preprocessing for textual inversion added

modules/textual_inversion/preprocess.py

@@ -0,0 +1,75 @@
+import os
+from PIL import Image, ImageOps
+import tqdm
+
+from modules import shared, images
+
+
+def preprocess(process_src, process_dst, process_flip, process_split, process_caption):
+    size = 512
+    src = os.path.abspath(process_src)
+    dst = os.path.abspath(process_dst)
+
+    assert src != dst, 'same directory specified as source and desitnation'
+
+    os.makedirs(dst, exist_ok=True)
+
+    files = os.listdir(src)
+
+    shared.state.textinfo = "Preprocessing..."
+    shared.state.job_count = len(files)
+
+    if process_caption:
+        shared.interrogator.load()
+
+    def save_pic_with_caption(image, index):
+        if process_caption:
+            caption = "-" + shared.interrogator.generate_caption(image)
+        else:
+            caption = ""
+
+        image.save(os.path.join(dst, f"{index:05}-{subindex[0]}{caption}.png"))
+        subindex[0] += 1
+
+    def save_pic(image, index):
+        save_pic_with_caption(image, index)
+
+        if process_flip:
+            save_pic_with_caption(ImageOps.mirror(image), index)
+
+    for index, imagefile in enumerate(tqdm.tqdm(files)):
+        subindex = [0]
+        filename = os.path.join(src, imagefile)
+        img = Image.open(filename).convert("RGB")
+
+        if shared.state.interrupted:
+            break
+
+        ratio = img.height / img.width
+        is_tall = ratio > 1.35
+        is_wide = ratio < 1 / 1.35
+
+        if process_split and is_tall:
+            img = img.resize((size, size * img.height // img.width))
+
+            top = img.crop((0, 0, size, size))
+            save_pic(top, index)
+
+            bot = img.crop((0, img.height - size, size, img.height))
+            save_pic(bot, index)
+        elif process_split and is_wide:
+            img = img.resize((size * img.width // img.height, size))
+
+            left = img.crop((0, 0, size, size))
+            save_pic(left, index)
+
+            right = img.crop((img.width - size, 0, img.width, size))
+            save_pic(right, index)
+        else:
+            img = images.resize_image(1, img, size, size)
+            save_pic(img, index)
+
+        shared.state.nextjob()
+
+    if process_caption:
+        shared.interrogator.send_blip_to_ram()

modules/textual_inversion/textual_inversion.py

@@ -7,6 +7,7 @@ import tqdm
 import html
 import datetime
 
+
 from modules import shared, devices, sd_hijack, processing, sd_models
 import modules.textual_inversion.dataset
 

modules/textual_inversion/ui.py

@@ -2,24 +2,31 @@ import html
 
 import gradio as gr
 
-import modules.textual_inversion.textual_inversion as ti
+import modules.textual_inversion.textual_inversion
+import modules.textual_inversion.preprocess
 from modules import sd_hijack, shared
 
 
 def create_embedding(name, initialization_text, nvpt):
-    filename = ti.create_embedding(name, nvpt, init_text=initialization_text)
+    filename = modules.textual_inversion.textual_inversion.create_embedding(name, nvpt, init_text=initialization_text)
 
     sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings()
 
     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 "Preprocessing finished.", ""
+
+
 def train_embedding(*args):
 
     try:
         sd_hijack.undo_optimizations()
 
-        embedding, filename = ti.train_embedding(*args)
+        embedding, filename = modules.textual_inversion.textual_inversion.train_embedding(*args)
 
         res = f"""
 Training {'interrupted' if shared.state.interrupted else 'finished'} at {embedding.step} steps.
@@ -30,3 +37,4 @@ Embedding saved to {html.escape(filename)}
         raise
     finally:
         sd_hijack.apply_optimizations()
+