Focal crop UI elements

modules/textual_inversion/preprocess.py

@@ -13,7 +13,7 @@ if cmd_opts.deepdanbooru:
     import modules.deepbooru as deepbooru
 
 
-def preprocess(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_entropy_focus=False):
+def preprocess(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False):
     try:
         if process_caption:
             shared.interrogator.load()
@@ -23,7 +23,7 @@ def preprocess(process_src, process_dst, process_width, process_height, preproce
             db_opts[deepbooru.OPT_INCLUDE_RANKS] = False
             deepbooru.create_deepbooru_process(opts.interrogate_deepbooru_score_threshold, db_opts)
 
-        preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru, split_threshold, overlap_ratio, process_entropy_focus)
+        preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru, split_threshold, overlap_ratio, process_focal_crop, process_focal_crop_face_weight, process_focal_crop_entropy_weight, process_focal_crop_edges_weight, process_focal_crop_debug)
 
     finally:
 
@@ -35,7 +35,7 @@ def preprocess(process_src, process_dst, process_width, process_height, preproce
 
 
 
-def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_entropy_focus=False):
+def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False):
     width = process_width
     height = process_height
     src = os.path.abspath(process_src)
@@ -139,27 +139,27 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre
             ratio = (img.height * width) / (img.width * height)
             inverse_xy = True
 
-        processing_option_ran = False
+        process_default_resize = True
 
         if process_split and ratio < 1.0 and ratio <= split_threshold:
             for splitted in split_pic(img, inverse_xy):
                 save_pic(splitted, index, existing_caption=existing_caption)
-            processing_option_ran = True
+            process_default_resize = False
 
         if process_entropy_focus and img.height != img.width:
             autocrop_settings = autocrop.Settings(
                 crop_width = width,
                 crop_height = height,
-                face_points_weight = 0.9,
-                entropy_points_weight = 0.7,
-                corner_points_weight = 0.5,
-                annotate_image = False
+                face_points_weight = process_focal_crop_face_weight,
+                entropy_points_weight = process_focal_crop_entropy_weight,
+                corner_points_weight = process_focal_crop_edges_weight,
+                annotate_image = process_focal_crop_debug
             )
-            focal = autocrop.crop_image(img, autocrop_settings)
+            for focal in autocrop.crop_image(img, autocrop_settings):
                 save_pic(focal, index, existing_caption=existing_caption)
-            processing_option_ran = True
+            process_default_resize = False
 
-        if not processing_option_ran:
+        if process_default_resize:
             img = images.resize_image(1, img, width, height)
             save_pic(img, index, existing_caption=existing_caption)
 

modules/ui.py

@@ -1260,7 +1260,7 @@ def create_ui(wrap_gradio_gpu_call):
                     with gr.Row():
                         process_flip = gr.Checkbox(label='Create flipped copies')
                         process_split = gr.Checkbox(label='Split oversized images')
-                        process_entropy_focus = gr.Checkbox(label='Create auto focal point crop')
+                        process_focal_crop = gr.Checkbox(label='Auto focal point crop')
                         process_caption = gr.Checkbox(label='Use BLIP for caption')
                         process_caption_deepbooru = gr.Checkbox(label='Use deepbooru for caption', visible=True if cmd_opts.deepdanbooru else False)
 
@@ -1268,6 +1268,12 @@ def create_ui(wrap_gradio_gpu_call):
                         process_split_threshold = gr.Slider(label='Split image threshold', value=0.5, minimum=0.0, maximum=1.0, step=0.05)
                         process_overlap_ratio = gr.Slider(label='Split image overlap ratio', value=0.2, minimum=0.0, maximum=0.9, step=0.05)
 
+                    with gr.Row(visible=False) as process_focal_crop_row:
+                        process_focal_crop_face_weight = gr.Slider(label='Focal point face weight', value=0.9, minimum=0.0, maximum=1.0, step=0.05)
+                        process_focal_crop_entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.3, minimum=0.0, maximum=1.0, step=0.05)
+                        process_focal_crop_edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05)
+                        process_focal_crop_debug = gr.Checkbox(label='Create debug image')
+
                     with gr.Row():
                         with gr.Column(scale=3):
                             gr.HTML(value="")
@@ -1281,6 +1287,12 @@ def create_ui(wrap_gradio_gpu_call):
                         outputs=[process_split_extra_row],
                     )
 
+                    process_focal_crop.change(
+                        fn=lambda show: gr_show(show),
+                        inputs=[process_focal_crop],
+                        outputs=[process_focal_crop_row],
+                    )
+
                 with gr.Tab(label="Train"):
                     gr.HTML(value="<p style='margin-bottom: 0.7em'>Train an embedding or Hypernetwork; you must specify a directory with a set of 1:1 ratio images <a href=\"https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Textual-Inversion\" style=\"font-weight:bold;\">[wiki]</a></p>")
                     with gr.Row():
@@ -1368,7 +1380,11 @@ def create_ui(wrap_gradio_gpu_call):
                 process_caption_deepbooru,
                 process_split_threshold,
                 process_overlap_ratio,
-                process_entropy_focus,
+                process_focal_crop,
+                process_focal_crop_face_weight,
+                process_focal_crop_entropy_weight,
+                process_focal_crop_edges_weight,
+                process_focal_crop_debug,
             ],
             outputs=[
                 ti_output,