ui.py import html import gradio as gr import modules.textual_inversion.textual_inversion import modules.textual_inversion.preprocess from modules import sd_hijack, shared def create_embedding(name, initialization_text, nvpt, overwrite_old): filename = modules.textual_inversion.textual_inversion.create_embedding(name, nvpt, overwrite_old, init_text=initialization_text) sd_hijack.model_hijack.embe..

textual_inversion.py import os import sys import traceback from collections import namedtuple import torch import tqdm import html import datetime import csv import safetensors.torch 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_checkp..

preprocess.pyimport os from PIL import Image, ImageOps import math import tqdm 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_th..

learn_schedule.py import tqdm class LearnScheduleIterator: def __init__(self, learn_rate, max_steps, cur_step=0): """ specify learn_rate as "0.001:100, 0.00001:1000, 1e-5:10000" to have lr of 0.001 until step 100, 0.00001 until 1000, and 1e-5 until 10000 """ pairs = learn_rate.split(',') self.rates = [] self.it = 0 self.maxit = 0 try: for pair in pairs: if not pair.strip(): continue tmp = pair.s..

image_embedding.py import base64 import json import numpy as np import zlib from PIL import Image, ImageDraw, ImageFont import torch class EmbeddingEncoder(json.JSONEncoder): def default(self, obj): if isinstance(obj, torch.Tensor): return {'TORCHTENSOR': obj.cpu().detach().numpy().tolist()} return json.JSONEncoder.default(self, obj) class EmbeddingDecoder(json.JSONDecoder): def __init__(self, *..

dataset.py import os import numpy as np import PIL import torch from PIL import Image from torch.utils.data import Dataset, DataLoader, Sampler from torchvision import transforms from collections import defaultdict from random import shuffle, choices import random import tqdm from modules import devices, shared import re from ldm.modules.distributions.distributions import DiagonalGaussianDistrib..

autocrop.py import cv2 import requests import os import numpy as np from PIL import ImageDraw GREEN = "#0F0" BLUE = "#00F" RED = "#F00" def crop_image(im, settings): """ Intelligently crop an image to the subject matter """ scale_by = 1 if is_landscape(im.width, im.height): scale_by = settings.crop_height / im.height elif is_portrait(im.width, im.height): scale_by = settings.crop_width / im.widt..

uni_pc.py import torch import math import tqdm class NoiseScheduleVP: def __init__( self, schedule='discrete', betas=None, alphas_cumprod=None, continuous_beta_0=0.1, continuous_beta_1=20., ): """Create a wrapper class for the forward SDE (VP type). *** Update: We support discrete-time diffusion models by implementing a picewise linear interpolation for log_alpha_t. We recommend to use schedule=..

sampler.py """SAMPLING ONLY.""" import torch from .uni_pc import NoiseScheduleVP, model_wrapper, UniPC from modules import shared, devices class UniPCSampler(object): def __init__(self, model, **kwargs): super().__init__() self.model = model to_torch = lambda x: x.clone().detach().to(torch.float32).to(model.device) self.before_sample = None self.after_sample = None self.register_buffer('alphas_c..

ddpm_edit.py """ wild mixture of https://github.com/lucidrains/denoising-diffusion-pytorch/blob/7706bdfc6f527f58d33f84b7b522e61e6e3164b3/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py https://github.com/openai/improved-diffusion/blob/e94489283bb876ac1477d5dd7709bbbd2d9902ce/improved_diffusion/gaussian_diffusion.py https://github.com/CompVis/taming-transformers -- merci """ # File mod..