app.py

import os
import cv2
import torch
import gradio as gr
from torchvision.transforms.functional import normalize
from basicsr.archs.rrdbnet_arch import RRDBNet
from basicsr.utils import imwrite, img2tensor, tensor2img
from basicsr.utils.misc import gpu_is_available, get_device
from basicsr.utils.realesrgan_utils import RealESRGANer
from basicsr.utils.registry import ARCH_REGISTRY

from facelib.utils.face_restoration_helper import FaceRestoreHelper
from facelib.utils.misc import is_gray


def imread(img_path):
    img = cv2.imread(img_path)
    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    return img


def set_realesrgan():
    half = True if gpu_is_available() else False
    model = RRDBNet(
        num_in_ch=3,
        num_out_ch=3,
        num_feat=64,
        num_block=23,
        num_grow_ch=32,
        scale=2,
    )
    upsampler = RealESRGANer(
        scale=2,
        model_path="CodeFormer/weights/realesrgan/RealESRGAN_x2plus.pth",
        model=model,
        tile=400,
        tile_pad=40,
        pre_pad=0,
        half=half,
    )
    return upsampler


upsampler = set_realesrgan()

device = get_device()
codeformer_net = ARCH_REGISTRY.get("CodeFormer")(
    dim_embd=512,
    codebook_size=1024,
    n_head=8,
    n_layers=9,
    connect_list=["32", "64", "128", "256"],
).to(device)
ckpt_path = "CodeFormer/weights/CodeFormer/codeformer.pth"
checkpoint = torch.load(ckpt_path)["params_ema"]
codeformer_net.load_state_dict(checkpoint)
codeformer_net.eval()

os.makedirs('output', exist_ok=True)


def inference(image, background_enhance, face_upsample, upscale, codeformer_fidelity):
    """Run a single prediction on the model"""
    try:  # global try
        # take the default setting for the demo
        has_aligned = False
        only_center_face = False
        draw_box = False
        detection_model = "retinaface_resnet50"

        img = cv2.imread(str(image), cv2.IMREAD_COLOR)

        upscale = int(upscale)
        if upscale > 4:
            upscale = 4
        if upscale > 2 and max(img.shape[:2]) > 1000:
            upscale = 2
        if max(img.shape[:2]) > 1500:
            upscale = 1
            background_enhance = False
            face_upsample = False

        face_helper = FaceRestoreHelper(
            upscale,
            face_size=512,
            crop_ratio=(1, 1),
            det_model=detection_model,
            save_ext="png",
            use_parse=True,
            device=device,
        )
        bg_upsampler = upsampler if background_enhance else None
        face_upsampler = upsampler if face_upsample else None

        if has_aligned:
            # the input faces are already cropped and aligned
            img = cv2.resize(img, (512, 512), interpolation=cv2.INTER_LINEAR)
            face_helper.is_gray = is_gray(img, threshold=5)
            if face_helper.is_gray:
                print('\tgrayscale input: True')
            face_helper.cropped_faces = [img]
        else:
            face_helper.read_image(img)
            # get face landmarks for each face
            num_det_faces = face_helper.get_face_landmarks_5(
                only_center_face=only_center_face, resize=640, eye_dist_threshold=5
            )
            print(f'\tdetect {num_det_faces} faces')
            # align and warp each face
            face_helper.align_warp_face()

        # face restoration for each cropped face
        for idx, cropped_face in enumerate(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(device)

            try:
                with torch.no_grad():
                    output = codeformer_net(
                        cropped_face_t, w=codeformer_fidelity, adain=True
                    )[0]
                    restored_face = tensor2img(output, rgb2bgr=True, min_max=(-1, 1))
                del output
                torch.cuda.empty_cache()
            except RuntimeError as error:
                print(f"Failed inference for CodeFormer: {error}")
                restored_face = tensor2img(
                    cropped_face_t, rgb2bgr=True, min_max=(-1, 1)
                )

            restored_face = restored_face.astype("uint8")
            face_helper.add_restored_face(restored_face)

        if not has_aligned:
            # upsample the background
            if bg_upsampler is not None:
                # Now only support RealESRGAN for upsampling background
                bg_img = bg_upsampler.enhance(img, outscale=upscale)[0]
            else:
                bg_img = None
            face_helper.get_inverse_affine(None)
            # paste each restored face to the input image
            if face_upsample and face_upsampler is not None:
                restored_img = face_helper.paste_faces_to_input_image(
                    upsample_img=bg_img,
                    draw_box=draw_box,
                    face_upsampler=face_upsampler,
                )
            else:
                restored_img = face_helper.paste_faces_to_input_image(
                    upsample_img=bg_img, draw_box=draw_box
                )

        # save restored img
        save_path = f'output/out.png'
        imwrite(restored_img, str(save_path))

        restored_img = cv2.cvtColor(restored_img, cv2.COLOR_BGR2RGB)
        return restored_img, save_path
    except Exception as error:
        print('Global exception', error)
        return None, None


title = "CodeFormer:  Face Restoration "

demo = gr.Interface(
    inference, [
        gr.inputs.Image(type="filepath", label="Input"),
        gr.inputs.Checkbox(default=True, label="Background_Enhance"),
        gr.inputs.Checkbox(default=True, label="Face_Upsample"),
        gr.inputs.Number(default=2, label="Rescaling_Factor (up to 4)"),
        gr.Slider(0, 1, value=0.5, step=0.01, label='Codeformer_Fidelity (0 for better quality, 1 for better identity)')
    ], [
        gr.outputs.Image(type="numpy", label="Output"),
        gr.outputs.File(label="Download the output")

    ],
    title=title,
    examples=[["input.png", True, True, 2, 0.5]]

)

demo.queue(concurrency_count=2)
demo.launch()