diff options
Diffstat (limited to 'modules/textual_inversion')
| -rw-r--r-- | modules/textual_inversion/autocrop.py | 12 | ||||
| -rw-r--r-- | modules/textual_inversion/dataset.py | 2 | ||||
| -rw-r--r-- | modules/textual_inversion/image_embedding.py | 4 | ||||
| -rw-r--r-- | modules/textual_inversion/learn_schedule.py | 6 | ||||
| -rw-r--r-- | modules/textual_inversion/preprocess.py | 24 | ||||
| -rw-r--r-- | modules/textual_inversion/textual_inversion.py | 34 |
6 files changed, 43 insertions, 39 deletions
diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index 68e1103c..7770d22f 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -1,10 +1,8 @@ import cv2
import requests
import os
-from collections import defaultdict
-from math import log, sqrt
import numpy as np
-from PIL import Image, ImageDraw
+from PIL import ImageDraw
GREEN = "#0F0"
BLUE = "#00F"
@@ -111,7 +109,7 @@ def focal_point(im, settings): if corner_centroid is not None:
color = BLUE
box = corner_centroid.bounding(max_size * corner_centroid.weight)
- d.text((box[0], box[1]-15), "Edge: %.02f" % corner_centroid.weight, fill=color)
+ 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:
@@ -119,7 +117,7 @@ def focal_point(im, settings): if entropy_centroid is not None:
color = "#ff0"
box = entropy_centroid.bounding(max_size * entropy_centroid.weight)
- d.text((box[0], box[1]-15), "Entropy: %.02f" % entropy_centroid.weight, fill=color)
+ 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:
@@ -127,7 +125,7 @@ def focal_point(im, settings): if face_centroid is not None:
color = RED
box = face_centroid.bounding(max_size * face_centroid.weight)
- d.text((box[0], box[1]-15), "Face: %.02f" % face_centroid.weight, fill=color)
+ 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:
@@ -185,7 +183,7 @@ def image_face_points(im, settings): try:
faces = classifier.detectMultiScale(gray, scaleFactor=1.1,
minNeighbors=7, minSize=(minsize, minsize), flags=cv2.CASCADE_SCALE_IMAGE)
- except:
+ except Exception:
continue
if len(faces) > 0:
diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py index af9fbcf2..41610e03 100644 --- a/modules/textual_inversion/dataset.py +++ b/modules/textual_inversion/dataset.py @@ -72,7 +72,7 @@ class PersonalizedBase(Dataset): except Exception:
continue
- text_filename = os.path.splitext(path)[0] + ".txt"
+ text_filename = f"{os.path.splitext(path)[0]}.txt"
filename = os.path.basename(path)
if os.path.exists(text_filename):
diff --git a/modules/textual_inversion/image_embedding.py b/modules/textual_inversion/image_embedding.py index 5593f88c..d85a4888 100644 --- a/modules/textual_inversion/image_embedding.py +++ b/modules/textual_inversion/image_embedding.py @@ -2,7 +2,7 @@ import base64 import json
import numpy as np
import zlib
-from PIL import Image, PngImagePlugin, ImageDraw, ImageFont
+from PIL import Image, ImageDraw, ImageFont
from fonts.ttf import Roboto
import torch
from modules.shared import opts
@@ -17,7 +17,7 @@ class EmbeddingEncoder(json.JSONEncoder): class EmbeddingDecoder(json.JSONDecoder):
def __init__(self, *args, **kwargs):
- json.JSONDecoder.__init__(self, object_hook=self.object_hook, *args, **kwargs)
+ json.JSONDecoder.__init__(self, *args, object_hook=self.object_hook, **kwargs)
def object_hook(self, d):
if 'TORCHTENSOR' in d:
diff --git a/modules/textual_inversion/learn_schedule.py b/modules/textual_inversion/learn_schedule.py index f63fc72f..c56bea45 100644 --- a/modules/textual_inversion/learn_schedule.py +++ b/modules/textual_inversion/learn_schedule.py @@ -12,7 +12,7 @@ class LearnScheduleIterator: self.it = 0
self.maxit = 0
try:
- for i, pair in enumerate(pairs):
+ for pair in pairs:
if not pair.strip():
continue
tmp = pair.split(':')
@@ -32,8 +32,8 @@ class LearnScheduleIterator: self.maxit += 1
return
assert self.rates
- except (ValueError, AssertionError):
- raise Exception('Invalid learning rate schedule. It should be a number or, for example, like "0.001:100, 0.00001:1000, 1e-5:10000" to have lr of 0.001 until step 100, 0.00001 until 1000, and 1e-5 until 10000.')
+ except (ValueError, AssertionError) as e:
+ raise Exception('Invalid learning rate schedule. It should be a number or, for example, like "0.001:100, 0.00001:1000, 1e-5:10000" to have lr of 0.001 until step 100, 0.00001 until 1000, and 1e-5 until 10000.') from e
def __iter__(self):
diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index 2239cb84..d0cad09e 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -1,17 +1,13 @@ import os
from PIL import Image, ImageOps
import math
-import platform
-import sys
import tqdm
-import time
from modules import paths, shared, images, deepbooru
-from modules.shared import opts, cmd_opts
from modules.textual_inversion import autocrop
-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):
+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=0.3, 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()
@@ -19,7 +15,7 @@ def preprocess(id_task, process_src, process_dst, process_width, process_height, 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, process_multicrop, process_multicrop_mindim, process_multicrop_maxdim, process_multicrop_minarea, process_multicrop_maxarea, process_multicrop_objective, process_multicrop_threshold)
+ 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:
@@ -63,9 +59,9 @@ def save_pic_with_caption(image, index, params: PreprocessParams, existing_capti image.save(os.path.join(params.dstdir, f"{basename}.png"))
if params.preprocess_txt_action == 'prepend' and existing_caption:
- caption = existing_caption + ' ' + caption
+ caption = f"{existing_caption} {caption}"
elif params.preprocess_txt_action == 'append' and existing_caption:
- caption = caption + ' ' + existing_caption
+ caption = f"{caption} {existing_caption}"
elif params.preprocess_txt_action == 'copy' and existing_caption:
caption = existing_caption
@@ -131,7 +127,7 @@ def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, thr 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):
+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)
@@ -161,7 +157,9 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre params.subindex = 0
filename = os.path.join(src, imagefile)
try:
- img = Image.open(filename).convert("RGB")
+ img = Image.open(filename)
+ img = ImageOps.exif_transpose(img)
+ img = img.convert("RGB")
except Exception:
continue
@@ -172,7 +170,7 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre params.src = filename
existing_caption = None
- existing_caption_filename = os.path.splitext(filename)[0] + '.txt'
+ 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()
@@ -223,6 +221,10 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre 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)
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index d2e62e58..9e1b2b9a 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -1,7 +1,6 @@ import os
import sys
import traceback
-import inspect
from collections import namedtuple
import torch
@@ -30,7 +29,7 @@ textual_inversion_templates = {} def list_textual_inversion_templates():
textual_inversion_templates.clear()
- for root, dirs, fns in os.walk(shared.cmd_opts.textual_inversion_templates_dir):
+ for root, _, fns in os.walk(shared.cmd_opts.textual_inversion_templates_dir):
for fn in fns:
path = os.path.join(root, fn)
@@ -69,7 +68,7 @@ class Embedding: 'hash': self.checksum(),
'optimizer_state_dict': self.optimizer_state_dict,
}
- torch.save(optimizer_saved_dict, filename + '.optim')
+ torch.save(optimizer_saved_dict, f"{filename}.optim")
def checksum(self):
if self.cached_checksum is not None:
@@ -167,8 +166,7 @@ class EmbeddingDatabase: # textual inversion embeddings
if 'string_to_param' in data:
param_dict = data['string_to_param']
- if hasattr(param_dict, '_parameters'):
- param_dict = getattr(param_dict, '_parameters') # fix for torch 1.12.1 loading saved file from torch 1.11
+ param_dict = getattr(param_dict, '_parameters', param_dict) # fix for torch 1.12.1 loading saved file from torch 1.11
assert len(param_dict) == 1, 'embedding file has multiple terms in it'
emb = next(iter(param_dict.items()))[1]
# diffuser concepts
@@ -199,7 +197,7 @@ class EmbeddingDatabase: if not os.path.isdir(embdir.path):
return
- for root, dirs, fns in os.walk(embdir.path, followlinks=True):
+ for root, _, fns in os.walk(embdir.path, followlinks=True):
for fn in fns:
try:
fullfn = os.path.join(root, fn)
@@ -216,7 +214,7 @@ class EmbeddingDatabase: def load_textual_inversion_embeddings(self, force_reload=False):
if not force_reload:
need_reload = False
- for path, embdir in self.embedding_dirs.items():
+ for embdir in self.embedding_dirs.values():
if embdir.has_changed():
need_reload = True
break
@@ -229,10 +227,16 @@ class EmbeddingDatabase: self.skipped_embeddings.clear()
self.expected_shape = self.get_expected_shape()
- for path, embdir in self.embedding_dirs.items():
+ for embdir in self.embedding_dirs.values():
self.load_from_dir(embdir)
embdir.update()
+ # re-sort word_embeddings because load_from_dir may not load in alphabetic order.
+ # using a temporary copy so we don't reinitialize self.word_embeddings in case other objects have a reference to it.
+ sorted_word_embeddings = {e.name: e for e in sorted(self.word_embeddings.values(), key=lambda e: e.name.lower())}
+ self.word_embeddings.clear()
+ self.word_embeddings.update(sorted_word_embeddings)
+
displayed_embeddings = (tuple(self.word_embeddings.keys()), tuple(self.skipped_embeddings.keys()))
if self.previously_displayed_embeddings != displayed_embeddings:
self.previously_displayed_embeddings = displayed_embeddings
@@ -431,8 +435,8 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st optimizer = torch.optim.AdamW([embedding.vec], lr=scheduler.learn_rate, weight_decay=0.0)
if shared.opts.save_optimizer_state:
optimizer_state_dict = None
- if os.path.exists(filename + '.optim'):
- optimizer_saved_dict = torch.load(filename + '.optim', map_location='cpu')
+ if os.path.exists(f"{filename}.optim"):
+ optimizer_saved_dict = torch.load(f"{filename}.optim", map_location='cpu')
if embedding.checksum() == optimizer_saved_dict.get('hash', None):
optimizer_state_dict = optimizer_saved_dict.get('optimizer_state_dict', None)
@@ -464,7 +468,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st try:
sd_hijack_checkpoint.add()
- for i in range((steps-initial_step) * gradient_step):
+ for _ in range((steps-initial_step) * gradient_step):
if scheduler.finished:
break
if shared.state.interrupted:
@@ -593,17 +597,17 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st data = torch.load(last_saved_file)
info.add_text("sd-ti-embedding", embedding_to_b64(data))
- title = "<{}>".format(data.get('name', '???'))
+ title = f"<{data.get('name', '???')}>"
try:
vectorSize = list(data['string_to_param'].values())[0].shape[0]
- except Exception as e:
+ except Exception:
vectorSize = '?'
checkpoint = sd_models.select_checkpoint()
footer_left = checkpoint.model_name
- footer_mid = '[{}]'.format(checkpoint.shorthash)
- footer_right = '{}v {}s'.format(vectorSize, steps_done)
+ footer_mid = f'[{checkpoint.shorthash}]'
+ footer_right = f'{vectorSize}v {steps_done}s'
captioned_image = caption_image_overlay(image, title, footer_left, footer_mid, footer_right)
captioned_image = insert_image_data_embed(captioned_image, data)
|