From 1f92336be768d235c18a82acb2195b7135101ae7 Mon Sep 17 00:00:00 2001 From: JC_Array Date: Sun, 9 Oct 2022 23:58:18 -0500 Subject: refactored the deepbooru module to improve speed on running multiple interogations in a row. Added the option to generate deepbooru tags for textual inversion preproccessing. --- modules/deepbooru.py | 84 ++++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 65 insertions(+), 19 deletions(-) (limited to 'modules/deepbooru.py') diff --git a/modules/deepbooru.py b/modules/deepbooru.py index 7e3c0618..cee4a3b4 100644 --- a/modules/deepbooru.py +++ b/modules/deepbooru.py @@ -1,21 +1,74 @@ import os.path from concurrent.futures import ProcessPoolExecutor -from multiprocessing import get_context +import multiprocessing -def _load_tf_and_return_tags(pil_image, threshold): +def get_deepbooru_tags(pil_image, threshold=0.5): + """ + This method is for running only one image at a time for simple use. Used to the img2img interrogate. + """ + from modules import shared # prevents circular reference + create_deepbooru_process(threshold) + shared.deepbooru_process_return["value"] = -1 + shared.deepbooru_process_queue.put(pil_image) + while shared.deepbooru_process_return["value"] == -1: + time.sleep(0.2) + release_process() + return ret + + +def deepbooru_process(queue, deepbooru_process_return, threshold): + model, tags = get_deepbooru_tags_model() + while True: # while process is running, keep monitoring queue for new image + pil_image = queue.get() + if pil_image == "QUIT": + break + else: + deepbooru_process_return["value"] = get_deepbooru_tags_from_model(model, tags, pil_image, threshold) + + +def create_deepbooru_process(threshold=0.5): + """ + Creates deepbooru process. A queue is created to send images into the process. This enables multiple images + to be processed in a row without reloading the model or creating a new process. To return the data, a shared + dictionary is created to hold the tags created. To wait for tags to be returned, a value of -1 is assigned + to the dictionary and the method adding the image to the queue should wait for this value to be updated with + the tags. + """ + from modules import shared # prevents circular reference + shared.deepbooru_process_manager = multiprocessing.Manager() + shared.deepbooru_process_queue = shared.deepbooru_process_manager.Queue() + shared.deepbooru_process_return = shared.deepbooru_process_manager.dict() + shared.deepbooru_process_return["value"] = -1 + shared.deepbooru_process = multiprocessing.Process(target=deepbooru_process, args=(shared.deepbooru_process_queue, shared.deepbooru_process_return, threshold)) + shared.deepbooru_process.start() + + +def release_process(): + """ + Stops the deepbooru process to return used memory + """ + from modules import shared # prevents circular reference + shared.deepbooru_process_queue.put("QUIT") + shared.deepbooru_process.join() + shared.deepbooru_process_queue = None + shared.deepbooru_process = None + shared.deepbooru_process_return = None + shared.deepbooru_process_manager = None + +def get_deepbooru_tags_model(): import deepdanbooru as dd import tensorflow as tf import numpy as np - this_folder = os.path.dirname(__file__) model_path = os.path.abspath(os.path.join(this_folder, '..', 'models', 'deepbooru')) if not os.path.exists(os.path.join(model_path, 'project.json')): # there is no point importing these every time import zipfile from basicsr.utils.download_util import load_file_from_url - load_file_from_url(r"https://github.com/KichangKim/DeepDanbooru/releases/download/v3-20211112-sgd-e28/deepdanbooru-v3-20211112-sgd-e28.zip", - model_path) + load_file_from_url( + r"https://github.com/KichangKim/DeepDanbooru/releases/download/v3-20211112-sgd-e28/deepdanbooru-v3-20211112-sgd-e28.zip", + model_path) with zipfile.ZipFile(os.path.join(model_path, "deepdanbooru-v3-20211112-sgd-e28.zip"), "r") as zip_ref: zip_ref.extractall(model_path) os.remove(os.path.join(model_path, "deepdanbooru-v3-20211112-sgd-e28.zip")) @@ -24,7 +77,13 @@ def _load_tf_and_return_tags(pil_image, threshold): model = dd.project.load_model_from_project( model_path, compile_model=True ) + return model, tags + +def get_deepbooru_tags_from_model(model, tags, pil_image, threshold=0.5): + import deepdanbooru as dd + import tensorflow as tf + import numpy as np width = model.input_shape[2] height = model.input_shape[1] image = np.array(pil_image) @@ -57,17 +116,4 @@ def _load_tf_and_return_tags(pil_image, threshold): print('\n'.join(sorted(result_tags_print, reverse=True))) - return ', '.join(result_tags_out).replace('_', ' ').replace(':', ' ') - - -def subprocess_init_no_cuda(): - import os - os.environ["CUDA_VISIBLE_DEVICES"] = "-1" - - -def get_deepbooru_tags(pil_image, threshold=0.5): - context = get_context('spawn') - with ProcessPoolExecutor(initializer=subprocess_init_no_cuda, mp_context=context) as executor: - f = executor.submit(_load_tf_and_return_tags, pil_image, threshold, ) - ret = f.result() # will rethrow any exceptions - return ret \ No newline at end of file + return ', '.join(result_tags_out).replace('_', ' ').replace(':', ' ') \ No newline at end of file -- cgit v1.2.3 From a1a05ad2d13d0b995dbf8ecead6315f17837ef81 Mon Sep 17 00:00:00 2001 From: JC_Array Date: Mon, 10 Oct 2022 16:47:58 -0500 Subject: import time missing, added to deepbooru fixxing error on get_deepbooru_tags --- modules/deepbooru.py | 1 + 1 file changed, 1 insertion(+) (limited to 'modules/deepbooru.py') diff --git a/modules/deepbooru.py b/modules/deepbooru.py index cee4a3b4..12555b2e 100644 --- a/modules/deepbooru.py +++ b/modules/deepbooru.py @@ -1,6 +1,7 @@ import os.path from concurrent.futures import ProcessPoolExecutor import multiprocessing +import time def get_deepbooru_tags(pil_image, threshold=0.5): -- cgit v1.2.3 From b980e7188c671fc55b26557f097076fb5c976ba0 Mon Sep 17 00:00:00 2001 From: JC_Array Date: Mon, 10 Oct 2022 16:52:54 -0500 Subject: corrected tag return in get_deepbooru_tags --- modules/deepbooru.py | 1 - 1 file changed, 1 deletion(-) (limited to 'modules/deepbooru.py') diff --git a/modules/deepbooru.py b/modules/deepbooru.py index 12555b2e..ebdba5e0 100644 --- a/modules/deepbooru.py +++ b/modules/deepbooru.py @@ -15,7 +15,6 @@ def get_deepbooru_tags(pil_image, threshold=0.5): while shared.deepbooru_process_return["value"] == -1: time.sleep(0.2) release_process() - return ret def deepbooru_process(queue, deepbooru_process_return, threshold): -- cgit v1.2.3 From 76ef3d75f61253516c024553335d9083d9660a8a Mon Sep 17 00:00:00 2001 From: JC_Array Date: Mon, 10 Oct 2022 18:01:49 -0500 Subject: added deepbooru settings (threshold and sort by alpha or likelyhood) --- modules/deepbooru.py | 36 +++++++++++++++++++++++++----------- modules/shared.py | 6 ++++++ 2 files changed, 31 insertions(+), 11 deletions(-) (limited to 'modules/deepbooru.py') diff --git a/modules/deepbooru.py b/modules/deepbooru.py index ebdba5e0..e31e92c0 100644 --- a/modules/deepbooru.py +++ b/modules/deepbooru.py @@ -3,31 +3,32 @@ from concurrent.futures import ProcessPoolExecutor import multiprocessing import time - -def get_deepbooru_tags(pil_image, threshold=0.5): +def get_deepbooru_tags(pil_image): """ This method is for running only one image at a time for simple use. Used to the img2img interrogate. """ from modules import shared # prevents circular reference - create_deepbooru_process(threshold) + create_deepbooru_process(shared.opts.deepbooru_threshold, shared.opts.deepbooru_sort_alpha) shared.deepbooru_process_return["value"] = -1 shared.deepbooru_process_queue.put(pil_image) while shared.deepbooru_process_return["value"] == -1: time.sleep(0.2) + tags = shared.deepbooru_process_return["value"] release_process() + return tags -def deepbooru_process(queue, deepbooru_process_return, threshold): +def deepbooru_process(queue, deepbooru_process_return, threshold, alpha_sort): model, tags = get_deepbooru_tags_model() while True: # while process is running, keep monitoring queue for new image pil_image = queue.get() if pil_image == "QUIT": break else: - deepbooru_process_return["value"] = get_deepbooru_tags_from_model(model, tags, pil_image, threshold) + deepbooru_process_return["value"] = get_deepbooru_tags_from_model(model, tags, pil_image, threshold, alpha_sort) -def create_deepbooru_process(threshold=0.5): +def create_deepbooru_process(threshold, alpha_sort): """ Creates deepbooru process. A queue is created to send images into the process. This enables multiple images to be processed in a row without reloading the model or creating a new process. To return the data, a shared @@ -40,7 +41,7 @@ def create_deepbooru_process(threshold=0.5): shared.deepbooru_process_queue = shared.deepbooru_process_manager.Queue() shared.deepbooru_process_return = shared.deepbooru_process_manager.dict() shared.deepbooru_process_return["value"] = -1 - shared.deepbooru_process = multiprocessing.Process(target=deepbooru_process, args=(shared.deepbooru_process_queue, shared.deepbooru_process_return, threshold)) + shared.deepbooru_process = multiprocessing.Process(target=deepbooru_process, args=(shared.deepbooru_process_queue, shared.deepbooru_process_return, threshold, alpha_sort)) shared.deepbooru_process.start() @@ -80,7 +81,7 @@ def get_deepbooru_tags_model(): return model, tags -def get_deepbooru_tags_from_model(model, tags, pil_image, threshold=0.5): +def get_deepbooru_tags_from_model(model, tags, pil_image, threshold, alpha_sort): import deepdanbooru as dd import tensorflow as tf import numpy as np @@ -105,15 +106,28 @@ def get_deepbooru_tags_from_model(model, tags, pil_image, threshold=0.5): for i, tag in enumerate(tags): result_dict[tag] = y[i] - result_tags_out = [] + + unsorted_tags_in_theshold = [] result_tags_print = [] for tag in tags: if result_dict[tag] >= threshold: if tag.startswith("rating:"): continue - result_tags_out.append(tag) + unsorted_tags_in_theshold.append((result_dict[tag], tag)) result_tags_print.append(f'{result_dict[tag]} {tag}') + # sort tags + result_tags_out = [] + sort_ndx = 0 + print(alpha_sort) + if alpha_sort: + sort_ndx = 1 + + # sort by reverse by likelihood and normal for alpha + unsorted_tags_in_theshold.sort(key=lambda y: y[sort_ndx], reverse=(not alpha_sort)) + for weight, tag in unsorted_tags_in_theshold: + result_tags_out.append(tag) + print('\n'.join(sorted(result_tags_print, reverse=True))) - return ', '.join(result_tags_out).replace('_', ' ').replace(':', ' ') \ No newline at end of file + return ', '.join(result_tags_out).replace('_', ' ').replace(':', ' ') diff --git a/modules/shared.py b/modules/shared.py index 1995a99a..2e307809 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -261,6 +261,12 @@ options_templates.update(options_section(('sampler-params', "Sampler parameters" 's_noise': OptionInfo(1.0, "sigma noise", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), })) +if cmd_opts.deepdanbooru: + options_templates.update(options_section(('deepbooru-params', "DeepBooru parameters"), { + "deepbooru_sort_alpha": OptionInfo(True, "Sort Alphabetical", gr.Checkbox), + 'deepbooru_threshold': OptionInfo(0.5, "Threshold", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), + })) + class Options: data = None -- cgit v1.2.3 From ff4ef13dd591ec52f196f344f47537695df95364 Mon Sep 17 00:00:00 2001 From: JC_Array Date: Tue, 11 Oct 2022 10:24:27 -0500 Subject: removed unneeded print --- modules/deepbooru.py | 1 - 1 file changed, 1 deletion(-) (limited to 'modules/deepbooru.py') diff --git a/modules/deepbooru.py b/modules/deepbooru.py index e31e92c0..89dcac3c 100644 --- a/modules/deepbooru.py +++ b/modules/deepbooru.py @@ -119,7 +119,6 @@ def get_deepbooru_tags_from_model(model, tags, pil_image, threshold, alpha_sort) # sort tags result_tags_out = [] sort_ndx = 0 - print(alpha_sort) if alpha_sort: sort_ndx = 1 -- cgit v1.2.3 From f53f703aebc801c4204182d52bb1e0bef9808e1f Mon Sep 17 00:00:00 2001 From: JC_Array Date: Tue, 11 Oct 2022 18:12:12 -0500 Subject: resolved conflicts, moved settings under interrogate section, settings only show if deepbooru flag is enabled --- modules/deepbooru.py | 2 +- modules/shared.py | 19 +++++++++---------- modules/textual_inversion/preprocess.py | 2 +- modules/ui.py | 2 +- 4 files changed, 12 insertions(+), 13 deletions(-) (limited to 'modules/deepbooru.py') diff --git a/modules/deepbooru.py b/modules/deepbooru.py index 89dcac3c..29529949 100644 --- a/modules/deepbooru.py +++ b/modules/deepbooru.py @@ -8,7 +8,7 @@ def get_deepbooru_tags(pil_image): This method is for running only one image at a time for simple use. Used to the img2img interrogate. """ from modules import shared # prevents circular reference - create_deepbooru_process(shared.opts.deepbooru_threshold, shared.opts.deepbooru_sort_alpha) + create_deepbooru_process(shared.opts.interrogate_deepbooru_score_threshold, shared.opts.deepbooru_sort_alpha) shared.deepbooru_process_return["value"] = -1 shared.deepbooru_process_queue.put(pil_image) while shared.deepbooru_process_return["value"] == -1: diff --git a/modules/shared.py b/modules/shared.py index 817203f8..5456c477 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -248,15 +248,20 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), { "random_artist_categories": OptionInfo([], "Allowed categories for random artists selection when using the Roll button", gr.CheckboxGroup, {"choices": artist_db.categories()}), })) -options_templates.update(options_section(('interrogate', "Interrogate Options"), { +interrogate_option_dictionary = { "interrogate_keep_models_in_memory": OptionInfo(False, "Interrogate: keep models in VRAM"), "interrogate_use_builtin_artists": OptionInfo(True, "Interrogate: use artists from artists.csv"), "interrogate_clip_num_beams": OptionInfo(1, "Interrogate: num_beams for BLIP", gr.Slider, {"minimum": 1, "maximum": 16, "step": 1}), "interrogate_clip_min_length": OptionInfo(24, "Interrogate: minimum description length (excluding artists, etc..)", gr.Slider, {"minimum": 1, "maximum": 128, "step": 1}), "interrogate_clip_max_length": OptionInfo(48, "Interrogate: maximum description length", gr.Slider, {"minimum": 1, "maximum": 256, "step": 1}), - "interrogate_clip_dict_limit": OptionInfo(1500, "Interrogate: maximum number of lines in text file (0 = No limit)"), - "interrogate_deepbooru_score_threshold": OptionInfo(0.5, "Interrogate: deepbooru score threshold", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.01}), -})) + "interrogate_clip_dict_limit": OptionInfo(1500, "Interrogate: maximum number of lines in text file (0 = No limit)") +} + +if cmd_opts.deepdanbooru: + interrogate_option_dictionary["interrogate_deepbooru_score_threshold"] = OptionInfo(0.5, "Interrogate: deepbooru score threshold", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.01}) + interrogate_option_dictionary["deepbooru_sort_alpha"] = OptionInfo(True, "Interrogate: deepbooru sort alphabetically", gr.Checkbox) + +options_templates.update(options_section(('interrogate', "Interrogate Options"), interrogate_option_dictionary)) options_templates.update(options_section(('ui', "User interface"), { "show_progressbar": OptionInfo(True, "Show progressbar"), @@ -282,12 +287,6 @@ options_templates.update(options_section(('sampler-params', "Sampler parameters" 'eta_noise_seed_delta': OptionInfo(0, "Eta noise seed delta", gr.Number, {"precision": 0}), })) -if cmd_opts.deepdanbooru: - options_templates.update(options_section(('deepbooru-params', "DeepBooru parameters"), { - "deepbooru_sort_alpha": OptionInfo(True, "Sort Alphabetical", gr.Checkbox), - 'deepbooru_threshold': OptionInfo(0.5, "Threshold", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), - })) - class Options: data = None diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index a96388d6..113cecf1 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -29,7 +29,7 @@ def preprocess(process_src, process_dst, process_width, process_height, process_ shared.interrogator.load() if process_caption_deepbooru: - deepbooru.create_deepbooru_process(opts.deepbooru_threshold, opts.deepbooru_sort_alpha) + deepbooru.create_deepbooru_process(opts.interrogate_deepbooru_score_threshold, opts.deepbooru_sort_alpha) def save_pic_with_caption(image, index): if process_caption: diff --git a/modules/ui.py b/modules/ui.py index 2891fc8c..fa45edca 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -317,7 +317,7 @@ def interrogate(image): def interrogate_deepbooru(image): - prompt = get_deepbooru_tags(image, opts.interrogate_deepbooru_score_threshold) + prompt = get_deepbooru_tags(image) return gr_show(True) if prompt is None else prompt -- cgit v1.2.3 From 698d303b04e293635bfb49c525409f3bcf671dce Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Wed, 12 Oct 2022 21:55:43 +0300 Subject: deepbooru: added option to use spaces or underscores deepbooru: added option to quote (\) in tags deepbooru/BLIP: write caption to file instead of image filename deepbooru/BLIP: now possible to use both for captions deepbooru: process is stopped even if an exception occurs --- modules/deepbooru.py | 65 ++++++++++++++++++----- modules/shared.py | 2 + modules/textual_inversion/preprocess.py | 92 ++++++++++++++------------------- modules/ui.py | 7 +-- 4 files changed, 95 insertions(+), 71 deletions(-) (limited to 'modules/deepbooru.py') diff --git a/modules/deepbooru.py b/modules/deepbooru.py index 29529949..419e6a9c 100644 --- a/modules/deepbooru.py +++ b/modules/deepbooru.py @@ -2,33 +2,44 @@ import os.path from concurrent.futures import ProcessPoolExecutor import multiprocessing import time +import re + +re_special = re.compile(r'([\\()])') def get_deepbooru_tags(pil_image): """ This method is for running only one image at a time for simple use. Used to the img2img interrogate. """ from modules import shared # prevents circular reference - create_deepbooru_process(shared.opts.interrogate_deepbooru_score_threshold, shared.opts.deepbooru_sort_alpha) - shared.deepbooru_process_return["value"] = -1 - shared.deepbooru_process_queue.put(pil_image) - while shared.deepbooru_process_return["value"] == -1: - time.sleep(0.2) - tags = shared.deepbooru_process_return["value"] - release_process() - return tags + try: + create_deepbooru_process(shared.opts.interrogate_deepbooru_score_threshold, create_deepbooru_opts()) + return get_tags_from_process(pil_image) + finally: + release_process() + + +def create_deepbooru_opts(): + from modules import shared -def deepbooru_process(queue, deepbooru_process_return, threshold, alpha_sort): + return { + "use_spaces": shared.opts.deepbooru_use_spaces, + "use_escape": shared.opts.deepbooru_escape, + "alpha_sort": shared.opts.deepbooru_sort_alpha, + } + + +def deepbooru_process(queue, deepbooru_process_return, threshold, deepbooru_opts): model, tags = get_deepbooru_tags_model() while True: # while process is running, keep monitoring queue for new image pil_image = queue.get() if pil_image == "QUIT": break else: - deepbooru_process_return["value"] = get_deepbooru_tags_from_model(model, tags, pil_image, threshold, alpha_sort) + deepbooru_process_return["value"] = get_deepbooru_tags_from_model(model, tags, pil_image, threshold, deepbooru_opts) -def create_deepbooru_process(threshold, alpha_sort): +def create_deepbooru_process(threshold, deepbooru_opts): """ Creates deepbooru process. A queue is created to send images into the process. This enables multiple images to be processed in a row without reloading the model or creating a new process. To return the data, a shared @@ -41,10 +52,23 @@ def create_deepbooru_process(threshold, alpha_sort): shared.deepbooru_process_queue = shared.deepbooru_process_manager.Queue() shared.deepbooru_process_return = shared.deepbooru_process_manager.dict() shared.deepbooru_process_return["value"] = -1 - shared.deepbooru_process = multiprocessing.Process(target=deepbooru_process, args=(shared.deepbooru_process_queue, shared.deepbooru_process_return, threshold, alpha_sort)) + shared.deepbooru_process = multiprocessing.Process(target=deepbooru_process, args=(shared.deepbooru_process_queue, shared.deepbooru_process_return, threshold, deepbooru_opts)) shared.deepbooru_process.start() +def get_tags_from_process(image): + from modules import shared + + shared.deepbooru_process_return["value"] = -1 + shared.deepbooru_process_queue.put(image) + while shared.deepbooru_process_return["value"] == -1: + time.sleep(0.2) + caption = shared.deepbooru_process_return["value"] + shared.deepbooru_process_return["value"] = -1 + + return caption + + def release_process(): """ Stops the deepbooru process to return used memory @@ -81,10 +105,15 @@ def get_deepbooru_tags_model(): return model, tags -def get_deepbooru_tags_from_model(model, tags, pil_image, threshold, alpha_sort): +def get_deepbooru_tags_from_model(model, tags, pil_image, threshold, deepbooru_opts): import deepdanbooru as dd import tensorflow as tf import numpy as np + + alpha_sort = deepbooru_opts['alpha_sort'] + use_spaces = deepbooru_opts['use_spaces'] + use_escape = deepbooru_opts['use_escape'] + width = model.input_shape[2] height = model.input_shape[1] image = np.array(pil_image) @@ -129,4 +158,12 @@ def get_deepbooru_tags_from_model(model, tags, pil_image, threshold, alpha_sort) print('\n'.join(sorted(result_tags_print, reverse=True))) - return ', '.join(result_tags_out).replace('_', ' ').replace(':', ' ') + tags_text = ', '.join(result_tags_out) + + if use_spaces: + tags_text = tags_text.replace('_', ' ') + + if use_escape: + tags_text = re.sub(re_special, r'\\\1', tags_text) + + return tags_text.replace(':', ' ') diff --git a/modules/shared.py b/modules/shared.py index e64e69fc..78b73aae 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -260,6 +260,8 @@ options_templates.update(options_section(('interrogate', "Interrogate Options"), "interrogate_clip_max_length": OptionInfo(48, "Interrogate: maximum description length", gr.Slider, {"minimum": 1, "maximum": 256, "step": 1}), "interrogate_deepbooru_score_threshold": OptionInfo(0.5, "Interrogate: deepbooru score threshold", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.01}), "deepbooru_sort_alpha": OptionInfo(True, "Interrogate: deepbooru sort alphabetically"), + "deepbooru_use_spaces": OptionInfo(False, "use spaces for tags in deepbooru"), + "deepbooru_escape": OptionInfo(True, "escape (\\) brackets in deepbooru (so they are used as literal brackets and not for emphasis)"), })) options_templates.update(options_section(('ui', "User interface"), { diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index 113cecf1..3047bede 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -10,7 +10,28 @@ from modules.shared import opts, cmd_opts 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): + try: + if process_caption: + shared.interrogator.load() + + if process_caption_deepbooru: + deepbooru.create_deepbooru_process(opts.interrogate_deepbooru_score_threshold, deepbooru.create_deepbooru_opts()) + + preprocess_work(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru) + + finally: + + if process_caption: + shared.interrogator.send_blip_to_ram() + + if process_caption_deepbooru: + deepbooru.release_process() + + + +def preprocess_work(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru=False): width = process_width height = process_height src = os.path.abspath(process_src) @@ -25,30 +46,28 @@ def preprocess(process_src, process_dst, process_width, process_height, process_ shared.state.textinfo = "Preprocessing..." shared.state.job_count = len(files) - if process_caption: - shared.interrogator.load() - - if process_caption_deepbooru: - deepbooru.create_deepbooru_process(opts.interrogate_deepbooru_score_threshold, opts.deepbooru_sort_alpha) - def save_pic_with_caption(image, index): + caption = "" + if process_caption: - caption = "-" + shared.interrogator.generate_caption(image) - caption = sanitize_caption(os.path.join(dst, f"{index:05}-{subindex[0]}"), caption, ".png") - elif process_caption_deepbooru: - shared.deepbooru_process_return["value"] = -1 - shared.deepbooru_process_queue.put(image) - while shared.deepbooru_process_return["value"] == -1: - time.sleep(0.2) - caption = "-" + shared.deepbooru_process_return["value"] - caption = sanitize_caption(os.path.join(dst, f"{index:05}-{subindex[0]}"), caption, ".png") - shared.deepbooru_process_return["value"] = -1 - else: - caption = filename - caption = os.path.splitext(caption)[0] - caption = os.path.basename(caption) + caption += shared.interrogator.generate_caption(image) + + if process_caption_deepbooru: + if len(caption) > 0: + caption += ", " + caption += deepbooru.get_tags_from_process(image) + + filename_part = filename + filename_part = os.path.splitext(filename_part)[0] + filename_part = os.path.basename(filename_part) + + basename = f"{index:05}-{subindex[0]}-{filename_part}" + image.save(os.path.join(dst, f"{basename}.png")) + + if len(caption) > 0: + with open(os.path.join(dst, f"{basename}.txt"), "w", encoding="utf8") as file: + file.write(caption) - image.save(os.path.join(dst, f"{index:05}-{subindex[0]}{caption}.png")) subindex[0] += 1 def save_pic(image, index): @@ -93,34 +112,3 @@ def preprocess(process_src, process_dst, process_width, process_height, process_ save_pic(img, index) shared.state.nextjob() - - if process_caption: - shared.interrogator.send_blip_to_ram() - - if process_caption_deepbooru: - deepbooru.release_process() - - -def sanitize_caption(base_path, original_caption, suffix): - operating_system = platform.system().lower() - if (operating_system == "windows"): - invalid_path_characters = "\\/:*?\"<>|" - max_path_length = 259 - else: - invalid_path_characters = "/" #linux/macos - max_path_length = 1023 - caption = original_caption - for invalid_character in invalid_path_characters: - caption = caption.replace(invalid_character, "") - fixed_path_length = len(base_path) + len(suffix) - if fixed_path_length + len(caption) <= max_path_length: - return caption - caption_tokens = caption.split() - new_caption = "" - for token in caption_tokens: - last_caption = new_caption - new_caption = new_caption + token + " " - if (len(new_caption) + fixed_path_length - 1 > max_path_length): - break - print(f"\nPath will be too long. Truncated caption: {original_caption}\nto: {last_caption}", file=sys.stderr) - return last_caption.strip() diff --git a/modules/ui.py b/modules/ui.py index c42535c8..e07ee0e1 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -1074,11 +1074,8 @@ 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_caption = gr.Checkbox(label='Use BLIP caption as filename') - if cmd_opts.deepdanbooru: - process_caption_deepbooru = gr.Checkbox(label='Use deepbooru caption as filename') - else: - process_caption_deepbooru = gr.Checkbox(label='Use deepbooru caption as filename', visible=False) + 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) with gr.Row(): with gr.Column(scale=3): -- cgit v1.2.3