From fbcce66601994f6ed370db36d9c238840fed6bd2 Mon Sep 17 00:00:00 2001 From: DepFA <35278260+dfaker@users.noreply.github.com> Date: Thu, 20 Oct 2022 00:46:54 +0100 Subject: add existing caption file handling --- modules/textual_inversion/preprocess.py | 32 ++++++++++++++++++++++++-------- 1 file changed, 24 insertions(+), 8 deletions(-) (limited to 'modules/textual_inversion/preprocess.py') diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index 886cf0c3..5c43fe13 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -48,7 +48,7 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pro shared.state.textinfo = "Preprocessing..." shared.state.job_count = len(files) - def save_pic_with_caption(image, index): + def save_pic_with_caption(image, index, existing_caption=None): caption = "" if process_caption: @@ -66,17 +66,26 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pro basename = f"{index:05}-{subindex[0]}-{filename_part}" image.save(os.path.join(dst, f"{basename}.png")) + if preprocess_txt_action == 'prepend' and existing_caption: + caption = existing_caption + ' ' + caption + elif preprocess_txt_action == 'append' and existing_caption: + caption = caption + ' ' + existing_caption + elif preprocess_txt_action == 'copy' and existing_caption: + caption = existing_caption + + caption = caption.strip() + if len(caption) > 0: with open(os.path.join(dst, f"{basename}.txt"), "w", encoding="utf8") as file: file.write(caption) subindex[0] += 1 - def save_pic(image, index): + def save_pic(image, index, existing_caption=None): save_pic_with_caption(image, index) if process_flip: - save_pic_with_caption(ImageOps.mirror(image), index) + save_pic_with_caption(ImageOps.mirror(image), index, existing_caption=existing_caption) for index, imagefile in enumerate(tqdm.tqdm(files)): subindex = [0] @@ -86,6 +95,13 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pro except Exception: continue + existing_caption = None + + try: + existing_caption = open(os.path.splitext(filename)[0] + '.txt', 'r').read() + except Exception as e: + print(e) + if shared.state.interrupted: break @@ -97,20 +113,20 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pro img = img.resize((width, height * img.height // img.width)) top = img.crop((0, 0, width, height)) - save_pic(top, index) + save_pic(top, index, existing_caption=existing_caption) bot = img.crop((0, img.height - height, width, img.height)) - save_pic(bot, index) + save_pic(bot, index, existing_caption=existing_caption) elif process_split and is_wide: img = img.resize((width * img.width // img.height, height)) left = img.crop((0, 0, width, height)) - save_pic(left, index) + save_pic(left, index, existing_caption=existing_caption) right = img.crop((img.width - width, 0, img.width, height)) - save_pic(right, index) + save_pic(right, index, existing_caption=existing_caption) else: img = images.resize_image(1, img, width, height) - save_pic(img, index) + save_pic(img, index, existing_caption=existing_caption) shared.state.nextjob() -- cgit v1.2.1 From 9b65c4ecf4f8eb6187ee721918adebe68e9bc631 Mon Sep 17 00:00:00 2001 From: DepFA <35278260+dfaker@users.noreply.github.com> Date: Thu, 20 Oct 2022 00:49:23 +0100 Subject: pass preprocess_txt_action param --- modules/textual_inversion/preprocess.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'modules/textual_inversion/preprocess.py') diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index 5c43fe13..3713bc89 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -11,7 +11,7 @@ if cmd_opts.deepdanbooru: import modules.deepbooru as deepbooru -def preprocess(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru=False): +def preprocess(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False): try: if process_caption: shared.interrogator.load() @@ -21,7 +21,7 @@ def preprocess(process_src, process_dst, process_width, process_height, process_ 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, process_flip, process_split, process_caption, process_caption_deepbooru) + preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru) finally: @@ -33,7 +33,7 @@ def preprocess(process_src, process_dst, process_width, process_height, process_ -def preprocess_work(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru=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): width = process_width height = process_height src = os.path.abspath(process_src) -- cgit v1.2.1 From 858462f719c22ca9f24b94a41699653c34b5f4fb Mon Sep 17 00:00:00 2001 From: DepFA <35278260+dfaker@users.noreply.github.com> Date: Thu, 20 Oct 2022 02:57:18 +0100 Subject: do caption copy for both flips --- modules/textual_inversion/preprocess.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'modules/textual_inversion/preprocess.py') diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index 3713bc89..6bba3852 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -82,7 +82,7 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre subindex[0] += 1 def save_pic(image, index, existing_caption=None): - save_pic_with_caption(image, index) + save_pic_with_caption(image, index, existing_caption=existing_caption) if process_flip: save_pic_with_caption(ImageOps.mirror(image), index, existing_caption=existing_caption) -- cgit v1.2.1 From 9681419e422515e42444e0174355b760645a846f Mon Sep 17 00:00:00 2001 From: Milly Date: Thu, 20 Oct 2022 16:53:46 +0900 Subject: train: fixed preprocess image ratio --- modules/textual_inversion/preprocess.py | 54 +++++++++++++++++++++------------ 1 file changed, 35 insertions(+), 19 deletions(-) (limited to 'modules/textual_inversion/preprocess.py') diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index 886cf0c3..2743bdeb 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -1,5 +1,6 @@ import os from PIL import Image, ImageOps +import math import platform import sys import tqdm @@ -38,6 +39,8 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pro height = process_height src = os.path.abspath(process_src) dst = os.path.abspath(process_dst) + split_threshold = 0.5 + overlap_ratio = 0.2 assert src != dst, 'same directory specified as source and destination' @@ -78,6 +81,29 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pro if process_flip: save_pic_with_caption(ImageOps.mirror(image), index) + def split_pic(image, inverse_xy): + if inverse_xy: + from_w, from_h = image.height, image.width + to_w, to_h = height, width + else: + from_w, from_h = image.width, image.height + to_w, to_h = width, height + h = from_h * to_w // from_w + if inverse_xy: + image = image.resize((h, to_w)) + else: + image = image.resize((to_w, h)) + + split_count = math.ceil((h - to_h * overlap_ratio) / (to_h * (1.0 - overlap_ratio))) + y_step = (h - to_h) / (split_count - 1) + for i in range(split_count): + y = int(y_step * i) + if inverse_xy: + splitted = image.crop((y, 0, y + to_h, to_w)) + else: + splitted = image.crop((0, y, to_w, y + to_h)) + yield splitted + for index, imagefile in enumerate(tqdm.tqdm(files)): subindex = [0] filename = os.path.join(src, imagefile) @@ -89,26 +115,16 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pro if shared.state.interrupted: break - ratio = img.height / img.width - is_tall = ratio > 1.35 - is_wide = ratio < 1 / 1.35 - - if process_split and is_tall: - img = img.resize((width, height * img.height // img.width)) - - top = img.crop((0, 0, width, height)) - save_pic(top, index) - - bot = img.crop((0, img.height - height, width, img.height)) - save_pic(bot, index) - elif process_split and is_wide: - img = img.resize((width * img.width // img.height, height)) - - left = img.crop((0, 0, width, height)) - save_pic(left, index) + if img.height > img.width: + ratio = (img.width * height) / (img.height * width) + inverse_xy = False + else: + ratio = (img.height * width) / (img.width * height) + inverse_xy = True - right = img.crop((img.width - width, 0, img.width, height)) - save_pic(right, index) + if process_split and ratio < 1.0 and ratio <= split_threshold: + for splitted in split_pic(img, inverse_xy): + save_pic(splitted, index) else: img = images.resize_image(1, img, width, height) save_pic(img, index) -- cgit v1.2.1 From 85dd62c4c7635b8e21a75f140d093036069e97a1 Mon Sep 17 00:00:00 2001 From: Milly Date: Thu, 20 Oct 2022 22:56:45 +0900 Subject: train: ui: added `Split image threshold` and `Split image overlap ratio` to preprocess --- modules/textual_inversion/preprocess.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'modules/textual_inversion/preprocess.py') diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index 2743bdeb..c8df8aa0 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -12,7 +12,7 @@ if cmd_opts.deepdanbooru: import modules.deepbooru as deepbooru -def preprocess(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru=False): +def preprocess(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2): try: if process_caption: shared.interrogator.load() @@ -22,7 +22,7 @@ def preprocess(process_src, process_dst, process_width, process_height, process_ 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, process_flip, process_split, process_caption, process_caption_deepbooru) + preprocess_work(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru, split_threshold, overlap_ratio) finally: @@ -34,13 +34,13 @@ def preprocess(process_src, process_dst, process_width, process_height, process_ -def preprocess_work(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru=False): +def preprocess_work(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2): width = process_width height = process_height src = os.path.abspath(process_src) dst = os.path.abspath(process_dst) - split_threshold = 0.5 - overlap_ratio = 0.2 + split_threshold = max(0.0, min(1.0, split_threshold)) + overlap_ratio = max(0.0, min(0.9, overlap_ratio)) assert src != dst, 'same directory specified as source and destination' -- cgit v1.2.1 From f49c08ea566385db339c6628f65c3a121033f67c Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Fri, 21 Oct 2022 18:46:02 +0300 Subject: prevent error spam when processing images without txt files for captions --- modules/textual_inversion/preprocess.py | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'modules/textual_inversion/preprocess.py') diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index 17e4ddc1..33eaddb6 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -122,11 +122,10 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre continue existing_caption = None - - try: - existing_caption = open(os.path.splitext(filename)[0] + '.txt', 'r').read() - except Exception as e: - print(e) + existing_caption_filename = os.path.splitext(filename)[0] + '.txt' + if os.path.exists(existing_caption_filename): + with open(existing_caption_filename, 'r', encoding="utf8") as file: + existing_caption = file.read() if shared.state.interrupted: break -- cgit v1.2.1