2023-03-26 07:39:09 +02:00
|
|
|
import os
|
|
|
|
|
2024-08-12 05:02:55 +02:00
|
|
|
import cv2
|
2023-03-26 07:39:09 +02:00
|
|
|
import torch
|
2024-08-12 05:02:55 +02:00
|
|
|
from torchvision.transforms.functional import normalize
|
2023-03-26 07:39:09 +02:00
|
|
|
from torch.hub import get_dir
|
|
|
|
|
2024-08-12 05:02:55 +02:00
|
|
|
from .facexlib.utils.face_restoration_helper import FaceRestoreHelper
|
|
|
|
from .gfpgan.archs.gfpganv1_clean_arch import GFPGANv1Clean
|
|
|
|
from .basicsr.img_util import img2tensor, tensor2img
|
2023-03-26 07:39:09 +02:00
|
|
|
|
2024-08-12 05:02:55 +02:00
|
|
|
|
|
|
|
class MyGFPGANer:
|
2023-03-26 07:39:09 +02:00
|
|
|
"""Helper for restoration with GFPGAN.
|
|
|
|
|
|
|
|
It will detect and crop faces, and then resize the faces to 512x512.
|
|
|
|
GFPGAN is used to restored the resized faces.
|
|
|
|
The background is upsampled with the bg_upsampler.
|
|
|
|
Finally, the faces will be pasted back to the upsample background image.
|
|
|
|
|
|
|
|
Args:
|
|
|
|
model_path (str): The path to the GFPGAN model. It can be urls (will first download it automatically).
|
|
|
|
upscale (float): The upscale of the final output. Default: 2.
|
|
|
|
arch (str): The GFPGAN architecture. Option: clean | original. Default: clean.
|
|
|
|
channel_multiplier (int): Channel multiplier for large networks of StyleGAN2. Default: 2.
|
|
|
|
bg_upsampler (nn.Module): The upsampler for the background. Default: None.
|
|
|
|
"""
|
|
|
|
|
|
|
|
def __init__(
|
|
|
|
self,
|
|
|
|
model_path,
|
|
|
|
upscale=2,
|
|
|
|
arch="clean",
|
|
|
|
channel_multiplier=2,
|
|
|
|
bg_upsampler=None,
|
|
|
|
device=None,
|
|
|
|
):
|
|
|
|
self.upscale = upscale
|
|
|
|
self.bg_upsampler = bg_upsampler
|
|
|
|
|
|
|
|
# initialize model
|
|
|
|
self.device = (
|
|
|
|
torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
|
|
|
if device is None
|
|
|
|
else device
|
|
|
|
)
|
|
|
|
# initialize the GFP-GAN
|
|
|
|
if arch == "clean":
|
|
|
|
self.gfpgan = GFPGANv1Clean(
|
|
|
|
out_size=512,
|
|
|
|
num_style_feat=512,
|
|
|
|
channel_multiplier=channel_multiplier,
|
|
|
|
decoder_load_path=None,
|
|
|
|
fix_decoder=False,
|
|
|
|
num_mlp=8,
|
|
|
|
input_is_latent=True,
|
|
|
|
different_w=True,
|
|
|
|
narrow=1,
|
|
|
|
sft_half=True,
|
|
|
|
)
|
|
|
|
elif arch == "RestoreFormer":
|
2024-08-12 05:02:55 +02:00
|
|
|
from .gfpgan.archs.restoreformer_arch import RestoreFormer
|
2023-03-26 07:39:09 +02:00
|
|
|
|
|
|
|
self.gfpgan = RestoreFormer()
|
|
|
|
|
|
|
|
hub_dir = get_dir()
|
|
|
|
model_dir = os.path.join(hub_dir, "checkpoints")
|
|
|
|
|
|
|
|
# initialize face helper
|
|
|
|
self.face_helper = FaceRestoreHelper(
|
|
|
|
upscale,
|
|
|
|
face_size=512,
|
|
|
|
crop_ratio=(1, 1),
|
|
|
|
det_model="retinaface_resnet50",
|
|
|
|
save_ext="png",
|
|
|
|
use_parse=True,
|
|
|
|
device=self.device,
|
|
|
|
model_rootpath=model_dir,
|
|
|
|
)
|
|
|
|
|
|
|
|
loadnet = torch.load(model_path)
|
|
|
|
if "params_ema" in loadnet:
|
|
|
|
keyname = "params_ema"
|
|
|
|
else:
|
|
|
|
keyname = "params"
|
|
|
|
self.gfpgan.load_state_dict(loadnet[keyname], strict=True)
|
|
|
|
self.gfpgan.eval()
|
|
|
|
self.gfpgan = self.gfpgan.to(self.device)
|
2024-08-12 05:02:55 +02:00
|
|
|
|
|
|
|
@torch.no_grad()
|
|
|
|
def enhance(
|
|
|
|
self,
|
|
|
|
img,
|
|
|
|
has_aligned=False,
|
|
|
|
only_center_face=False,
|
|
|
|
paste_back=True,
|
|
|
|
weight=0.5,
|
|
|
|
):
|
|
|
|
self.face_helper.clean_all()
|
|
|
|
|
|
|
|
if has_aligned: # the inputs are already aligned
|
|
|
|
img = cv2.resize(img, (512, 512))
|
|
|
|
self.face_helper.cropped_faces = [img]
|
|
|
|
else:
|
|
|
|
self.face_helper.read_image(img)
|
|
|
|
# get face landmarks for each face
|
|
|
|
self.face_helper.get_face_landmarks_5(
|
|
|
|
only_center_face=only_center_face, eye_dist_threshold=5
|
|
|
|
)
|
|
|
|
# eye_dist_threshold=5: skip faces whose eye distance is smaller than 5 pixels
|
|
|
|
# TODO: even with eye_dist_threshold, it will still introduce wrong detections and restorations.
|
|
|
|
# align and warp each face
|
|
|
|
self.face_helper.align_warp_face()
|
|
|
|
|
|
|
|
# face restoration
|
|
|
|
for cropped_face in self.face_helper.cropped_faces:
|
|
|
|
# prepare data
|
|
|
|
cropped_face_t = img2tensor(
|
|
|
|
cropped_face / 255.0, bgr2rgb=True, float32=True
|
|
|
|
)
|
|
|
|
normalize(cropped_face_t, (0.5, 0.5, 0.5), (0.5, 0.5, 0.5), inplace=True)
|
|
|
|
cropped_face_t = cropped_face_t.unsqueeze(0).to(self.device)
|
|
|
|
|
|
|
|
try:
|
|
|
|
output = self.gfpgan(cropped_face_t, return_rgb=False, weight=weight)[0]
|
|
|
|
# convert to image
|
|
|
|
restored_face = tensor2img(
|
|
|
|
output.squeeze(0), rgb2bgr=True, min_max=(-1, 1)
|
|
|
|
)
|
|
|
|
except RuntimeError as error:
|
|
|
|
print(f"\tFailed inference for GFPGAN: {error}.")
|
|
|
|
restored_face = cropped_face
|
|
|
|
|
|
|
|
restored_face = restored_face.astype("uint8")
|
|
|
|
self.face_helper.add_restored_face(restored_face)
|
|
|
|
|
|
|
|
if not has_aligned and paste_back:
|
|
|
|
# upsample the background
|
|
|
|
if self.bg_upsampler is not None:
|
|
|
|
# Now only support RealESRGAN for upsampling background
|
|
|
|
bg_img = self.bg_upsampler.enhance(img, outscale=self.upscale)[0]
|
|
|
|
else:
|
|
|
|
bg_img = None
|
|
|
|
|
|
|
|
self.face_helper.get_inverse_affine(None)
|
|
|
|
# paste each restored face to the input image
|
|
|
|
restored_img = self.face_helper.paste_faces_to_input_image(
|
|
|
|
upsample_img=bg_img
|
|
|
|
)
|
|
|
|
return (
|
|
|
|
self.face_helper.cropped_faces,
|
|
|
|
self.face_helper.restored_faces,
|
|
|
|
restored_img,
|
|
|
|
)
|
|
|
|
else:
|
|
|
|
return self.face_helper.cropped_faces, self.face_helper.restored_faces, None
|