Merge branch 'master' into embed-embeddings-in-images

3 files changed, 22 insertions, 14 deletions

diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py
index 7c44ea5b..bcf772d2 100644
--- a/modules/textual_inversion/dataset.py
+++ b/modules/textual_inversion/dataset.py
@@ -15,11 +15,10 @@ re_tag = re.compile(r"[a-zA-Z][_\w\d()]+")
 

 

 class PersonalizedBase(Dataset):

-    def __init__(self, data_root, size=None, repeats=100, flip_p=0.5, placeholder_token="*", width=512, height=512, 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):

 

         self.placeholder_token = placeholder_token

 

-        self.size = size

         self.width = width

         self.height = height

         self.flip = transforms.RandomHorizontalFlip(p=flip_p)

diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py
index f1c002a2..d7efdef2 100644
--- a/modules/textual_inversion/preprocess.py
+++ b/modules/textual_inversion/preprocess.py
@@ -7,8 +7,9 @@ import tqdm
 from modules import shared, images

 

 

-def preprocess(process_src, process_dst, process_flip, process_split, process_caption):

-    size = 512

+def preprocess(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption):

+    width = process_width

+    height = process_height

     src = os.path.abspath(process_src)

     dst = os.path.abspath(process_dst)

 

@@ -55,23 +56,23 @@ def preprocess(process_src, process_dst, process_flip, process_split, process_ca
         is_wide = ratio < 1 / 1.35

 

         if process_split and is_tall:

-            img = img.resize((size, size * img.height // img.width))

+            img = img.resize((width, height * img.height // img.width))

 

-            top = img.crop((0, 0, size, size))

+            top = img.crop((0, 0, width, height))

             save_pic(top, index)

 

-            bot = img.crop((0, img.height - size, size, img.height))

+            bot = img.crop((0, img.height - height, width, img.height))

             save_pic(bot, index)

         elif process_split and is_wide:

-            img = img.resize((size * img.width // img.height, size))

+            img = img.resize((width * img.width // img.height, height))

 

-            left = img.crop((0, 0, size, size))

+            left = img.crop((0, 0, width, height))

             save_pic(left, index)

 

-            right = img.crop((img.width - size, 0, img.width, size))

+            right = img.crop((img.width - width, 0, img.width, height))

             save_pic(right, index)

         else:

-            img = images.resize_image(1, img, size, size)

+            img = images.resize_image(1, img, width, height)

             save_pic(img, index)

 

         shared.state.nextjob()

diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py
index 9a18ee5c..7a24192e 100644
--- a/modules/textual_inversion/textual_inversion.py
+++ b/modules/textual_inversion/textual_inversion.py
@@ -190,7 +190,7 @@ def create_embedding(name, num_vectors_per_token, init_text='*'):
     return fn

 

 

-def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps, create_image_every, save_embedding_every, template_file, save_image_with_stored_embedding):

+def train_embedding(embedding_name, learn_rate, data_root, log_directory, training_width, training_height, steps, num_repeats, create_image_every, save_embedding_every, template_file):

     assert embedding_name, 'embedding not selected'

 

     shared.state.textinfo = "Initializing textual inversion training..."

@@ -222,7 +222,7 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
 

     shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."

     with torch.autocast("cuda"):

-        ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, size=512, placeholder_token=embedding_name, model=shared.sd_model, device=devices.device, template_file=template_file)

+        ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=num_repeats, placeholder_token=embedding_name, model=shared.sd_model, device=devices.device, template_file=template_file)

 

     hijack = sd_hijack.model_hijack

 

@@ -240,6 +240,9 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
     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

+

     pbar = tqdm.tqdm(enumerate(ds), total=steps-ititial_step)

     for i, (x, text) in pbar:

         embedding.step = i + ititial_step

@@ -263,7 +266,10 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
             loss.backward()

             optimizer.step()

 

-        pbar.set_description(f"loss: {losses.mean():.7f}")

+        epoch_num = embedding.step // epoch_len

+        epoch_step = embedding.step - (epoch_num * epoch_len) + 1

+

+        pbar.set_description(f"[Epoch {epoch_num}: {epoch_step}/{epoch_len}]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')

@@ -276,6 +282,8 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
                 sd_model=shared.sd_model,

                 prompt=text,

                 steps=20,

+				height=training_height,

+				width=training_width,

                 do_not_save_grid=True,

                 do_not_save_samples=True,

             )