diff options
Diffstat (limited to 'modules/textual_inversion/preprocess.py')
| -rw-r--r-- | modules/textual_inversion/preprocess.py | 51 |
1 files changed, 43 insertions, 8 deletions
diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index 56b9b2eb..2239cb84 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -6,13 +6,12 @@ import sys import tqdm
import time
-from modules import shared, images, deepbooru
-from modules.paths import models_path
+from modules import paths, shared, images, deepbooru
from modules.shared import opts, cmd_opts
from modules.textual_inversion import autocrop
-def preprocess(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False):
+def preprocess(id_task, 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, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None):
try:
if process_caption:
shared.interrogator.load()
@@ -20,7 +19,7 @@ def preprocess(process_src, process_dst, process_width, process_height, preproce if process_caption_deepbooru:
deepbooru.model.start()
- preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru, split_threshold, overlap_ratio, process_focal_crop, process_focal_crop_face_weight, process_focal_crop_entropy_weight, process_focal_crop_edges_weight, process_focal_crop_debug)
+ preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru, split_threshold, overlap_ratio, process_focal_crop, process_focal_crop_face_weight, process_focal_crop_entropy_weight, process_focal_crop_edges_weight, process_focal_crop_debug, process_multicrop, process_multicrop_mindim, process_multicrop_maxdim, process_multicrop_minarea, process_multicrop_maxarea, process_multicrop_objective, process_multicrop_threshold)
finally:
@@ -109,8 +108,30 @@ def split_pic(image, inverse_xy, width, height, overlap_ratio): splitted = image.crop((0, y, to_w, y + to_h))
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):
+# not using torchvision.transforms.CenterCrop because it doesn't allow float regions
+def center_crop(image: Image, w: int, h: int):
+ iw, ih = image.size
+ if ih / h < iw / w:
+ sw = w * ih / h
+ box = (iw - sw) / 2, 0, iw - (iw - sw) / 2, ih
+ else:
+ sh = h * iw / w
+ box = 0, (ih - sh) / 2, iw, ih - (ih - sh) / 2
+ return image.resize((w, h), Image.Resampling.LANCZOS, box)
+
+
+def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, threshold):
+ iw, ih = image.size
+ err = lambda w, h: 1-(lambda x: x if x < 1 else 1/x)(iw/ih/(w/h))
+ wh = max(((w, h) for w in range(mindim, maxdim+1, 64) for h in range(mindim, maxdim+1, 64)
+ if minarea <= w * h <= maxarea and err(w, h) <= threshold),
+ key= lambda wh: (wh[0]*wh[1], -err(*wh))[::1 if objective=='Maximize area' else -1],
+ default=None
+ )
+ return wh and center_crop(image, *wh)
+
+
+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, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None):
width = process_width
height = process_height
src = os.path.abspath(process_src)
@@ -124,6 +145,7 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre files = listfiles(src)
+ shared.state.job = "preprocess"
shared.state.textinfo = "Preprocessing..."
shared.state.job_count = len(files)
@@ -134,7 +156,8 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre params.process_caption_deepbooru = process_caption_deepbooru
params.preprocess_txt_action = preprocess_txt_action
- for index, imagefile in enumerate(tqdm.tqdm(files)):
+ pbar = tqdm.tqdm(files)
+ for index, imagefile in enumerate(pbar):
params.subindex = 0
filename = os.path.join(src, imagefile)
try:
@@ -142,6 +165,10 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre except Exception:
continue
+ description = f"Preprocessing [Image {index}/{len(files)}]"
+ pbar.set_description(description)
+ shared.state.textinfo = description
+
params.src = filename
existing_caption = None
@@ -171,7 +198,7 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre dnn_model_path = None
try:
- dnn_model_path = autocrop.download_and_cache_models(os.path.join(models_path, "opencv"))
+ dnn_model_path = autocrop.download_and_cache_models(os.path.join(paths.models_path, "opencv"))
except Exception as e:
print("Unable to load face detection model for auto crop selection. Falling back to lower quality haar method.", e)
@@ -188,6 +215,14 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre save_pic(focal, index, params, existing_caption=existing_caption)
process_default_resize = False
+ if process_multicrop:
+ cropped = multicrop_pic(img, process_multicrop_mindim, process_multicrop_maxdim, process_multicrop_minarea, process_multicrop_maxarea, process_multicrop_objective, process_multicrop_threshold)
+ if cropped is not None:
+ save_pic(cropped, index, params, existing_caption=existing_caption)
+ else:
+ print(f"skipped {img.width}x{img.height} image {filename} (can't find suitable size within error threshold)")
+ process_default_resize = False
+
if process_default_resize:
img = images.resize_image(1, img, width, height)
save_pic(img, index, params, existing_caption=existing_caption)
|