recursive=True):
             h = model_hash(filename)
             title = modeltitle(filename, h)
-            checkpoints_list[title] = CheckpointInfo(filename, title, h)
+            model_name = title.rsplit(".",1)[0] # remove extension if present
+            checkpoints_list[title] = CheckpointInfo(filename, title, h, model_name)
 
 
 def model_hash(filename):

modules/ui.py

@@ -859,10 +859,12 @@ def create_ui(txt2img, img2img, run_extras, run_pnginfo, run_modelmerger):
             with gr.Column(variant='panel'):
                 gr.HTML(value="<p>A merger of the two checkpoints will be generated in your <b>/models</b> directory.</p>")
                 
-                modelname_0 = gr.Textbox(elem_id="modelmerger_modelname_0", label="Model Name (to)")
+                with gr.Row():
-                modelname_1 = gr.Textbox(elem_id="modelmerger_modelname_1", label="Model Name (from)")
+                    ckpt_name_list = sorted([x.model_name for x in modules.sd_models.checkpoints_list.values()])
-                interp_method = gr.Radio(choices=["Weighted Sum", "Sigmoid"], value="Weighted Sum", label="Interpolation Method")
+                    primary_model_name   = gr.Dropdown(ckpt_name_list, elem_id="modelmerger_primary_model_name", label="Primary Model Name")
+                    secondary_model_name = gr.Dropdown(ckpt_name_list, elem_id="modelmerger_secondary_model_name", label="Secondary Model Name")
                 interp_amount = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Interpolation Amount', value=0.3)
+                interp_method = gr.Radio(choices=["Weighted Sum", "Sigmoid"], value="Weighted Sum", label="Interpolation Method")
                 submit = gr.Button(elem_id="modelmerger_merge", label="Merge", variant='primary')
             
             with gr.Column(variant='panel'):
@@ -871,8 +873,8 @@ def create_ui(txt2img, img2img, run_extras, run_pnginfo, run_modelmerger):
             submit.click(
                 fn=run_modelmerger,
                 inputs=[
-                    modelname_0,
+                    primary_model_name,
-                    modelname_1,
+                    secondary_model_name,
                     interp_method,
                     interp_amount
                 ],