diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py index acc4ce597ee9ee969e2019eed8a66c7ce9df7753..bcf772d2fc97473cce23909b4bc9d95ceeca2359 100644 --- a/modules/textual_inversion/dataset.py +++ b/modules/textual_inversion/dataset.py @@ -15,13 +15,12 @@ re_tag = re.compile(r"[a-zA-Z][_\w\d()]+") class PersonalizedBase(Dataset): - def __init__(self, data_root, size, 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): self.placeholder_token = placeholder_token - self.size = size - self.width = size - self.height = size + self.width = width + self.height = height self.flip = transforms.RandomHorizontalFlip(p=flip_p) self.dataset = [] diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index b3de6fd7eeff9b6b1c41efdff4ff8c466fad28a5..d7efdef29db4c5313101b603a60c83440e150cf6 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_size, process_flip, process_split, process_caption): - size = process_size +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_size, process_flip, process_spl 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 769682ea5083649f39b24db5d8cf9d76bb964afb..5965c5a0612838965294928283249057acdef515 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -6,7 +6,6 @@ import torch import tqdm import html import datetime -import math from modules import shared, devices, sd_hijack, processing, sd_models @@ -157,7 +156,7 @@ def create_embedding(name, num_vectors_per_token, init_text='*'): return fn -def train_embedding(embedding_name, learn_rate, data_root, log_directory, training_size, steps, num_repeats, create_image_every, save_embedding_every, template_file): +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..." @@ -183,7 +182,7 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini 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=training_size, repeats=num_repeats, 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 @@ -227,7 +226,7 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini loss.backward() optimizer.step() - epoch_num = math.floor(embedding.step / epoch_len) + 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}") @@ -243,8 +242,8 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini sd_model=shared.sd_model, prompt=text, steps=20, - height=training_size, - width=training_size, + height=training_height, + width=training_width, do_not_save_grid=True, do_not_save_samples=True, ) diff --git a/modules/ui.py b/modules/ui.py index f821fd8db20fd72af4391f42993085d6d6fe24ea..8c06ad7cc84b7b8520eba24e3976d92574bfea18 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -1029,7 +1029,8 @@ def create_ui(wrap_gradio_gpu_call): process_src = gr.Textbox(label='Source directory') process_dst = gr.Textbox(label='Destination directory') - process_size = gr.Slider(minimum=64, maximum=2048, step=64, label="Size (width and height)", value=512) + process_width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512) + process_height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512) with gr.Row(): process_flip = gr.Checkbox(label='Create flipped copies') @@ -1050,7 +1051,8 @@ def create_ui(wrap_gradio_gpu_call): dataset_directory = gr.Textbox(label='Dataset directory', placeholder="Path to directory with input images") log_directory = gr.Textbox(label='Log directory', placeholder="Path to directory where to write outputs", value="textual_inversion") template_file = gr.Textbox(label='Prompt template file', value=os.path.join(script_path, "textual_inversion_templates", "style_filewords.txt")) - training_size = gr.Slider(minimum=64, maximum=2048, step=64, label="Size (width and height)", value=512) + training_width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512) + training_height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512) steps = gr.Number(label='Max steps', value=100000, precision=0) num_repeats = gr.Number(label='Number of repeats for a single input image per epoch', value=100, precision=0) create_image_every = gr.Number(label='Save an image to log directory every N steps, 0 to disable', value=500, precision=0) @@ -1095,7 +1097,8 @@ def create_ui(wrap_gradio_gpu_call): inputs=[ process_src, process_dst, - process_size, + process_width, + process_height, process_flip, process_split, process_caption, @@ -1114,7 +1117,8 @@ def create_ui(wrap_gradio_gpu_call): learn_rate, dataset_directory, log_directory, - training_size, + training_width, + training_height, steps, num_repeats, create_image_every,