utils.py

import gc
from itertools import islice
import os 
import cv2
import numpy as np
import torch
from diffusers.pipelines.stable_diffusion.safety_checker import \
    StableDiffusionSafetyChecker
from PIL import Image
from transformers import AutoFeatureExtractor

from stable_diffusion.ldm.util import instantiate_from_config

# load safety model
safety_model_id = os.path.join(os.environ.get('NOVEL_CORE_MODULE'), "models/stable-diffusion-safety-checker")
safety_feature_extractor = AutoFeatureExtractor.from_pretrained(safety_model_id)
safety_checker = StableDiffusionSafetyChecker.from_pretrained(safety_model_id)

def chunk(it, size):
    it = iter(it)
    return iter(lambda: tuple(islice(it, size)), ())


def numpy_to_pil(images):
    """
    Convert a numpy image or a batch of images to a PIL image.
    """
    if images.ndim == 3:
        images = images[None, ...]
    images = (images * 255).round().astype("uint8")
    pil_images = [Image.fromarray(image) for image in images]

    return pil_images


def load_model_from_config(config, ckpt, verbose=False):
    print(f"Loading model from {ckpt}")
    pl_sd = torch.load(ckpt, map_location="cpu")
    if "global_step" in pl_sd:
        print(f"Global Step: {pl_sd['global_step']}")
    sd = pl_sd["state_dict"]
    model = instantiate_from_config(config.model)
    m, u = model.load_state_dict(sd, strict=False)
    if len(m) > 0 and verbose:
        print("missing keys:")
        print(m)
    if len(u) > 0 and verbose:
        print("unexpected keys:")
        print(u)

    model.cuda()
    model.eval()
    return model


def put_watermark(img, wm_encoder=None):
    if wm_encoder is not None:
        img = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
        img = wm_encoder.encode(img, 'dwtDct')
        img = Image.fromarray(img[:, :, ::-1])
    return img


def load_replacement(x):
    try:
        hwc = x.shape
        y = Image.open("assets/rick.jpeg").convert("RGB").resize((hwc[1], hwc[0]))
        y = (np.array(y)/255.0).astype(x.dtype)
        assert y.shape == x.shape
        return y
    except Exception:
        return x


def check_safety(x_image, allow_nsfw):
    print("================ allow_nsfw_concept: {} =================".format(allow_nsfw))
    if allow_nsfw:
        return x_image, None
    safety_checker_input = safety_feature_extractor(numpy_to_pil(x_image), return_tensors="pt")
    x_checked_image, has_nsfw_concept = safety_checker(images=x_image, clip_input=safety_checker_input.pixel_values)
    assert x_checked_image.shape[0] == len(has_nsfw_concept)
    for i in range(len(has_nsfw_concept)):
        x_checked_image[i] = load_replacement(x_checked_image[i])
    return x_checked_image, has_nsfw_concept


def free_memory():
    gc.collect()
    torch.cuda.empty_cache()