diff options
Diffstat (limited to 'modules/textual_inversion')
| -rw-r--r-- | modules/textual_inversion/autocrop.py | 17 | ||||
| -rw-r--r-- | modules/textual_inversion/dataset.py | 2 | ||||
| -rw-r--r-- | modules/textual_inversion/image_embedding.py | 21 | ||||
| -rw-r--r-- | modules/textual_inversion/logging.py | 48 | ||||
| -rw-r--r-- | modules/textual_inversion/preprocess.py | 6 | ||||
| -rw-r--r-- | modules/textual_inversion/textual_inversion.py | 37 |
6 files changed, 92 insertions, 39 deletions
diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index 8e667a4d..1675e39a 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -77,27 +77,27 @@ def focal_point(im, settings): pois = []
weight_pref_total = 0
- if len(corner_points) > 0:
+ if corner_points:
weight_pref_total += settings.corner_points_weight
- if len(entropy_points) > 0:
+ if entropy_points:
weight_pref_total += settings.entropy_points_weight
- if len(face_points) > 0:
+ if face_points:
weight_pref_total += settings.face_points_weight
corner_centroid = None
- if len(corner_points) > 0:
+ if corner_points:
corner_centroid = centroid(corner_points)
corner_centroid.weight = settings.corner_points_weight / weight_pref_total
pois.append(corner_centroid)
entropy_centroid = None
- if len(entropy_points) > 0:
+ if entropy_points:
entropy_centroid = centroid(entropy_points)
entropy_centroid.weight = settings.entropy_points_weight / weight_pref_total
pois.append(entropy_centroid)
face_centroid = None
- if len(face_points) > 0:
+ if face_points:
face_centroid = centroid(face_points)
face_centroid.weight = settings.face_points_weight / weight_pref_total
pois.append(face_centroid)
@@ -187,7 +187,7 @@ def image_face_points(im, settings): except Exception:
continue
- if len(faces) > 0:
+ 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 []
@@ -298,8 +298,7 @@ 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'
- if not os.path.exists(dirname):
- os.makedirs(dirname)
+ os.makedirs(dirname, exist_ok=True)
cache_file = os.path.join(dirname, model_file_name)
if not os.path.exists(cache_file):
diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py index b9621fc9..7ee05061 100644 --- a/modules/textual_inversion/dataset.py +++ b/modules/textual_inversion/dataset.py @@ -32,7 +32,7 @@ class DatasetEntry: class PersonalizedBase(Dataset):
def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, cond_model=None, device=None, template_file=None, include_cond=False, batch_size=1, gradient_step=1, shuffle_tags=False, tag_drop_out=0, latent_sampling_method='once', varsize=False, use_weight=False):
- re_word = re.compile(shared.opts.dataset_filename_word_regex) if len(shared.opts.dataset_filename_word_regex) > 0 else None
+ re_word = re.compile(shared.opts.dataset_filename_word_regex) if shared.opts.dataset_filename_word_regex else None
self.placeholder_token = placeholder_token
diff --git a/modules/textual_inversion/image_embedding.py b/modules/textual_inversion/image_embedding.py index 5858a55f..81cff7bf 100644 --- a/modules/textual_inversion/image_embedding.py +++ b/modules/textual_inversion/image_embedding.py @@ -1,8 +1,10 @@ import base64
import json
+import warnings
+
import numpy as np
import zlib
-from PIL import Image, ImageDraw, ImageFont
+from PIL import Image, ImageDraw
import torch
@@ -129,14 +131,17 @@ def extract_image_data_embed(image): def caption_image_overlay(srcimage, title, footerLeft, footerMid, footerRight, textfont=None):
+ from modules.images import get_font
+ if textfont:
+ warnings.warn(
+ 'passing in a textfont to caption_image_overlay is deprecated and does nothing',
+ DeprecationWarning,
+ stacklevel=2,
+ )
from math import cos
image = srcimage.copy()
fontsize = 32
- if textfont is None:
- from modules.images import get_font
- textfont = get_font(fontsize)
-
factor = 1.5
gradient = Image.new('RGBA', (1, image.size[1]), color=(0, 0, 0, 0))
for y in range(image.size[1]):
@@ -147,12 +152,12 @@ def caption_image_overlay(srcimage, title, footerLeft, footerMid, footerRight, t draw = ImageDraw.Draw(image)
- font = ImageFont.truetype(textfont, fontsize)
+ font = get_font(fontsize)
padding = 10
_, _, w, h = draw.textbbox((0, 0), title, font=font)
fontsize = min(int(fontsize * (((image.size[0]*0.75)-(padding*4))/w)), 72)
- font = ImageFont.truetype(textfont, fontsize)
+ font = get_font(fontsize)
_, _, w, h = draw.textbbox((0, 0), title, font=font)
draw.text((padding, padding), title, anchor='lt', font=font, fill=(255, 255, 255, 230))
@@ -163,7 +168,7 @@ def caption_image_overlay(srcimage, title, footerLeft, footerMid, footerRight, t _, _, w, h = draw.textbbox((0, 0), footerRight, font=font)
fontsize_right = min(int(fontsize * (((image.size[0]/3)-(padding))/w)), 72)
- font = ImageFont.truetype(textfont, min(fontsize_left, fontsize_mid, fontsize_right))
+ font = get_font(min(fontsize_left, fontsize_mid, fontsize_right))
draw.text((padding, image.size[1]-padding), footerLeft, anchor='ls', font=font, fill=(255, 255, 255, 230))
draw.text((image.size[0]/2, image.size[1]-padding), footerMid, anchor='ms', font=font, fill=(255, 255, 255, 230))
diff --git a/modules/textual_inversion/logging.py b/modules/textual_inversion/logging.py index 734a4b6f..45823eb1 100644 --- a/modules/textual_inversion/logging.py +++ b/modules/textual_inversion/logging.py @@ -2,11 +2,51 @@ import datetime import json
import os
-saved_params_shared = {"model_name", "model_hash", "initial_step", "num_of_dataset_images", "learn_rate", "batch_size", "clip_grad_mode", "clip_grad_value", "gradient_step", "data_root", "log_directory", "training_width", "training_height", "steps", "create_image_every", "template_file", "gradient_step", "latent_sampling_method"}
-saved_params_ti = {"embedding_name", "num_vectors_per_token", "save_embedding_every", "save_image_with_stored_embedding"}
-saved_params_hypernet = {"hypernetwork_name", "layer_structure", "activation_func", "weight_init", "add_layer_norm", "use_dropout", "save_hypernetwork_every"}
+saved_params_shared = {
+ "batch_size",
+ "clip_grad_mode",
+ "clip_grad_value",
+ "create_image_every",
+ "data_root",
+ "gradient_step",
+ "initial_step",
+ "latent_sampling_method",
+ "learn_rate",
+ "log_directory",
+ "model_hash",
+ "model_name",
+ "num_of_dataset_images",
+ "steps",
+ "template_file",
+ "training_height",
+ "training_width",
+}
+saved_params_ti = {
+ "embedding_name",
+ "num_vectors_per_token",
+ "save_embedding_every",
+ "save_image_with_stored_embedding",
+}
+saved_params_hypernet = {
+ "activation_func",
+ "add_layer_norm",
+ "hypernetwork_name",
+ "layer_structure",
+ "save_hypernetwork_every",
+ "use_dropout",
+ "weight_init",
+}
saved_params_all = saved_params_shared | saved_params_ti | saved_params_hypernet
-saved_params_previews = {"preview_prompt", "preview_negative_prompt", "preview_steps", "preview_sampler_index", "preview_cfg_scale", "preview_seed", "preview_width", "preview_height"}
+saved_params_previews = {
+ "preview_cfg_scale",
+ "preview_height",
+ "preview_negative_prompt",
+ "preview_prompt",
+ "preview_sampler_index",
+ "preview_seed",
+ "preview_steps",
+ "preview_width",
+}
def save_settings_to_file(log_directory, all_params):
diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index a009d8e8..dbd856bd 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -7,7 +7,7 @@ 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=0.3, 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=0.15, 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()
@@ -47,7 +47,7 @@ def save_pic_with_caption(image, index, params: PreprocessParams, existing_capti caption += shared.interrogator.generate_caption(image)
if params.process_caption_deepbooru:
- if len(caption) > 0:
+ if caption:
caption += ", "
caption += deepbooru.model.tag_multi(image)
@@ -67,7 +67,7 @@ def save_pic_with_caption(image, index, params: PreprocessParams, existing_capti caption = caption.strip()
- if len(caption) > 0:
+ if caption:
with open(os.path.join(params.dstdir, f"{basename}.txt"), "w", encoding="utf8") as file:
file.write(caption)
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index d489ed1e..bb6f211c 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -1,6 +1,4 @@ import os
-import sys
-import traceback
from collections import namedtuple
import torch
@@ -14,7 +12,7 @@ import numpy as np from PIL import Image, PngImagePlugin
from torch.utils.tensorboard import SummaryWriter
-from modules import shared, devices, sd_hijack, processing, sd_models, images, sd_samplers, sd_hijack_checkpoint
+from modules import shared, devices, sd_hijack, processing, sd_models, images, sd_samplers, sd_hijack_checkpoint, errors
import modules.textual_inversion.dataset
from modules.textual_inversion.learn_schedule import LearnRateScheduler
@@ -120,16 +118,29 @@ class EmbeddingDatabase: self.embedding_dirs.clear()
def register_embedding(self, embedding, model):
- self.word_embeddings[embedding.name] = embedding
-
- ids = model.cond_stage_model.tokenize([embedding.name])[0]
+ return self.register_embedding_by_name(embedding, model, embedding.name)
+ def register_embedding_by_name(self, embedding, model, name):
+ ids = model.cond_stage_model.tokenize([name])[0]
first_id = ids[0]
if first_id not in self.ids_lookup:
self.ids_lookup[first_id] = []
-
- self.ids_lookup[first_id] = sorted(self.ids_lookup[first_id] + [(ids, embedding)], key=lambda x: len(x[0]), reverse=True)
-
+ if name in self.word_embeddings:
+ # remove old one from the lookup list
+ lookup = [x for x in self.ids_lookup[first_id] if x[1].name!=name]
+ else:
+ lookup = self.ids_lookup[first_id]
+ if embedding is not None:
+ lookup += [(ids, embedding)]
+ self.ids_lookup[first_id] = sorted(lookup, key=lambda x: len(x[0]), reverse=True)
+ if embedding is None:
+ # unregister embedding with specified name
+ if name in self.word_embeddings:
+ del self.word_embeddings[name]
+ if len(self.ids_lookup[first_id])==0:
+ del self.ids_lookup[first_id]
+ return None
+ self.word_embeddings[name] = embedding
return embedding
def get_expected_shape(self):
@@ -207,8 +218,7 @@ class EmbeddingDatabase: self.load_from_file(fullfn, fn)
except Exception:
- print(f"Error loading embedding {fn}:", file=sys.stderr)
- print(traceback.format_exc(), file=sys.stderr)
+ errors.report(f"Error loading embedding {fn}", exc_info=True)
continue
def load_textual_inversion_embeddings(self, force_reload=False):
@@ -241,7 +251,7 @@ class EmbeddingDatabase: if self.previously_displayed_embeddings != displayed_embeddings:
self.previously_displayed_embeddings = displayed_embeddings
print(f"Textual inversion embeddings loaded({len(self.word_embeddings)}): {', '.join(self.word_embeddings.keys())}")
- if len(self.skipped_embeddings) > 0:
+ if self.skipped_embeddings:
print(f"Textual inversion embeddings skipped({len(self.skipped_embeddings)}): {', '.join(self.skipped_embeddings.keys())}")
def find_embedding_at_position(self, tokens, offset):
@@ -632,8 +642,7 @@ Last saved image: {html.escape(last_saved_image)}<br/> filename = os.path.join(shared.cmd_opts.embeddings_dir, f'{embedding_name}.pt')
save_embedding(embedding, optimizer, checkpoint, embedding_name, filename, remove_cached_checksum=True)
except Exception:
- print(traceback.format_exc(), file=sys.stderr)
- pass
+ errors.report("Error training embedding", exc_info=True)
finally:
pbar.leave = False
pbar.close()
|