move functions out of main body for image preprocessing for easier hijacking

modules/textual_inversion/preprocess.py

@@ -35,64 +35,62 @@ def preprocess(process_src, process_dst, process_width, process_height, preproce
             deepbooru.release_process()
 
 
+def listfiles(dirname):
+    return os.listdir(dirname)
 
-def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False):
-    width = process_width
-    height = process_height
-    src = os.path.abspath(process_src)
-    dst = os.path.abspath(process_dst)
-    split_threshold = max(0.0, min(1.0, split_threshold))
-    overlap_ratio = max(0.0, min(0.9, overlap_ratio))
 
-    assert src != dst, 'same directory specified as source and destination'
+class PreprocessParams:
+    src = None
+    dstdir = None
+    subindex = 0
+    flip = False
+    process_caption = False
+    process_caption_deepbooru = False
+    preprocess_txt_action = None
 
-    os.makedirs(dst, exist_ok=True)
 
-    files = os.listdir(src)
+def save_pic_with_caption(image, index, params: PreprocessParams, existing_caption=None):
-
-    shared.state.textinfo = "Preprocessing..."
-    shared.state.job_count = len(files)
-
-    def save_pic_with_caption(image, index, existing_caption=None):
     caption = ""
 
-        if process_caption:
+    if params.process_caption:
         caption += shared.interrogator.generate_caption(image)
 
-        if process_caption_deepbooru:
+    if params.process_caption_deepbooru:
         if len(caption) > 0:
             caption += ", "
         caption += deepbooru.get_tags_from_process(image)
 
-        filename_part = filename
+    filename_part = params.src
     filename_part = os.path.splitext(filename_part)[0]
     filename_part = os.path.basename(filename_part)
 
-        basename = f"{index:05}-{subindex[0]}-{filename_part}"
+    basename = f"{index:05}-{params.subindex}-{filename_part}"
-        image.save(os.path.join(dst, f"{basename}.png"))
+    image.save(os.path.join(params.dstdir, f"{basename}.png"))
 
-        if preprocess_txt_action == 'prepend' and existing_caption:
+    if params.preprocess_txt_action == 'prepend' and existing_caption:
         caption = existing_caption + ' ' + caption
-        elif preprocess_txt_action == 'append' and existing_caption:
+    elif params.preprocess_txt_action == 'append' and existing_caption:
         caption = caption + ' ' + existing_caption
-        elif preprocess_txt_action == 'copy' and existing_caption:
+    elif params.preprocess_txt_action == 'copy' and existing_caption:
         caption = existing_caption
 
     caption = caption.strip()
 
     if len(caption) > 0:
-            with open(os.path.join(dst, f"{basename}.txt"), "w", encoding="utf8") as file:
+        with open(os.path.join(params.dstdir, f"{basename}.txt"), "w", encoding="utf8") as file:
             file.write(caption)
 
-        subindex[0] += 1
+    params.subindex += 1
 
-    def save_pic(image, index, existing_caption=None):
-        save_pic_with_caption(image, index, existing_caption=existing_caption)
 
-        if process_flip:
+def save_pic(image, index, params, existing_caption=None):
-            save_pic_with_caption(ImageOps.mirror(image), index, existing_caption=existing_caption)
+    save_pic_with_caption(image, index, params, existing_caption=existing_caption)
 
-    def split_pic(image, inverse_xy):
+    if params.flip:
+        save_pic_with_caption(ImageOps.mirror(image), index, params, existing_caption=existing_caption)
+
+
+def split_pic(image, inverse_xy, width, height, overlap_ratio):
     if inverse_xy:
         from_w, from_h = image.height, image.width
         to_w, to_h = height, width
@@ -116,14 +114,40 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre
         yield splitted
 
 
+def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False):
+    width = process_width
+    height = process_height
+    src = os.path.abspath(process_src)
+    dst = os.path.abspath(process_dst)
+    split_threshold = max(0.0, min(1.0, split_threshold))
+    overlap_ratio = max(0.0, min(0.9, overlap_ratio))
+
+    assert src != dst, 'same directory specified as source and destination'
+
+    os.makedirs(dst, exist_ok=True)
+
+    files = listfiles(src)
+
+    shared.state.textinfo = "Preprocessing..."
+    shared.state.job_count = len(files)
+
+    params = PreprocessParams()
+    params.dstdir = dst
+    params.flip = process_flip
+    params.process_caption = process_caption
+    params.process_caption_deepbooru = process_caption_deepbooru
+    params.preprocess_txt_action = preprocess_txt_action
+
     for index, imagefile in enumerate(tqdm.tqdm(files)):
-        subindex = [0]
+        params.subindex = 0
         filename = os.path.join(src, imagefile)
         try:
             img = Image.open(filename).convert("RGB")
         except Exception:
             continue
 
+        params.src = filename
+
         existing_caption = None
         existing_caption_filename = os.path.splitext(filename)[0] + '.txt'
         if os.path.exists(existing_caption_filename):
@@ -143,8 +167,8 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre
         process_default_resize = True
 
         if process_split and ratio < 1.0 and ratio <= split_threshold:
-            for splitted in split_pic(img, inverse_xy):
+            for splitted in split_pic(img, inverse_xy, width, height, overlap_ratio):
-                save_pic(splitted, index, existing_caption=existing_caption)
+                save_pic(splitted, index, params, existing_caption=existing_caption)
             process_default_resize = False
 
         if process_focal_crop and img.height != img.width:
@@ -165,11 +189,11 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre
                 dnn_model_path = dnn_model_path,
             )
             for focal in autocrop.crop_image(img, autocrop_settings):
-                save_pic(focal, index, existing_caption=existing_caption)
+                save_pic(focal, index, params, existing_caption=existing_caption)
             process_default_resize = False
 
         if process_default_resize:
             img = images.resize_image(1, img, width, height)
-            save_pic(img, index, existing_caption=existing_caption)
+            save_pic(img, index, params, existing_caption=existing_caption)
 
         shared.state.nextjob()