diff options
Diffstat (limited to 'modules/textual_inversion')
| -rw-r--r-- | modules/textual_inversion/autocrop.py | 239 | ||||
| -rw-r--r-- | modules/textual_inversion/preprocess.py | 232 | ||||
| -rw-r--r-- | modules/textual_inversion/textual_inversion.py | 10 | ||||
| -rw-r--r-- | modules/textual_inversion/ui.py | 7 |
4 files changed, 129 insertions, 359 deletions
diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index 1675e39a..e223a2e0 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -3,6 +3,8 @@ import requests import os
import numpy as np
from PIL import ImageDraw
+from modules import paths_internal
+from pkg_resources import parse_version
GREEN = "#0F0"
BLUE = "#00F"
@@ -25,7 +27,6 @@ def crop_image(im, settings): elif is_portrait(settings.crop_width, settings.crop_height):
scale_by = settings.crop_height / im.height
-
im = im.resize((int(im.width * scale_by), int(im.height * scale_by)))
im_debug = im.copy()
@@ -69,6 +70,7 @@ def crop_image(im, settings): return results
+
def focal_point(im, settings):
corner_points = image_corner_points(im, settings) if settings.corner_points_weight > 0 else []
entropy_points = image_entropy_points(im, settings) if settings.entropy_points_weight > 0 else []
@@ -78,118 +80,120 @@ def focal_point(im, settings): weight_pref_total = 0
if corner_points:
- weight_pref_total += settings.corner_points_weight
+ weight_pref_total += settings.corner_points_weight
if entropy_points:
- weight_pref_total += settings.entropy_points_weight
+ weight_pref_total += settings.entropy_points_weight
if face_points:
- weight_pref_total += settings.face_points_weight
+ weight_pref_total += settings.face_points_weight
corner_centroid = None
if corner_points:
- corner_centroid = centroid(corner_points)
- corner_centroid.weight = settings.corner_points_weight / weight_pref_total
- pois.append(corner_centroid)
+ corner_centroid = centroid(corner_points)
+ corner_centroid.weight = settings.corner_points_weight / weight_pref_total
+ pois.append(corner_centroid)
entropy_centroid = None
if entropy_points:
- entropy_centroid = centroid(entropy_points)
- entropy_centroid.weight = settings.entropy_points_weight / weight_pref_total
- pois.append(entropy_centroid)
+ entropy_centroid = centroid(entropy_points)
+ entropy_centroid.weight = settings.entropy_points_weight / weight_pref_total
+ pois.append(entropy_centroid)
face_centroid = None
if face_points:
- face_centroid = centroid(face_points)
- face_centroid.weight = settings.face_points_weight / weight_pref_total
- pois.append(face_centroid)
+ face_centroid = centroid(face_points)
+ face_centroid.weight = settings.face_points_weight / weight_pref_total
+ pois.append(face_centroid)
average_point = poi_average(pois, settings)
if settings.annotate_image:
- d = ImageDraw.Draw(im)
- max_size = min(im.width, im.height) * 0.07
- if corner_centroid is not None:
- color = BLUE
- box = corner_centroid.bounding(max_size * corner_centroid.weight)
- d.text((box[0], box[1]-15), f"Edge: {corner_centroid.weight:.02f}", fill=color)
- d.ellipse(box, outline=color)
- if len(corner_points) > 1:
- for f in corner_points:
- d.rectangle(f.bounding(4), outline=color)
- if entropy_centroid is not None:
- color = "#ff0"
- box = entropy_centroid.bounding(max_size * entropy_centroid.weight)
- d.text((box[0], box[1]-15), f"Entropy: {entropy_centroid.weight:.02f}", fill=color)
- d.ellipse(box, outline=color)
- if len(entropy_points) > 1:
- for f in entropy_points:
- d.rectangle(f.bounding(4), outline=color)
- if face_centroid is not None:
- color = RED
- box = face_centroid.bounding(max_size * face_centroid.weight)
- d.text((box[0], box[1]-15), f"Face: {face_centroid.weight:.02f}", fill=color)
- d.ellipse(box, outline=color)
- if len(face_points) > 1:
- for f in face_points:
- d.rectangle(f.bounding(4), outline=color)
-
- d.ellipse(average_point.bounding(max_size), outline=GREEN)
+ d = ImageDraw.Draw(im)
+ max_size = min(im.width, im.height) * 0.07
+ if corner_centroid is not None:
+ color = BLUE
+ box = corner_centroid.bounding(max_size * corner_centroid.weight)
+ d.text((box[0], box[1] - 15), f"Edge: {corner_centroid.weight:.02f}", fill=color)
+ d.ellipse(box, outline=color)
+ if len(corner_points) > 1:
+ for f in corner_points:
+ d.rectangle(f.bounding(4), outline=color)
+ if entropy_centroid is not None:
+ color = "#ff0"
+ box = entropy_centroid.bounding(max_size * entropy_centroid.weight)
+ d.text((box[0], box[1] - 15), f"Entropy: {entropy_centroid.weight:.02f}", fill=color)
+ d.ellipse(box, outline=color)
+ if len(entropy_points) > 1:
+ for f in entropy_points:
+ d.rectangle(f.bounding(4), outline=color)
+ if face_centroid is not None:
+ color = RED
+ box = face_centroid.bounding(max_size * face_centroid.weight)
+ d.text((box[0], box[1] - 15), f"Face: {face_centroid.weight:.02f}", fill=color)
+ d.ellipse(box, outline=color)
+ if len(face_points) > 1:
+ for f in face_points:
+ d.rectangle(f.bounding(4), outline=color)
+
+ d.ellipse(average_point.bounding(max_size), outline=GREEN)
return average_point
def image_face_points(im, settings):
if settings.dnn_model_path is not None:
- detector = cv2.FaceDetectorYN.create(
- settings.dnn_model_path,
- "",
- (im.width, im.height),
- 0.9, # score threshold
- 0.3, # nms threshold
- 5000 # keep top k before nms
- )
- faces = detector.detect(np.array(im))
- results = []
- if faces[1] is not None:
- for face in faces[1]:
- x = face[0]
- y = face[1]
- w = face[2]
- h = face[3]
- results.append(
- PointOfInterest(
- int(x + (w * 0.5)), # face focus left/right is center
- int(y + (h * 0.33)), # face focus up/down is close to the top of the head
- size = w,
- weight = 1/len(faces[1])
- )
- )
- return results
+ detector = cv2.FaceDetectorYN.create(
+ settings.dnn_model_path,
+ "",
+ (im.width, im.height),
+ 0.9, # score threshold
+ 0.3, # nms threshold
+ 5000 # keep top k before nms
+ )
+ faces = detector.detect(np.array(im))
+ results = []
+ if faces[1] is not None:
+ for face in faces[1]:
+ x = face[0]
+ y = face[1]
+ w = face[2]
+ h = face[3]
+ results.append(
+ PointOfInterest(
+ int(x + (w * 0.5)), # face focus left/right is center
+ int(y + (h * 0.33)), # face focus up/down is close to the top of the head
+ size=w,
+ weight=1 / len(faces[1])
+ )
+ )
+ return results
else:
- np_im = np.array(im)
- gray = cv2.cvtColor(np_im, cv2.COLOR_BGR2GRAY)
-
- tries = [
- [ f'{cv2.data.haarcascades}haarcascade_eye.xml', 0.01 ],
- [ f'{cv2.data.haarcascades}haarcascade_frontalface_default.xml', 0.05 ],
- [ f'{cv2.data.haarcascades}haarcascade_profileface.xml', 0.05 ],
- [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt.xml', 0.05 ],
- [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt2.xml', 0.05 ],
- [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt_tree.xml', 0.05 ],
- [ f'{cv2.data.haarcascades}haarcascade_eye_tree_eyeglasses.xml', 0.05 ],
- [ f'{cv2.data.haarcascades}haarcascade_upperbody.xml', 0.05 ]
- ]
- for t in tries:
- classifier = cv2.CascadeClassifier(t[0])
- minsize = int(min(im.width, im.height) * t[1]) # at least N percent of the smallest side
- try:
- faces = classifier.detectMultiScale(gray, scaleFactor=1.1,
- minNeighbors=7, minSize=(minsize, minsize), flags=cv2.CASCADE_SCALE_IMAGE)
- except Exception:
- continue
-
- if faces:
- rects = [[f[0], f[1], f[0] + f[2], f[1] + f[3]] for f in faces]
- return [PointOfInterest((r[0] +r[2]) // 2, (r[1] + r[3]) // 2, size=abs(r[0]-r[2]), weight=1/len(rects)) for r in rects]
+ np_im = np.array(im)
+ gray = cv2.cvtColor(np_im, cv2.COLOR_BGR2GRAY)
+
+ tries = [
+ [f'{cv2.data.haarcascades}haarcascade_eye.xml', 0.01],
+ [f'{cv2.data.haarcascades}haarcascade_frontalface_default.xml', 0.05],
+ [f'{cv2.data.haarcascades}haarcascade_profileface.xml', 0.05],
+ [f'{cv2.data.haarcascades}haarcascade_frontalface_alt.xml', 0.05],
+ [f'{cv2.data.haarcascades}haarcascade_frontalface_alt2.xml', 0.05],
+ [f'{cv2.data.haarcascades}haarcascade_frontalface_alt_tree.xml', 0.05],
+ [f'{cv2.data.haarcascades}haarcascade_eye_tree_eyeglasses.xml', 0.05],
+ [f'{cv2.data.haarcascades}haarcascade_upperbody.xml', 0.05]
+ ]
+ for t in tries:
+ classifier = cv2.CascadeClassifier(t[0])
+ minsize = int(min(im.width, im.height) * t[1]) # at least N percent of the smallest side
+ try:
+ faces = classifier.detectMultiScale(gray, scaleFactor=1.1,
+ minNeighbors=7, minSize=(minsize, minsize),
+ flags=cv2.CASCADE_SCALE_IMAGE)
+ except Exception:
+ continue
+
+ if faces:
+ rects = [[f[0], f[1], f[0] + f[2], f[1] + f[3]] for f in faces]
+ return [PointOfInterest((r[0] + r[2]) // 2, (r[1] + r[3]) // 2, size=abs(r[0] - r[2]),
+ weight=1 / len(rects)) for r in rects]
return []
@@ -198,7 +202,7 @@ def image_corner_points(im, settings): # naive attempt at preventing focal points from collecting at watermarks near the bottom
gd = ImageDraw.Draw(grayscale)
- gd.rectangle([0, im.height*.9, im.width, im.height], fill="#999")
+ gd.rectangle([0, im.height * .9, im.width, im.height], fill="#999")
np_im = np.array(grayscale)
@@ -206,7 +210,7 @@ def image_corner_points(im, settings): np_im,
maxCorners=100,
qualityLevel=0.04,
- minDistance=min(grayscale.width, grayscale.height)*0.06,
+ minDistance=min(grayscale.width, grayscale.height) * 0.06,
useHarrisDetector=False,
)
@@ -215,8 +219,8 @@ def image_corner_points(im, settings): focal_points = []
for point in points:
- x, y = point.ravel()
- focal_points.append(PointOfInterest(x, y, size=4, weight=1/len(points)))
+ x, y = point.ravel()
+ focal_points.append(PointOfInterest(x, y, size=4, weight=1 / len(points)))
return focal_points
@@ -225,13 +229,13 @@ def image_entropy_points(im, settings): landscape = im.height < im.width
portrait = im.height > im.width
if landscape:
- move_idx = [0, 2]
- move_max = im.size[0]
+ move_idx = [0, 2]
+ move_max = im.size[0]
elif portrait:
- move_idx = [1, 3]
- move_max = im.size[1]
+ move_idx = [1, 3]
+ move_max = im.size[1]
else:
- return []
+ return []
e_max = 0
crop_current = [0, 0, settings.crop_width, settings.crop_height]
@@ -241,14 +245,14 @@ def image_entropy_points(im, settings): e = image_entropy(crop)
if (e > e_max):
- e_max = e
- crop_best = list(crop_current)
+ e_max = e
+ crop_best = list(crop_current)
crop_current[move_idx[0]] += 4
crop_current[move_idx[1]] += 4
- x_mid = int(crop_best[0] + settings.crop_width/2)
- y_mid = int(crop_best[1] + settings.crop_height/2)
+ x_mid = int(crop_best[0] + settings.crop_width / 2)
+ y_mid = int(crop_best[1] + settings.crop_height / 2)
return [PointOfInterest(x_mid, y_mid, size=25, weight=1.0)]
@@ -294,22 +298,23 @@ def is_square(w, h): return w == h
-def download_and_cache_models(dirname):
- download_url = 'https://github.com/opencv/opencv_zoo/blob/91fb0290f50896f38a0ab1e558b74b16bc009428/models/face_detection_yunet/face_detection_yunet_2022mar.onnx?raw=true'
- model_file_name = 'face_detection_yunet.onnx'
+model_dir_opencv = os.path.join(paths_internal.models_path, 'opencv')
+if parse_version(cv2.__version__) >= parse_version('4.8'):
+ model_file_path = os.path.join(model_dir_opencv, 'face_detection_yunet_2023mar.onnx')
+ model_url = 'https://github.com/opencv/opencv_zoo/blob/b6e370b10f641879a87890d44e42173077154a05/models/face_detection_yunet/face_detection_yunet_2023mar.onnx?raw=true'
+else:
+ model_file_path = os.path.join(model_dir_opencv, 'face_detection_yunet.onnx')
+ model_url = 'https://github.com/opencv/opencv_zoo/blob/91fb0290f50896f38a0ab1e558b74b16bc009428/models/face_detection_yunet/face_detection_yunet_2022mar.onnx?raw=true'
- os.makedirs(dirname, exist_ok=True)
- cache_file = os.path.join(dirname, model_file_name)
- if not os.path.exists(cache_file):
- print(f"downloading face detection model from '{download_url}' to '{cache_file}'")
- response = requests.get(download_url)
- with open(cache_file, "wb") as f:
+def download_and_cache_models():
+ if not os.path.exists(model_file_path):
+ os.makedirs(model_dir_opencv, exist_ok=True)
+ print(f"downloading face detection model from '{model_url}' to '{model_file_path}'")
+ response = requests.get(model_url)
+ with open(model_file_path, "wb") as f:
f.write(response.content)
-
- if os.path.exists(cache_file):
- return cache_file
- return None
+ return model_file_path
class PointOfInterest:
diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py deleted file mode 100644 index dbd856bd..00000000 --- a/modules/textual_inversion/preprocess.py +++ /dev/null @@ -1,232 +0,0 @@ -import os
-from PIL import Image, ImageOps
-import math
-import tqdm
-
-from modules import paths, shared, images, deepbooru
-from modules.textual_inversion import autocrop
-
-
-def preprocess(id_task, process_src, process_dst, process_width, process_height, preprocess_txt_action, process_keep_original_size, 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=0.15, 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()
-
- if process_caption_deepbooru:
- deepbooru.model.start()
-
- preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_keep_original_size, 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:
-
- if process_caption:
- shared.interrogator.send_blip_to_ram()
-
- if process_caption_deepbooru:
- deepbooru.model.stop()
-
-
-def listfiles(dirname):
- return os.listdir(dirname)
-
-
-class PreprocessParams:
- src = None
- dstdir = None
- subindex = 0
- flip = False
- process_caption = False
- process_caption_deepbooru = False
- preprocess_txt_action = None
-
-
-def save_pic_with_caption(image, index, params: PreprocessParams, existing_caption=None):
- caption = ""
-
- if params.process_caption:
- caption += shared.interrogator.generate_caption(image)
-
- if params.process_caption_deepbooru:
- if caption:
- caption += ", "
- caption += deepbooru.model.tag_multi(image)
-
- filename_part = params.src
- filename_part = os.path.splitext(filename_part)[0]
- filename_part = os.path.basename(filename_part)
-
- basename = f"{index:05}-{params.subindex}-{filename_part}"
- image.save(os.path.join(params.dstdir, f"{basename}.png"))
-
- if params.preprocess_txt_action == 'prepend' and existing_caption:
- caption = f"{existing_caption} {caption}"
- elif params.preprocess_txt_action == 'append' and existing_caption:
- caption = f"{caption} {existing_caption}"
- elif params.preprocess_txt_action == 'copy' and existing_caption:
- caption = existing_caption
-
- caption = caption.strip()
-
- if caption:
- with open(os.path.join(params.dstdir, f"{basename}.txt"), "w", encoding="utf8") as file:
- file.write(caption)
-
- params.subindex += 1
-
-
-def save_pic(image, index, params, existing_caption=None):
- save_pic_with_caption(image, index, params, existing_caption=existing_caption)
-
- 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
- else:
- from_w, from_h = image.width, image.height
- to_w, to_h = width, height
- h = from_h * to_w // from_w
- if inverse_xy:
- image = image.resize((h, to_w))
- else:
- image = image.resize((to_w, h))
-
- split_count = math.ceil((h - to_h * overlap_ratio) / (to_h * (1.0 - overlap_ratio)))
- y_step = (h - to_h) / (split_count - 1)
- for i in range(split_count):
- y = int(y_step * i)
- if inverse_xy:
- splitted = image.crop((y, 0, y + to_h, to_w))
- else:
- splitted = image.crop((0, y, to_w, y + to_h))
- yield splitted
-
-# 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_keep_original_size, 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)
- 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.job = "preprocess"
- 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
-
- pbar = tqdm.tqdm(files)
- for index, imagefile in enumerate(pbar):
- params.subindex = 0
- filename = os.path.join(src, imagefile)
- try:
- img = Image.open(filename)
- img = ImageOps.exif_transpose(img)
- img = img.convert("RGB")
- except Exception:
- continue
-
- description = f"Preprocessing [Image {index}/{len(files)}]"
- pbar.set_description(description)
- shared.state.textinfo = description
-
- params.src = filename
-
- existing_caption = None
- existing_caption_filename = f"{os.path.splitext(filename)[0]}.txt"
- if os.path.exists(existing_caption_filename):
- with open(existing_caption_filename, 'r', encoding="utf8") as file:
- existing_caption = file.read()
-
- if shared.state.interrupted:
- break
-
- if img.height > img.width:
- ratio = (img.width * height) / (img.height * width)
- inverse_xy = False
- else:
- ratio = (img.height * width) / (img.width * height)
- inverse_xy = True
-
- process_default_resize = True
-
- if process_split and ratio < 1.0 and ratio <= split_threshold:
- for splitted in split_pic(img, inverse_xy, width, height, overlap_ratio):
- save_pic(splitted, index, params, existing_caption=existing_caption)
- process_default_resize = False
-
- if process_focal_crop and img.height != img.width:
-
- dnn_model_path = None
- try:
- 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)
-
- autocrop_settings = autocrop.Settings(
- crop_width = width,
- crop_height = height,
- face_points_weight = process_focal_crop_face_weight,
- entropy_points_weight = process_focal_crop_entropy_weight,
- corner_points_weight = process_focal_crop_edges_weight,
- annotate_image = process_focal_crop_debug,
- dnn_model_path = dnn_model_path,
- )
- for focal in autocrop.crop_image(img, autocrop_settings):
- 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_keep_original_size:
- save_pic(img, 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, params, existing_caption=existing_caption)
-
- shared.state.nextjob()
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index 04dda585..c6bcab15 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -11,7 +11,6 @@ import safetensors.torch import numpy as np
from PIL import Image, PngImagePlugin
-from torch.utils.tensorboard import SummaryWriter
from modules import shared, devices, sd_hijack, sd_models, images, sd_samplers, sd_hijack_checkpoint, errors, hashes
import modules.textual_inversion.dataset
@@ -344,6 +343,7 @@ def write_loss(log_directory, filename, step, epoch_len, values): })
def tensorboard_setup(log_directory):
+ from torch.utils.tensorboard import SummaryWriter
os.makedirs(os.path.join(log_directory, "tensorboard"), exist_ok=True)
return SummaryWriter(
log_dir=os.path.join(log_directory, "tensorboard"),
@@ -448,8 +448,12 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."
old_parallel_processing_allowed = shared.parallel_processing_allowed
+ tensorboard_writer = None
if shared.opts.training_enable_tensorboard:
- tensorboard_writer = tensorboard_setup(log_directory)
+ try:
+ tensorboard_writer = tensorboard_setup(log_directory)
+ except ImportError:
+ errors.report("Error initializing tensorboard", exc_info=True)
pin_memory = shared.opts.pin_memory
@@ -622,7 +626,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st last_saved_image, last_text_info = images.save_image(image, images_dir, "", p.seed, p.prompt, shared.opts.samples_format, processed.infotexts[0], p=p, forced_filename=forced_filename, save_to_dirs=False)
last_saved_image += f", prompt: {preview_text}"
- if shared.opts.training_enable_tensorboard and shared.opts.training_tensorboard_save_images:
+ if tensorboard_writer and shared.opts.training_tensorboard_save_images:
tensorboard_add_image(tensorboard_writer, f"Validation at epoch {epoch_num}", image, embedding.step)
if save_image_with_stored_embedding and os.path.exists(last_saved_file) and embedding_yet_to_be_embedded:
diff --git a/modules/textual_inversion/ui.py b/modules/textual_inversion/ui.py index 35c4feef..f149ad1f 100644 --- a/modules/textual_inversion/ui.py +++ b/modules/textual_inversion/ui.py @@ -3,7 +3,6 @@ import html import gradio as gr
import modules.textual_inversion.textual_inversion
-import modules.textual_inversion.preprocess
from modules import sd_hijack, shared
@@ -15,12 +14,6 @@ def create_embedding(name, initialization_text, nvpt, overwrite_old): return gr.Dropdown.update(choices=sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys())), f"Created: {filename}", ""
-def preprocess(*args):
- modules.textual_inversion.preprocess.preprocess(*args)
-
- return f"Preprocessing {'interrupted' if shared.state.interrupted else 'finished'}.", ""
-
-
def train_embedding(*args):
assert not shared.cmd_opts.lowvram, 'Training models with lowvram not possible'
|