From cd8673bd9b2e59bddefee8d307340d643695fe11 Mon Sep 17 00:00:00 2001
From: DepFA <35278260+dfaker@users.noreply.github.com>
Date: Sun, 9 Oct 2022 05:40:57 +0100
Subject: add embed embedding to ui

---
 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 b51af121..a5983204 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -1001,7 +1001,8 @@ def create_ui(wrap_gradio_gpu_call):
                     steps = gr.Number(label='Max steps', value=100000, precision=0)
                     create_image_every = gr.Number(label='Save an image to log directory every N steps, 0 to disable', value=500, precision=0)
                     save_embedding_every = gr.Number(label='Save a copy of embedding to log directory every N steps, 0 to disable', value=500, precision=0)
-
+                    save_image_with_stored_embedding = gr.Checkbox(label='Save images with embedding in PNG chunks', value=True)
+                    
                     with gr.Row():
                         with gr.Column(scale=2):
                             gr.HTML(value="")
@@ -1063,6 +1064,7 @@ def create_ui(wrap_gradio_gpu_call):
                 create_image_every,
                 save_embedding_every,
                 template_file,
+                save_image_with_stored_embedding,
             ],
             outputs=[
                 ti_output,
-- 
cgit v1.2.3


From 6435691bb11c5a35703720bfd2a875f24c066f86 Mon Sep 17 00:00:00 2001
From: Justin Maier <Zipp425@gmail.com>
Date: Sun, 9 Oct 2022 19:26:52 -0600
Subject: Add "Scale to" option to Extras

---
 javascript/ui.js  |  3 ++-
 modules/extras.py | 28 +++++++++++++++++++++++-----
 modules/ui.py     | 38 +++++++++++++++++++++++++-------------
 3 files changed, 50 insertions(+), 19 deletions(-)

(limited to 'modules/ui.py')

diff --git a/javascript/ui.js b/javascript/ui.js
index b1053201..4100944e 100644
--- a/javascript/ui.js
+++ b/javascript/ui.js
@@ -101,7 +101,8 @@ function create_tab_index_args(tabId, args){
 }
 
 function get_extras_tab_index(){
-    return create_tab_index_args('mode_extras', arguments)
+    const [,,...args] = [...arguments]
+    return [get_tab_index('mode_extras'), get_tab_index('extras_resize_mode'), ...args]
 }
 
 function create_submit_args(args){
diff --git a/modules/extras.py b/modules/extras.py
index 41e8612c..83ca7049 100644
--- a/modules/extras.py
+++ b/modules/extras.py
@@ -1,3 +1,4 @@
+import math
 import os
 
 import numpy as np
@@ -19,7 +20,7 @@ import gradio as gr
 cached_images = {}
 
 
-def run_extras(extras_mode, image, image_folder, gfpgan_visibility, codeformer_visibility, codeformer_weight, upscaling_resize, extras_upscaler_1, extras_upscaler_2, extras_upscaler_2_visibility):
+def run_extras(extras_mode, resize_mode, image, image_folder, gfpgan_visibility, codeformer_visibility, codeformer_weight, upscaling_resize, upscaling_resize_w, upscaling_resize_h, upscaling_crop, extras_upscaler_1, extras_upscaler_2, extras_upscaler_2_visibility):
     devices.torch_gc()
 
     imageArr = []
@@ -67,8 +68,23 @@ def run_extras(extras_mode, image, image_folder, gfpgan_visibility, codeformer_v
             info += f"CodeFormer w: {round(codeformer_weight, 2)}, CodeFormer visibility:{round(codeformer_visibility, 2)}\n"
             image = res
 
+        if resize_mode == 1:
+            upscaling_resize = max(upscaling_resize_w/image.width, upscaling_resize_h/image.height)
+            crop_info = " (crop)" if upscaling_crop else ""
+            info += f"Resize to: {upscaling_resize_w:g}x{upscaling_resize_h:g}{crop_info}\n"
+
+            def crop_upscaled_center(image, resize_w, resize_h):
+                left = int(math.ceil((image.width - resize_w) / 2))
+                right = image.width - int(math.floor((image.width - resize_w) / 2))
+                top = int(math.ceil((image.height - resize_h) / 2))
+                bottom = image.height - int(math.floor((image.height - resize_h) / 2))
+
+                image = image.crop((left, top, right, bottom))
+                return image
+
+
         if upscaling_resize != 1.0:
-            def upscale(image, scaler_index, resize):
+            def upscale(image, scaler_index, resize, mode, resize_w, resize_h, crop):
                 small = image.crop((image.width // 2, image.height // 2, image.width // 2 + 10, image.height // 2 + 10))
                 pixels = tuple(np.array(small).flatten().tolist())
                 key = (resize, scaler_index, image.width, image.height, gfpgan_visibility, codeformer_visibility, codeformer_weight) + pixels
@@ -77,15 +93,17 @@ def run_extras(extras_mode, image, image_folder, gfpgan_visibility, codeformer_v
                 if c is None:
                     upscaler = shared.sd_upscalers[scaler_index]
                     c = upscaler.scaler.upscale(image, resize, upscaler.data_path)
+                    if mode == 1 and crop:
+                        c = crop_upscaled_center(c, resize_w, resize_h)
                     cached_images[key] = c
 
                 return c
 
             info += f"Upscale: {round(upscaling_resize, 3)}, model:{shared.sd_upscalers[extras_upscaler_1].name}\n"
-            res = upscale(image, extras_upscaler_1, upscaling_resize)
+            res = upscale(image, extras_upscaler_1, upscaling_resize, resize_mode, upscaling_resize_w, upscaling_resize_h, upscaling_crop)
 
             if extras_upscaler_2 != 0 and extras_upscaler_2_visibility > 0:
-                res2 = upscale(image, extras_upscaler_2, upscaling_resize)
+                res2 = upscale(image, extras_upscaler_2, upscaling_resize, resize_mode, upscaling_resize_w, upscaling_resize_h, upscaling_crop)
                 info += f"Upscale: {round(upscaling_resize, 3)}, visibility: {round(extras_upscaler_2_visibility, 3)}, model:{shared.sd_upscalers[extras_upscaler_2].name}\n"
                 res = Image.blend(res, res2, extras_upscaler_2_visibility)
 
@@ -190,7 +208,7 @@ def run_modelmerger(primary_model_name, secondary_model_name, interp_method, int
             theta_0[key] = theta_func(theta_0[key], theta_1[key], (float(1.0) - interp_amount))  # Need to reverse the interp_amount to match the desired mix ration in the merged checkpoint
             if save_as_half:
                 theta_0[key] = theta_0[key].half()
-    
+
     for key in theta_1.keys():
         if 'model' in key and key not in theta_0:
             theta_0[key] = theta_1[key]
diff --git a/modules/ui.py b/modules/ui.py
index 2231a8ed..4bb2892b 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -101,7 +101,7 @@ def send_gradio_gallery_to_image(x):
 
 
 def save_files(js_data, images, do_make_zip, index):
-    import csv    
+    import csv
     filenames = []
     fullfns = []
 
@@ -551,7 +551,7 @@ def create_ui(wrap_gradio_gpu_call):
 
                     with gr.Row():
                         do_make_zip = gr.Checkbox(label="Make Zip when Save?", value=False)
-                    
+
                     with gr.Row():
                         download_files = gr.File(None, file_count="multiple", interactive=False, show_label=False, visible=False)
 
@@ -739,7 +739,7 @@ def create_ui(wrap_gradio_gpu_call):
 
                     with gr.Row():
                         do_make_zip = gr.Checkbox(label="Make Zip when Save?", value=False)
-                    
+
                     with gr.Row():
                         download_files = gr.File(None, file_count="multiple", interactive=False, show_label=False, visible=False)
 
@@ -903,7 +903,15 @@ def create_ui(wrap_gradio_gpu_call):
                     with gr.TabItem('Batch Process'):
                         image_batch = gr.File(label="Batch Process", file_count="multiple", interactive=True, type="file")
 
-                upscaling_resize = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label="Resize", value=2)
+                with gr.Tabs(elem_id="extras_resize_mode"):
+                    with gr.TabItem('Scale by'):
+                        upscaling_resize = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label="Resize", value=2)
+                    with gr.TabItem('Scale to'):
+                        with gr.Group():
+                            with gr.Row():
+                                upscaling_resize_w = gr.Number(label="Width", value=512)
+                                upscaling_resize_h = gr.Number(label="Height", value=512)
+                            upscaling_crop = gr.Checkbox(label='Crop to fit', value=True)
 
                 with gr.Group():
                     extras_upscaler_1 = gr.Radio(label='Upscaler 1', choices=[x.name for x in shared.sd_upscalers], value=shared.sd_upscalers[0].name, type="index")
@@ -934,6 +942,7 @@ def create_ui(wrap_gradio_gpu_call):
             fn=wrap_gradio_gpu_call(modules.extras.run_extras),
             _js="get_extras_tab_index",
             inputs=[
+                dummy_component,
                 dummy_component,
                 extras_image,
                 image_batch,
@@ -941,6 +950,9 @@ def create_ui(wrap_gradio_gpu_call):
                 codeformer_visibility,
                 codeformer_weight,
                 upscaling_resize,
+                upscaling_resize_w,
+                upscaling_resize_h,
+                upscaling_crop,
                 extras_upscaler_1,
                 extras_upscaler_2,
                 extras_upscaler_2_visibility,
@@ -951,14 +963,14 @@ def create_ui(wrap_gradio_gpu_call):
                 html_info,
             ]
         )
-     
+
         extras_send_to_img2img.click(
             fn=lambda x: image_from_url_text(x),
             _js="extract_image_from_gallery_img2img",
             inputs=[result_images],
             outputs=[init_img],
         )
-        
+
         extras_send_to_inpaint.click(
             fn=lambda x: image_from_url_text(x),
             _js="extract_image_from_gallery_img2img",
@@ -1286,7 +1298,7 @@ Requested path was: {f}
             outputs=[],
             _js='function(){restart_reload()}'
         )
-        
+
         if column is not None:
             column.__exit__()
 
@@ -1318,12 +1330,12 @@ Requested path was: {f}
                 component_dict[k] = component
 
         settings_interface.gradio_ref = demo
-        
+
         with gr.Tabs() as tabs:
             for interface, label, ifid in interfaces:
                 with gr.TabItem(label, id=ifid):
                     interface.render()
-        
+
         if os.path.exists(os.path.join(script_path, "notification.mp3")):
             audio_notification = gr.Audio(interactive=False, value=os.path.join(script_path, "notification.mp3"), elem_id="audio_notification", visible=False)
 
@@ -1456,10 +1468,10 @@ Requested path was: {f}
 
             if getattr(obj,'custom_script_source',None) is not None:
               key = 'customscript/' + obj.custom_script_source + '/' + key
-            
+
             if getattr(obj, 'do_not_save_to_config', False):
                 return
-            
+
             saved_value = ui_settings.get(key, None)
             if saved_value is None:
                 ui_settings[key] = getattr(obj, field)
@@ -1483,10 +1495,10 @@ Requested path was: {f}
 
         if type(x) == gr.Textbox:
             apply_field(x, 'value')
-        
+
         if type(x) == gr.Number:
             apply_field(x, 'value')
-        
+
     visit(txt2img_interface, loadsave, "txt2img")
     visit(img2img_interface, loadsave, "img2img")
     visit(extras_interface, loadsave, "extras")
-- 
cgit v1.2.3


From 1f92336be768d235c18a82acb2195b7135101ae7 Mon Sep 17 00:00:00 2001
From: JC_Array <justin318@att.net>
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 +++++++++++++++++++++++++--------
 modules/textual_inversion/preprocess.py | 22 ++++++++-
 modules/ui.py                           | 52 ++++++++++++++------
 3 files changed, 122 insertions(+), 36 deletions(-)

(limited to 'modules/ui.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
diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py
index f1c002a2..9f63c9a4 100644
--- a/modules/textual_inversion/preprocess.py
+++ b/modules/textual_inversion/preprocess.py
@@ -3,11 +3,14 @@ from PIL import Image, ImageOps
 import platform
 import sys
 import tqdm
+import time
 
 from modules import shared, images
+from modules.shared import opts, cmd_opts
+if cmd_opts.deepdanbooru:
+    import modules.deepbooru as deepbooru
 
-
-def preprocess(process_src, process_dst, process_flip, process_split, process_caption):
+def preprocess(process_src, process_dst, process_flip, process_split, process_caption, process_caption_deepbooru=False):
     size = 512
     src = os.path.abspath(process_src)
     dst = os.path.abspath(process_dst)
@@ -24,10 +27,21 @@ def preprocess(process_src, process_dst, process_flip, process_split, process_ca
     if process_caption:
         shared.interrogator.load()
 
+    if process_caption_deepbooru:
+        deepbooru.create_deepbooru_process()
+
     def save_pic_with_caption(image, index):
         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]
@@ -79,6 +93,10 @@ def preprocess(process_src, process_dst, process_flip, process_split, process_ca
     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"):
diff --git a/modules/ui.py b/modules/ui.py
index 2231a8ed..179e3a83 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -1034,6 +1034,9 @@ def create_ui(wrap_gradio_gpu_call):
                         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')
+
 
                     with gr.Row():
                         with gr.Column(scale=3):
@@ -1086,21 +1089,40 @@ def create_ui(wrap_gradio_gpu_call):
             ]
         )
 
-        run_preprocess.click(
-            fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.preprocess, extra_outputs=[gr.update()]),
-            _js="start_training_textual_inversion",
-            inputs=[
-                process_src,
-                process_dst,
-                process_flip,
-                process_split,
-                process_caption,
-            ],
-            outputs=[
-                ti_output,
-                ti_outcome,
-            ],
-        )
+        if cmd_opts.deepdanbooru:
+            # if process_caption_deepbooru is None, it will cause an error, as a result only include it if it is enabled
+            run_preprocess.click(
+                fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.preprocess, extra_outputs=[gr.update()]),
+                _js="start_training_textual_inversion",
+                inputs=[
+                    process_src,
+                    process_dst,
+                    process_flip,
+                    process_split,
+                    process_caption,
+                    process_caption_deepbooru,
+                ],
+                outputs=[
+                    ti_output,
+                    ti_outcome,
+                ],
+            )
+        else:
+            run_preprocess.click(
+                fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.preprocess, extra_outputs=[gr.update()]),
+                _js="start_training_textual_inversion",
+                inputs=[
+                    process_src,
+                    process_dst,
+                    process_flip,
+                    process_split,
+                    process_caption,
+                ],
+                outputs=[
+                    ti_output,
+                    ti_outcome,
+                ],
+            )
 
         train_embedding.click(
             fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.train_embedding, extra_outputs=[gr.update()]),
-- 
cgit v1.2.3


From 8ec069e64df48f8f202f8b93a08e91b69448eb39 Mon Sep 17 00:00:00 2001
From: JC_Array <justin318@att.net>
Date: Mon, 10 Oct 2022 03:23:24 -0500
Subject: removed duplicate run_preprocess.click by creating
 run_preprocess_inputs list and appending deepbooru variable to input list if
 in scope

---
 modules/ui.py | 49 +++++++++++++++++--------------------------------
 1 file changed, 17 insertions(+), 32 deletions(-)

(limited to 'modules/ui.py')

diff --git a/modules/ui.py b/modules/ui.py
index 179e3a83..22ca74c2 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -1089,40 +1089,25 @@ def create_ui(wrap_gradio_gpu_call):
             ]
         )
 
+        run_preprocess_inputs = [
+            process_src,
+            process_dst,
+            process_flip,
+            process_split,
+            process_caption,
+        ]
         if cmd_opts.deepdanbooru:
             # if process_caption_deepbooru is None, it will cause an error, as a result only include it if it is enabled
-            run_preprocess.click(
-                fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.preprocess, extra_outputs=[gr.update()]),
-                _js="start_training_textual_inversion",
-                inputs=[
-                    process_src,
-                    process_dst,
-                    process_flip,
-                    process_split,
-                    process_caption,
-                    process_caption_deepbooru,
-                ],
-                outputs=[
-                    ti_output,
-                    ti_outcome,
-                ],
-            )
-        else:
-            run_preprocess.click(
-                fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.preprocess, extra_outputs=[gr.update()]),
-                _js="start_training_textual_inversion",
-                inputs=[
-                    process_src,
-                    process_dst,
-                    process_flip,
-                    process_split,
-                    process_caption,
-                ],
-                outputs=[
-                    ti_output,
-                    ti_outcome,
-                ],
-            )
+            run_preprocess_inputs.append(process_caption_deepbooru)
+        run_preprocess.click(
+            fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.preprocess, extra_outputs=[gr.update()]),
+            _js="start_training_textual_inversion",
+            inputs=run_preprocess_inputs,
+            outputs=[
+                ti_output,
+                ti_outcome,
+            ],
+        )
 
         train_embedding.click(
             fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.train_embedding, extra_outputs=[gr.update()]),
-- 
cgit v1.2.3


From 2f94331df2cb1181439adecc28cfd758049f6501 Mon Sep 17 00:00:00 2001
From: JC_Array <justin318@att.net>
Date: Mon, 10 Oct 2022 03:34:00 -0500
Subject: removed change in last commit, simplified to adding the visible
 argument to process_caption_deepbooru and it set to False if deepdanbooru
 argument is not set

---
 modules/ui.py | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

(limited to 'modules/ui.py')

diff --git a/modules/ui.py b/modules/ui.py
index 22ca74c2..f8adafb3 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -1036,7 +1036,8 @@ def create_ui(wrap_gradio_gpu_call):
                         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)
 
                     with gr.Row():
                         with gr.Column(scale=3):
@@ -1089,20 +1090,17 @@ def create_ui(wrap_gradio_gpu_call):
             ]
         )
 
-        run_preprocess_inputs = [
-            process_src,
-            process_dst,
-            process_flip,
-            process_split,
-            process_caption,
-        ]
-        if cmd_opts.deepdanbooru:
-            # if process_caption_deepbooru is None, it will cause an error, as a result only include it if it is enabled
-            run_preprocess_inputs.append(process_caption_deepbooru)
         run_preprocess.click(
             fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.preprocess, extra_outputs=[gr.update()]),
             _js="start_training_textual_inversion",
-            inputs=run_preprocess_inputs,
+            inputs=[
+                process_src,
+                process_dst,
+                process_flip,
+                process_split,
+                process_caption,
+                process_caption_deepbooru
+            ],
             outputs=[
                 ti_output,
                 ti_outcome,
-- 
cgit v1.2.3


From 1d64976dbc5a0f3124567b91fadd5014a9d93c5f Mon Sep 17 00:00:00 2001
From: Justin Maier <Zipp425@gmail.com>
Date: Mon, 10 Oct 2022 12:04:21 -0600
Subject: Simplify crop logic

---
 modules/extras.py | 14 +++-----------
 modules/ui.py     |  4 ++--
 2 files changed, 5 insertions(+), 13 deletions(-)

(limited to 'modules/ui.py')

diff --git a/modules/extras.py b/modules/extras.py
index 83ca7049..b24d7de3 100644
--- a/modules/extras.py
+++ b/modules/extras.py
@@ -73,16 +73,6 @@ def run_extras(extras_mode, resize_mode, image, image_folder, gfpgan_visibility,
             crop_info = " (crop)" if upscaling_crop else ""
             info += f"Resize to: {upscaling_resize_w:g}x{upscaling_resize_h:g}{crop_info}\n"
 
-            def crop_upscaled_center(image, resize_w, resize_h):
-                left = int(math.ceil((image.width - resize_w) / 2))
-                right = image.width - int(math.floor((image.width - resize_w) / 2))
-                top = int(math.ceil((image.height - resize_h) / 2))
-                bottom = image.height - int(math.floor((image.height - resize_h) / 2))
-
-                image = image.crop((left, top, right, bottom))
-                return image
-
-
         if upscaling_resize != 1.0:
             def upscale(image, scaler_index, resize, mode, resize_w, resize_h, crop):
                 small = image.crop((image.width // 2, image.height // 2, image.width // 2 + 10, image.height // 2 + 10))
@@ -94,7 +84,9 @@ def run_extras(extras_mode, resize_mode, image, image_folder, gfpgan_visibility,
                     upscaler = shared.sd_upscalers[scaler_index]
                     c = upscaler.scaler.upscale(image, resize, upscaler.data_path)
                     if mode == 1 and crop:
-                        c = crop_upscaled_center(c, resize_w, resize_h)
+                        cropped = Image.new("RGB", (resize_w, resize_h))
+                        cropped.paste(c, box=(resize_w // 2 - c.width // 2, resize_h // 2 - c.height // 2))
+                        c = cropped
                     cached_images[key] = c
 
                 return c
diff --git a/modules/ui.py b/modules/ui.py
index 4bb2892b..1aabe18d 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -909,8 +909,8 @@ def create_ui(wrap_gradio_gpu_call):
                     with gr.TabItem('Scale to'):
                         with gr.Group():
                             with gr.Row():
-                                upscaling_resize_w = gr.Number(label="Width", value=512)
-                                upscaling_resize_h = gr.Number(label="Height", value=512)
+                                upscaling_resize_w = gr.Number(label="Width", value=512, precision=0)
+                                upscaling_resize_h = gr.Number(label="Height", value=512, precision=0)
                             upscaling_crop = gr.Checkbox(label='Crop to fit', value=True)
 
                 with gr.Group():
-- 
cgit v1.2.3


From f53f703aebc801c4204182d52bb1e0bef9808e1f Mon Sep 17 00:00:00 2001
From: JC_Array <justin318@att.net>
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/ui.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 fec2221eeaafb50afd26ba3e109bf6f928011e69 Mon Sep 17 00:00:00 2001
From: Greg Fuller <gfuller23@gmail.com>
Date: Tue, 11 Oct 2022 19:29:38 -0700
Subject: Truncate error text to fix service lockup / stall

What:
* Update wrap_gradio_call to add a limit to the maximum amount of text output

Why:
* wrap_gradio_call currently prints out a list of the arguments provided to the failing function.
   * if that function is save_image, this causes the entire image to be printed to stderr
    * If the image is large, this can cause the service to lock up while attempting to print all the text
 * It is easy to generate large images using the x/y plot script
 * it is easy to encounter image save exceptions, including if the output directory does not exist / cannot be written to, or if the file is too big
  * The huge amount of log spam is confusing and not particularly helpful
---
 modules/ui.py | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

(limited to 'modules/ui.py')

diff --git a/modules/ui.py b/modules/ui.py
index 1204eef7..33a49d3b 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -181,8 +181,15 @@ def wrap_gradio_call(func, extra_outputs=None):
         try:
             res = list(func(*args, **kwargs))
         except Exception as e:
+            # When printing out our debug argument list, do not print out more than a MB of text
+            max_debug_str_len = 131072 # (1024*1024)/8
+
             print("Error completing request", file=sys.stderr)
-            print("Arguments:", args, kwargs, file=sys.stderr)
+            argStr = f"Arguments: {str(args)} {str(kwargs)}"
+            print(argStr[:max_debug_str_len], file=sys.stderr)
+            if len(argStr) > max_debug_str_len:
+                print(f"(Argument list truncated at {max_debug_str_len}/{len(argStr)} characters)", file=sys.stderr)
+
             print(traceback.format_exc(), file=sys.stderr)
 
             shared.state.job = ""
-- 
cgit v1.2.3


From 57e03cdd244eee4e33ccab7554b3594563a3d0cd Mon Sep 17 00:00:00 2001
From: brkirch <brkirch@users.noreply.github.com>
Date: Wed, 12 Oct 2022 00:54:24 -0400
Subject: Ensure the directory exists before saving to it

The directory for the images saved with the Save button may still not exist, so it needs to be created prior to opening the log.csv file.
---
 modules/ui.py | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'modules/ui.py')

diff --git a/modules/ui.py b/modules/ui.py
index 00bf09ae..cd67b84b 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -131,6 +131,8 @@ def save_files(js_data, images, do_make_zip, index):
         images = [images[index]]
         start_index = index
 
+    os.makedirs(opts.outdir_save, exist_ok=True)
+
     with open(os.path.join(opts.outdir_save, "log.csv"), "a", encoding="utf8", newline='') as file:
         at_start = file.tell() == 0
         writer = csv.writer(file)
-- 
cgit v1.2.3


From ee015a1af66a94a75c914659fa0d321e702a0a87 Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Wed, 12 Oct 2022 11:05:57 +0300
Subject: change textual inversion tab to train remake train interface to use
 tabs

---
 modules/hypernetworks/hypernetwork.py |  2 +-
 modules/ui.py                         | 22 +++++++++-------------
 2 files changed, 10 insertions(+), 14 deletions(-)

(limited to 'modules/ui.py')

diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py
index 8f2192e2..8314450a 100644
--- a/modules/hypernetworks/hypernetwork.py
+++ b/modules/hypernetworks/hypernetwork.py
@@ -175,7 +175,7 @@ def attention_CrossAttention_forward(self, x, context=None, mask=None):
 
 
 def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory, steps, create_image_every, save_hypernetwork_every, template_file, preview_image_prompt):
-    assert hypernetwork_name, 'embedding not selected'
+    assert hypernetwork_name, 'hypernetwork not selected'
 
     path = shared.hypernetworks.get(hypernetwork_name, None)
     shared.loaded_hypernetwork = Hypernetwork()
diff --git a/modules/ui.py b/modules/ui.py
index 4bfdd275..86a2da6c 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -1035,14 +1035,14 @@ def create_ui(wrap_gradio_gpu_call):
 
     sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings()
 
-    with gr.Blocks() as textual_inversion_interface:
+    with gr.Blocks() as train_interface:
         with gr.Row().style(equal_height=False):
-            with gr.Column():
-                with gr.Group():
-                    gr.HTML(value="<p style='margin-bottom: 0.7em'>See <b><a href=\"https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Textual-Inversion\">wiki</a></b> for detailed explanation.</p>")
+            gr.HTML(value="<p style='margin-bottom: 0.7em'>See <b><a href=\"https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Textual-Inversion\">wiki</a></b> for detailed explanation.</p>")
 
-                    gr.HTML(value="<p style='margin-bottom: 0.7em'>Create a new embedding</p>")
+        with gr.Row().style(equal_height=False):
+            with gr.Tabs(elem_id="train_tabs"):
 
+                with gr.Tab(label="Create embedding"):
                     new_embedding_name = gr.Textbox(label="Name")
                     initialization_text = gr.Textbox(label="Initialization text", value="*")
                     nvpt = gr.Slider(label="Number of vectors per token", minimum=1, maximum=75, step=1, value=1)
@@ -1054,9 +1054,7 @@ def create_ui(wrap_gradio_gpu_call):
                         with gr.Column():
                             create_embedding = gr.Button(value="Create embedding", variant='primary')
 
-                with gr.Group():
-                    gr.HTML(value="<p style='margin-bottom: 0.7em'>Create a new hypernetwork</p>")
-
+                with gr.Tab(label="Create hypernetwork"):
                     new_hypernetwork_name = gr.Textbox(label="Name")
                     new_hypernetwork_sizes = gr.CheckboxGroup(label="Modules", value=["768", "320", "640", "1280"], choices=["768", "320", "640", "1280"])
 
@@ -1067,9 +1065,7 @@ def create_ui(wrap_gradio_gpu_call):
                         with gr.Column():
                             create_hypernetwork = gr.Button(value="Create hypernetwork", variant='primary')
 
-                with gr.Group():
-                    gr.HTML(value="<p style='margin-bottom: 0.7em'>Preprocess images</p>")
-
+                with gr.Tab(label="Preprocess images"):
                     process_src = gr.Textbox(label='Source directory')
                     process_dst = gr.Textbox(label='Destination directory')
                     process_width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512)
@@ -1091,7 +1087,7 @@ def create_ui(wrap_gradio_gpu_call):
                         with gr.Column():
                             run_preprocess = gr.Button(value="Preprocess", variant='primary')
 
-                with gr.Group():
+                with gr.Tab(label="Train"):
                     gr.HTML(value="<p style='margin-bottom: 0.7em'>Train an embedding; must specify a directory with a set of 1:1 ratio images</p>")
                     train_embedding_name = gr.Dropdown(label='Embedding', choices=sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys()))
                     train_hypernetwork_name = gr.Dropdown(label='Hypernetwork', choices=[x for x in shared.hypernetworks.keys()])
@@ -1388,7 +1384,7 @@ Requested path was: {f}
         (extras_interface, "Extras", "extras"),
         (pnginfo_interface, "PNG Info", "pnginfo"),
         (modelmerger_interface, "Checkpoint Merger", "modelmerger"),
-        (textual_inversion_interface, "Textual inversion", "ti"),
+        (train_interface, "Train", "ti"),
         (settings_interface, "Settings", "settings"),
     ]
 
-- 
cgit v1.2.3


From c3c8eef9fd5a0c8b26319e32ca4a19b56204e6df Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Wed, 12 Oct 2022 20:49:47 +0300
Subject: train: change filename processing to be more simple and configurable
 train: make it possible to make text files with prompts train: rework
 scheduler so that there's less repeating code in textual inversion and
 hypernets train: move epochs setting to options

---
 javascript/hints.js                            |  3 ++
 modules/hypernetworks/hypernetwork.py          | 40 +++++++++-------------
 modules/shared.py                              |  3 ++
 modules/textual_inversion/dataset.py           | 47 +++++++++++++++++++-------
 modules/textual_inversion/learn_schedule.py    | 37 +++++++++++++++++++-
 modules/textual_inversion/textual_inversion.py | 35 +++++++------------
 modules/ui.py                                  |  2 --
 7 files changed, 105 insertions(+), 62 deletions(-)

(limited to 'modules/ui.py')

diff --git a/javascript/hints.js b/javascript/hints.js
index b81c181b..d51ee14c 100644
--- a/javascript/hints.js
+++ b/javascript/hints.js
@@ -81,6 +81,9 @@ titles = {
 
     "Eta noise seed delta": "If this values is non-zero, it will be added to seed and used to initialize RNG for noises when using samplers with Eta. You can use this to produce even more variation of images, or you can use this to match images of other software if you know what you are doing.",
     "Do not add watermark to images": "If this option is enabled, watermark will not be added to created images. Warning: if you do not add watermark, you may be behaving in an unethical manner.",
+
+    "Filename word regex": "This regular expression will be used extract words from filename, and they will be joined using the option below into label text used for training. Leave empty to keep filename text as it is.",
+    "Filename join string": "This string will be used to hoin split words into a single line if the option above is enabled.",
 }
 
 
diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py
index 8314450a..b6c06d49 100644
--- a/modules/hypernetworks/hypernetwork.py
+++ b/modules/hypernetworks/hypernetwork.py
@@ -14,7 +14,7 @@ import torch
 from torch import einsum
 from einops import rearrange, repeat
 import modules.textual_inversion.dataset
-from modules.textual_inversion.learn_schedule import LearnSchedule
+from modules.textual_inversion.learn_schedule import LearnRateScheduler
 
 
 class HypernetworkModule(torch.nn.Module):
@@ -223,31 +223,23 @@ def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory,
     if ititial_step > steps:
         return hypernetwork, filename
 
-    schedules = iter(LearnSchedule(learn_rate, steps, ititial_step))
-    (learn_rate, end_step) = next(schedules)
-    print(f'Training at rate of {learn_rate} until step {end_step}')
-
-    optimizer = torch.optim.AdamW(weights, lr=learn_rate)
+    scheduler = LearnRateScheduler(learn_rate, steps, ititial_step)
+    optimizer = torch.optim.AdamW(weights, lr=scheduler.learn_rate)
 
     pbar = tqdm.tqdm(enumerate(ds), total=steps - ititial_step)
-    for i, (x, text, cond) in pbar:
+    for i, entry in pbar:
         hypernetwork.step = i + ititial_step
 
-        if hypernetwork.step > end_step:
-            try:
-                (learn_rate, end_step) = next(schedules)
-            except Exception:
-                break
-            tqdm.tqdm.write(f'Training at rate of {learn_rate} until step {end_step}')
-            for pg in optimizer.param_groups:
-                pg['lr'] = learn_rate
+        scheduler.apply(optimizer, hypernetwork.step)
+        if scheduler.finished:
+            break
 
         if shared.state.interrupted:
             break
 
         with torch.autocast("cuda"):
-            cond = cond.to(devices.device)
-            x = x.to(devices.device)
+            cond = entry.cond.to(devices.device)
+            x = entry.latent.to(devices.device)
             loss = shared.sd_model(x.unsqueeze(0), cond)[0]
             del x
             del cond
@@ -267,7 +259,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory,
         if hypernetwork.step > 0 and images_dir is not None and hypernetwork.step % create_image_every == 0:
             last_saved_image = os.path.join(images_dir, f'{hypernetwork_name}-{hypernetwork.step}.png')
 
-            preview_text = text if preview_image_prompt == "" else preview_image_prompt
+            preview_text = entry.cond_text if preview_image_prompt == "" else preview_image_prompt
 
             optimizer.zero_grad()
             shared.sd_model.cond_stage_model.to(devices.device)
@@ -282,16 +274,16 @@ def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory,
             )
 
             processed = processing.process_images(p)
-            image = processed.images[0]
+            image = processed.images[0] if len(processed.images)>0 else None
 
             if unload:
                 shared.sd_model.cond_stage_model.to(devices.cpu)
                 shared.sd_model.first_stage_model.to(devices.cpu)
 
-            shared.state.current_image = image
-            image.save(last_saved_image)
-
-            last_saved_image += f", prompt: {preview_text}"
+            if image is not None:
+                shared.state.current_image = image
+                image.save(last_saved_image)
+                last_saved_image += f", prompt: {preview_text}"
 
         shared.state.job_no = hypernetwork.step
 
@@ -299,7 +291,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory,
 <p>
 Loss: {losses.mean():.7f}<br/>
 Step: {hypernetwork.step}<br/>
-Last prompt: {html.escape(text)}<br/>
+Last prompt: {html.escape(entry.cond_text)}<br/>
 Last saved embedding: {html.escape(last_saved_file)}<br/>
 Last saved image: {html.escape(last_saved_image)}<br/>
 </p>
diff --git a/modules/shared.py b/modules/shared.py
index 42e99741..e64e69fc 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -231,6 +231,9 @@ options_templates.update(options_section(('system', "System"), {
 
 options_templates.update(options_section(('training', "Training"), {
     "unload_models_when_training": OptionInfo(False, "Unload VAE and CLIP from VRAM when training"),
+    "dataset_filename_word_regex": OptionInfo("", "Filename word regex"),
+    "dataset_filename_join_string": OptionInfo(" ", "Filename join string"),
+    "training_image_repeats_per_epoch": OptionInfo(100, "Number of repeats for a single input image per epoch; used only for displaying epoch number", gr.Number, {"precision": 0}),
 }))
 
 options_templates.update(options_section(('sd', "Stable Diffusion"), {
diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py
index f61f40d3..67e90afe 100644
--- a/modules/textual_inversion/dataset.py
+++ b/modules/textual_inversion/dataset.py
@@ -11,11 +11,21 @@ import tqdm
 from modules import devices, shared
 import re
 
-re_tag = re.compile(r"[a-zA-Z][_\w\d()]+")
+re_numbers_at_start = re.compile(r"^[-\d]+\s*")
+
+
+class DatasetEntry:
+    def __init__(self, filename=None, latent=None, filename_text=None):
+        self.filename = filename
+        self.latent = latent
+        self.filename_text = filename_text
+        self.cond = None
+        self.cond_text = None
 
 
 class PersonalizedBase(Dataset):
     def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, device=None, template_file=None, include_cond=False):
+        re_word = re.compile(shared.opts.dataset_filename_word_regex) if len(shared.opts.dataset_filename_word_regex)>0 else None
 
         self.placeholder_token = placeholder_token
 
@@ -42,9 +52,18 @@ class PersonalizedBase(Dataset):
             except Exception:
                 continue
 
+            text_filename = os.path.splitext(path)[0] + ".txt"
             filename = os.path.basename(path)
-            filename_tokens = os.path.splitext(filename)[0]
-            filename_tokens = re_tag.findall(filename_tokens)
+
+            if os.path.exists(text_filename):
+                with open(text_filename, "r", encoding="utf8") as file:
+                    filename_text = file.read()
+            else:
+                filename_text = os.path.splitext(filename)[0]
+                filename_text = re.sub(re_numbers_at_start, '', filename_text)
+                if re_word:
+                    tokens = re_word.findall(filename_text)
+                    filename_text = (shared.opts.dataset_filename_join_string or "").join(tokens)
 
             npimage = np.array(image).astype(np.uint8)
             npimage = (npimage / 127.5 - 1.0).astype(np.float32)
@@ -55,13 +74,13 @@ class PersonalizedBase(Dataset):
             init_latent = model.get_first_stage_encoding(model.encode_first_stage(torchdata.unsqueeze(dim=0))).squeeze()
             init_latent = init_latent.to(devices.cpu)
 
+            entry = DatasetEntry(filename=path, filename_text=filename_text, latent=init_latent)
+
             if include_cond:
-                text = self.create_text(filename_tokens)
-                cond = cond_model([text]).to(devices.cpu)
-            else:
-                cond = None
+                entry.cond_text = self.create_text(filename_text)
+                entry.cond = cond_model([entry.cond_text]).to(devices.cpu)
 
-            self.dataset.append((init_latent, filename_tokens, cond))
+            self.dataset.append(entry)
 
         self.length = len(self.dataset) * repeats
 
@@ -72,10 +91,10 @@ class PersonalizedBase(Dataset):
     def shuffle(self):
         self.indexes = self.initial_indexes[torch.randperm(self.initial_indexes.shape[0])]
 
-    def create_text(self, filename_tokens):
+    def create_text(self, filename_text):
         text = random.choice(self.lines)
         text = text.replace("[name]", self.placeholder_token)
-        text = text.replace("[filewords]", ' '.join(filename_tokens))
+        text = text.replace("[filewords]", filename_text)
         return text
 
     def __len__(self):
@@ -86,7 +105,9 @@ class PersonalizedBase(Dataset):
             self.shuffle()
 
         index = self.indexes[i % len(self.indexes)]
-        x, filename_tokens, cond = self.dataset[index]
+        entry = self.dataset[index]
+
+        if entry.cond is None:
+            entry.cond_text = self.create_text(entry.filename_text)
 
-        text = self.create_text(filename_tokens)
-        return x, text, cond
+        return entry
diff --git a/modules/textual_inversion/learn_schedule.py b/modules/textual_inversion/learn_schedule.py
index db720271..2062726a 100644
--- a/modules/textual_inversion/learn_schedule.py
+++ b/modules/textual_inversion/learn_schedule.py
@@ -1,6 +1,12 @@
+import tqdm
 
-class LearnSchedule:
+
+class LearnScheduleIterator:
     def __init__(self, learn_rate, max_steps, cur_step=0):
+        """
+        specify learn_rate as "0.001:100, 0.00001:1000, 1e-5:10000" to have lr of 0.001 until step 100, 0.00001 until 1000, 1e-5:10000 until 10000
+        """
+
         pairs = learn_rate.split(',')
         self.rates = []
         self.it = 0
@@ -32,3 +38,32 @@ class LearnSchedule:
             return self.rates[self.it - 1]
         else:
             raise StopIteration
+
+
+class LearnRateScheduler:
+    def __init__(self, learn_rate, max_steps, cur_step=0, verbose=True):
+        self.schedules = LearnScheduleIterator(learn_rate, max_steps, cur_step)
+        (self.learn_rate,  self.end_step) = next(self.schedules)
+        self.verbose = verbose
+
+        if self.verbose:
+            print(f'Training at rate of {self.learn_rate} until step {self.end_step}')
+
+        self.finished = False
+
+    def apply(self, optimizer, step_number):
+        if step_number <= self.end_step:
+            return
+
+        try:
+            (self.learn_rate, self.end_step) = next(self.schedules)
+        except Exception:
+            self.finished = True
+            return
+
+        if self.verbose:
+            tqdm.tqdm.write(f'Training at rate of {self.learn_rate} until step {self.end_step}')
+
+        for pg in optimizer.param_groups:
+            pg['lr'] = self.learn_rate
+
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py
index c5153e4a..fa0e33a2 100644
--- a/modules/textual_inversion/textual_inversion.py
+++ b/modules/textual_inversion/textual_inversion.py
@@ -11,7 +11,7 @@ from PIL import Image, PngImagePlugin
 
 from modules import shared, devices, sd_hijack, processing, sd_models
 import modules.textual_inversion.dataset
-from modules.textual_inversion.learn_schedule import LearnSchedule
+from modules.textual_inversion.learn_schedule import LearnRateScheduler
 
 from modules.textual_inversion.image_embedding import (embedding_to_b64, embedding_from_b64,
                                                        insert_image_data_embed, extract_image_data_embed,
@@ -172,8 +172,7 @@ def create_embedding(name, num_vectors_per_token, init_text='*'):
     return fn
 
 
-
-def train_embedding(embedding_name, learn_rate, data_root, log_directory, training_width, training_height, steps, num_repeats, create_image_every, save_embedding_every, template_file, save_image_with_stored_embedding, preview_image_prompt):
+def train_embedding(embedding_name, learn_rate, data_root, log_directory, training_width, training_height, steps, create_image_every, save_embedding_every, template_file, save_image_with_stored_embedding, preview_image_prompt):
     assert embedding_name, 'embedding not selected'
 
     shared.state.textinfo = "Initializing textual inversion training..."
@@ -205,7 +204,7 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini
 
     shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."
     with torch.autocast("cuda"):
-        ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=num_repeats, placeholder_token=embedding_name, model=shared.sd_model, device=devices.device, template_file=template_file)
+        ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=embedding_name, model=shared.sd_model, device=devices.device, template_file=template_file)
 
     hijack = sd_hijack.model_hijack
 
@@ -221,32 +220,24 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini
     if ititial_step > steps:
         return embedding, filename
 
-    schedules = iter(LearnSchedule(learn_rate, steps, ititial_step))
-    (learn_rate, end_step) = next(schedules)
-    print(f'Training at rate of {learn_rate} until step {end_step}')
-
-    optimizer = torch.optim.AdamW([embedding.vec], lr=learn_rate)
+    scheduler = LearnRateScheduler(learn_rate, steps, ititial_step)
+    optimizer = torch.optim.AdamW([embedding.vec], lr=scheduler.learn_rate)
 
     pbar = tqdm.tqdm(enumerate(ds), total=steps-ititial_step)
-    for i, (x, text, _) in pbar:
+    for i, entry in pbar:
         embedding.step = i + ititial_step
 
-        if embedding.step > end_step:
-            try:
-                (learn_rate, end_step) = next(schedules)
-            except:
-                break
-            tqdm.tqdm.write(f'Training at rate of {learn_rate} until step {end_step}')
-            for pg in optimizer.param_groups:
-                pg['lr'] = learn_rate
+        scheduler.apply(optimizer, embedding.step)
+        if scheduler.finished:
+            break
 
         if shared.state.interrupted:
             break
 
         with torch.autocast("cuda"):
-            c = cond_model([text])
+            c = cond_model([entry.cond_text])
 
-            x = x.to(devices.device)
+            x = entry.latent.to(devices.device)
             loss = shared.sd_model(x.unsqueeze(0), c)[0]
             del x
 
@@ -268,7 +259,7 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini
         if embedding.step > 0 and images_dir is not None and embedding.step % create_image_every == 0:
             last_saved_image = os.path.join(images_dir, f'{embedding_name}-{embedding.step}.png')
 
-            preview_text = text if preview_image_prompt == "" else preview_image_prompt
+            preview_text = entry.cond_text if preview_image_prompt == "" else preview_image_prompt
 
             p = processing.StableDiffusionProcessingTxt2Img(
                 sd_model=shared.sd_model,
@@ -314,7 +305,7 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini
 <p>
 Loss: {losses.mean():.7f}<br/>
 Step: {embedding.step}<br/>
-Last prompt: {html.escape(text)}<br/>
+Last prompt: {html.escape(entry.cond_text)}<br/>
 Last saved embedding: {html.escape(last_saved_file)}<br/>
 Last saved image: {html.escape(last_saved_image)}<br/>
 </p>
diff --git a/modules/ui.py b/modules/ui.py
index 2b332267..c42535c8 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -1098,7 +1098,6 @@ def create_ui(wrap_gradio_gpu_call):
                     training_width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512)
                     training_height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512)
                     steps = gr.Number(label='Max steps', value=100000, precision=0)
-                    num_repeats = gr.Number(label='Number of repeats for a single input image per epoch', value=100, precision=0)
                     create_image_every = gr.Number(label='Save an image to log directory every N steps, 0 to disable', value=500, precision=0)
                     save_embedding_every = gr.Number(label='Save a copy of embedding to log directory every N steps, 0 to disable', value=500, precision=0)
                     save_image_with_stored_embedding = gr.Checkbox(label='Save images with embedding in PNG chunks', value=True)
@@ -1176,7 +1175,6 @@ def create_ui(wrap_gradio_gpu_call):
                 training_width,
                 training_height,
                 steps,
-                num_repeats,
                 create_image_every,
                 save_embedding_every,
                 template_file,
-- 
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/ui.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