From 087609ee181a91a523647435ffffa6288a317e2f Mon Sep 17 00:00:00 2001 From: captin411 Date: Wed, 19 Oct 2022 03:19:35 -0700 Subject: UI changes for focal point image cropping --- modules/ui.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'modules/ui.py') diff --git a/modules/ui.py b/modules/ui.py index 1ff7eb4f..b6be713b 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -1234,6 +1234,7 @@ 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 into two') + process_entropy_focus = gr.Checkbox(label='Create 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) @@ -1318,7 +1319,8 @@ def create_ui(wrap_gradio_gpu_call): process_flip, process_split, process_caption, - process_caption_deepbooru + process_caption_deepbooru, + process_entropy_focus ], outputs=[ ti_output, -- cgit v1.2.3 From db8ed5fe5cd6e967d12d43d96b7f83083e58626c Mon Sep 17 00:00:00 2001 From: captin411 Date: Tue, 25 Oct 2022 15:22:29 -0700 Subject: Focal crop UI elements --- modules/textual_inversion/preprocess.py | 26 +++++++++++++------------- modules/ui.py | 20 ++++++++++++++++++-- 2 files changed, 31 insertions(+), 15 deletions(-) (limited to 'modules/ui.py') diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index a8c17c6f..1e4d4de8 100644 --- a/modules/textual_inversion/preprocess.py +++ b/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) - save_pic(focal, index, existing_caption=existing_caption) - processing_option_ran = True + for focal in autocrop.crop_image(img, autocrop_settings): + save_pic(focal, index, existing_caption=existing_caption) + 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) diff --git a/modules/ui.py b/modules/ui.py index 028eb4e5..95b9c703 100644 --- a/modules/ui.py +++ b/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="

Train an embedding or Hypernetwork; you must specify a directory with a set of 1:1 ratio images [wiki]

") 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, -- cgit v1.2.3 From df0c5ea29d7f0c682ac81f184f3e482a6450d018 Mon Sep 17 00:00:00 2001 From: captin411 Date: Tue, 25 Oct 2022 17:06:59 -0700 Subject: update default weights --- modules/textual_inversion/autocrop.py | 16 ++++++++-------- modules/ui.py | 2 +- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'modules/ui.py') diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index 01a92b12..9859974a 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -71,9 +71,9 @@ def crop_image(im, settings): return results def focal_point(im, settings): - corner_points = image_corner_points(im, settings) - entropy_points = image_entropy_points(im, settings) - face_points = image_face_points(im, settings) + corner_points = image_corner_points(im, settings) if settings.corner_points_weight > 0 else [] + entropy_points = image_entropy_points(im, settings) if settings.entropy_points_weight > 0 else [] + face_points = image_face_points(im, settings) if settings.face_points_weight > 0 else [] pois = [] @@ -144,7 +144,7 @@ def image_face_points(im, settings): settings.dnn_model_path, "", (im.width, im.height), - 0.8, # score threshold + 0.9, # score threshold 0.3, # nms threshold 5000 # keep top k before nms ) @@ -159,7 +159,7 @@ def image_face_points(im, settings): results.append( PointOfInterest( int(x + (w * 0.5)), # face focus left/right is center - int(y + (h * 0)), # face focus up/down is close to the top of the head + int(y + (h * 0.33)), # face focus up/down is close to the top of the head size = w, weight = 1/len(faces[1]) ) @@ -207,7 +207,7 @@ def image_corner_points(im, settings): np_im, maxCorners=100, qualityLevel=0.04, - minDistance=min(grayscale.width, grayscale.height)*0.03, + minDistance=min(grayscale.width, grayscale.height)*0.06, useHarrisDetector=False, ) @@ -256,8 +256,8 @@ def image_entropy_points(im, settings): def image_entropy(im): # greyscale image entropy - band = np.asarray(im.convert("L")) - # band = np.asarray(im.convert("1"), dtype=np.uint8) + # band = np.asarray(im.convert("L")) + band = np.asarray(im.convert("1"), dtype=np.uint8) hist, _ = np.histogram(band, bins=range(0, 256)) hist = hist[hist > 0] return -np.log2(hist / hist.sum()).sum() diff --git a/modules/ui.py b/modules/ui.py index 95b9c703..095200a8 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -1270,7 +1270,7 @@ def create_ui(wrap_gradio_gpu_call): 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_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') -- cgit v1.2.3