Merge pull request #3139 from captin411/focal-point-cropping

[Preprocess image] New option to auto crop based on complexity, edges, faces

1 files changed, 18 insertions, 0 deletions

diff --git a/modules/ui.py b/modules/ui.py
index 8e343258..0a63e357 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -1261,6 +1261,7 @@ 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_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 +1269,12 @@ 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=0.15, 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 +1288,12 @@ 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():

@@ -1369,6 +1382,11 @@ def create_ui(wrap_gradio_gpu_call):
                 process_caption_deepbooru,

                 process_split_threshold,

                 process_overlap_ratio,

+                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,