diff options
Diffstat (limited to 'modules/textual_inversion')
| -rw-r--r-- | modules/textual_inversion/dataset.py | 36 | ||||
| -rw-r--r-- | modules/textual_inversion/learn_schedule.py | 34 | ||||
| -rw-r--r-- | modules/textual_inversion/preprocess.py | 27 | ||||
| -rw-r--r-- | modules/textual_inversion/textual_inversion.py | 29 | ||||
| -rw-r--r-- | modules/textual_inversion/ui.py | 3 |
5 files changed, 103 insertions, 26 deletions
diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py index bcf772d2..f61f40d3 100644 --- a/modules/textual_inversion/dataset.py +++ b/modules/textual_inversion/dataset.py @@ -8,14 +8,14 @@ from torchvision import transforms import random
import tqdm
-from modules import devices
+from modules import devices, shared
import re
re_tag = re.compile(r"[a-zA-Z][_\w\d()]+")
class PersonalizedBase(Dataset):
- def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, device=None, template_file=None):
+ def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, device=None, template_file=None, include_cond=False):
self.placeholder_token = placeholder_token
@@ -32,12 +32,15 @@ class PersonalizedBase(Dataset): assert data_root, 'dataset directory not specified'
+ cond_model = shared.sd_model.cond_stage_model
+
self.image_paths = [os.path.join(data_root, file_path) for file_path in os.listdir(data_root)]
print("Preparing dataset...")
for path in tqdm.tqdm(self.image_paths):
- image = Image.open(path)
- image = image.convert('RGB')
- image = image.resize((self.width, self.height), PIL.Image.BICUBIC)
+ try:
+ image = Image.open(path).convert('RGB').resize((self.width, self.height), PIL.Image.BICUBIC)
+ except Exception:
+ continue
filename = os.path.basename(path)
filename_tokens = os.path.splitext(filename)[0]
@@ -52,7 +55,13 @@ class PersonalizedBase(Dataset): init_latent = model.get_first_stage_encoding(model.encode_first_stage(torchdata.unsqueeze(dim=0))).squeeze()
init_latent = init_latent.to(devices.cpu)
- self.dataset.append((init_latent, filename_tokens))
+ if include_cond:
+ text = self.create_text(filename_tokens)
+ cond = cond_model([text]).to(devices.cpu)
+ else:
+ cond = None
+
+ self.dataset.append((init_latent, filename_tokens, cond))
self.length = len(self.dataset) * repeats
@@ -63,6 +72,12 @@ class PersonalizedBase(Dataset): def shuffle(self):
self.indexes = self.initial_indexes[torch.randperm(self.initial_indexes.shape[0])]
+ def create_text(self, filename_tokens):
+ text = random.choice(self.lines)
+ text = text.replace("[name]", self.placeholder_token)
+ text = text.replace("[filewords]", ' '.join(filename_tokens))
+ return text
+
def __len__(self):
return self.length
@@ -71,10 +86,7 @@ class PersonalizedBase(Dataset): self.shuffle()
index = self.indexes[i % len(self.indexes)]
- x, filename_tokens = self.dataset[index]
-
- text = random.choice(self.lines)
- text = text.replace("[name]", self.placeholder_token)
- text = text.replace("[filewords]", ' '.join(filename_tokens))
+ x, filename_tokens, cond = self.dataset[index]
- return x, text
+ text = self.create_text(filename_tokens)
+ return x, text, cond
diff --git a/modules/textual_inversion/learn_schedule.py b/modules/textual_inversion/learn_schedule.py new file mode 100644 index 00000000..db720271 --- /dev/null +++ b/modules/textual_inversion/learn_schedule.py @@ -0,0 +1,34 @@ +
+class LearnSchedule:
+ def __init__(self, learn_rate, max_steps, cur_step=0):
+ pairs = learn_rate.split(',')
+ self.rates = []
+ self.it = 0
+ self.maxit = 0
+ for i, pair in enumerate(pairs):
+ tmp = pair.split(':')
+ if len(tmp) == 2:
+ step = int(tmp[1])
+ if step > cur_step:
+ self.rates.append((float(tmp[0]), min(step, max_steps)))
+ self.maxit += 1
+ if step > max_steps:
+ return
+ elif step == -1:
+ self.rates.append((float(tmp[0]), max_steps))
+ self.maxit += 1
+ return
+ else:
+ self.rates.append((float(tmp[0]), max_steps))
+ self.maxit += 1
+ return
+
+ def __iter__(self):
+ return self
+
+ def __next__(self):
+ if self.it < self.maxit:
+ self.it += 1
+ return self.rates[self.it - 1]
+ else:
+ raise StopIteration
diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index d7efdef2..113cecf1 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -3,11 +3,14 @@ from PIL import Image, ImageOps import platform
import sys
import tqdm
+import time
from modules import shared, images
+from modules.shared import opts, cmd_opts
+if cmd_opts.deepdanbooru:
+ import modules.deepbooru as deepbooru
-
-def preprocess(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption):
+def preprocess(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru=False):
width = process_width
height = process_height
src = os.path.abspath(process_src)
@@ -25,10 +28,21 @@ def preprocess(process_src, process_dst, process_width, process_height, process_ if process_caption:
shared.interrogator.load()
+ if process_caption_deepbooru:
+ deepbooru.create_deepbooru_process(opts.interrogate_deepbooru_score_threshold, opts.deepbooru_sort_alpha)
+
def save_pic_with_caption(image, index):
if process_caption:
caption = "-" + shared.interrogator.generate_caption(image)
caption = sanitize_caption(os.path.join(dst, f"{index:05}-{subindex[0]}"), caption, ".png")
+ elif process_caption_deepbooru:
+ shared.deepbooru_process_return["value"] = -1
+ shared.deepbooru_process_queue.put(image)
+ while shared.deepbooru_process_return["value"] == -1:
+ time.sleep(0.2)
+ caption = "-" + shared.deepbooru_process_return["value"]
+ caption = sanitize_caption(os.path.join(dst, f"{index:05}-{subindex[0]}"), caption, ".png")
+ shared.deepbooru_process_return["value"] = -1
else:
caption = filename
caption = os.path.splitext(caption)[0]
@@ -46,7 +60,10 @@ def preprocess(process_src, process_dst, process_width, process_height, process_ for index, imagefile in enumerate(tqdm.tqdm(files)):
subindex = [0]
filename = os.path.join(src, imagefile)
- img = Image.open(filename).convert("RGB")
+ try:
+ img = Image.open(filename).convert("RGB")
+ except Exception:
+ continue
if shared.state.interrupted:
break
@@ -80,6 +97,10 @@ def preprocess(process_src, process_dst, process_width, process_height, process_ if process_caption:
shared.interrogator.send_blip_to_ram()
+ if process_caption_deepbooru:
+ deepbooru.release_process()
+
+
def sanitize_caption(base_path, original_caption, suffix):
operating_system = platform.system().lower()
if (operating_system == "windows"):
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index b072d745..c5153e4a 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -11,6 +11,7 @@ from PIL import Image, PngImagePlugin from modules import shared, devices, sd_hijack, processing, sd_models
import modules.textual_inversion.dataset
+from modules.textual_inversion.learn_schedule import LearnSchedule
from modules.textual_inversion.image_embedding import (embedding_to_b64, embedding_from_b64,
insert_image_data_embed, extract_image_data_embed,
@@ -211,8 +212,6 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini embedding = hijack.embedding_db.word_embeddings[embedding_name]
embedding.vec.requires_grad = True
- optimizer = torch.optim.AdamW([embedding.vec], lr=learn_rate)
-
losses = torch.zeros((32,))
last_saved_file = "<none>"
@@ -222,15 +221,24 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini if ititial_step > steps:
return embedding, filename
- tr_img_len = len([os.path.join(data_root, file_path) for file_path in os.listdir(data_root)])
- epoch_len = (tr_img_len * num_repeats) + tr_img_len
+ schedules = iter(LearnSchedule(learn_rate, steps, ititial_step))
+ (learn_rate, end_step) = next(schedules)
+ print(f'Training at rate of {learn_rate} until step {end_step}')
+
+ optimizer = torch.optim.AdamW([embedding.vec], lr=learn_rate)
pbar = tqdm.tqdm(enumerate(ds), total=steps-ititial_step)
- for i, (x, text) in pbar:
+ for i, (x, text, _) in pbar:
embedding.step = i + ititial_step
- if embedding.step > steps:
- break
+ if embedding.step > end_step:
+ try:
+ (learn_rate, end_step) = next(schedules)
+ except:
+ break
+ tqdm.tqdm.write(f'Training at rate of {learn_rate} until step {end_step}')
+ for pg in optimizer.param_groups:
+ pg['lr'] = learn_rate
if shared.state.interrupted:
break
@@ -248,10 +256,10 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini loss.backward()
optimizer.step()
- epoch_num = embedding.step // epoch_len
- epoch_step = embedding.step - (epoch_num * epoch_len) + 1
+ epoch_num = embedding.step // len(ds)
+ epoch_step = embedding.step - (epoch_num * len(ds)) + 1
- pbar.set_description(f"[Epoch {epoch_num}: {epoch_step}/{epoch_len}]loss: {losses.mean():.7f}")
+ pbar.set_description(f"[Epoch {epoch_num}: {epoch_step}/{len(ds)}]loss: {losses.mean():.7f}")
if embedding.step > 0 and embedding_dir is not None and embedding.step % save_embedding_every == 0:
last_saved_file = os.path.join(embedding_dir, f'{embedding_name}-{embedding.step}.pt')
@@ -320,4 +328,3 @@ Last saved image: {html.escape(last_saved_image)}<br/> embedding.save(filename)
return embedding, filename
-
diff --git a/modules/textual_inversion/ui.py b/modules/textual_inversion/ui.py index c57de1f9..36881e7a 100644 --- a/modules/textual_inversion/ui.py +++ b/modules/textual_inversion/ui.py @@ -22,6 +22,9 @@ def preprocess(*args): def train_embedding(*args):
+
+ assert not shared.cmd_opts.lowvram, 'Training models with lowvram not possible'
+
try:
sd_hijack.undo_optimizations()
|