app.py

import os

os.system("git clone --recursive https://github.com/JD-P/cloob-latent-diffusion")
os.system("cd cloob-latent-diffusion;pip install omegaconf pillow pytorch-lightning einops wandb ftfy regex ./CLIP")

import argparse
from functools import partial
from pathlib import Path
import sys
sys.path.append('./cloob-latent-diffusion')
sys.path.append('./cloob-latent-diffusion/cloob-training')
sys.path.append('./cloob-latent-diffusion/latent-diffusion')
sys.path.append('./cloob-latent-diffusion/taming-transformers')
sys.path.append('./cloob-latent-diffusion/v-diffusion-pytorch')
from omegaconf import OmegaConf
from PIL import Image
import torch
from torch import nn
from torch.nn import functional as F
from torchvision import transforms
from torchvision.transforms import functional as TF
from tqdm import trange
from CLIP import clip
from cloob_training import model_pt, pretrained
import ldm.models.autoencoder
from diffusion import sampling, utils
import train_latent_diffusion as train
from huggingface_hub import hf_hub_url, cached_download
import random

# Download the model files
checkpoint = cached_download(hf_hub_url("huggan/distill-ccld-wa", filename="model_student.ckpt"))
ae_model_path = cached_download(hf_hub_url("huggan/ccld_wa", filename="ae_model.ckpt"))
ae_config_path = cached_download(hf_hub_url("huggan/ccld_wa", filename="ae_model.yaml"))

# Define a few utility functions


def parse_prompt(prompt, default_weight=3.):
    if prompt.startswith('http://') or prompt.startswith('https://'):
        vals = prompt.rsplit(':', 2)
        vals = [vals[0] + ':' + vals[1], *vals[2:]]
    else:
        vals = prompt.rsplit(':', 1)
    vals = vals + ['', default_weight][len(vals):]
    return vals[0], float(vals[1])