app.py

import os
os.system("pip freeze")
from huggingface_hub import hf_hub_download
os.system("pip -qq install facenet_pytorch")
from facenet_pytorch import MTCNN
from torchvision import transforms
import torch, PIL
from tqdm.notebook import tqdm
import gradio as gr
import torch

modelarcanev4 = hf_hub_download(repo_id="akhaliq/ArcaneGANv0.4", filename="ArcaneGANv0.4.jit")
modelarcanev3 = hf_hub_download(repo_id="akhaliq/ArcaneGANv0.3", filename="ArcaneGANv0.3.jit")
modelarcanev2 = hf_hub_download(repo_id="akhaliq/ArcaneGANv0.2", filename="ArcaneGANv0.2.jit")


mtcnn = MTCNN(image_size=256, margin=80)

# simplest ye olde trustworthy MTCNN for face detection with landmarks
def detect(img):
 
        # Detect faces
        batch_boxes, batch_probs, batch_points = mtcnn.detect(img, landmarks=True)
        # Select faces
        if not mtcnn.keep_all:
            batch_boxes, batch_probs, batch_points = mtcnn.select_boxes(
                batch_boxes, batch_probs, batch_points, img, method=mtcnn.selection_method
            )
 
        return batch_boxes, batch_points

# my version of isOdd, should make a separate repo for it :D
def makeEven(_x):
  return _x if (_x % 2 == 0) else _x+1

# the actual scaler function
def scale(boxes, _img, max_res=1_500_000, target_face=256, fixed_ratio=0, max_upscale=2, VERBOSE=False):
 
    x, y = _img.size
 
    ratio = 2 #initial ratio
 
    #scale to desired face size
    if (boxes is not None):
      if len(boxes)>0:
        ratio = target_face/max(boxes[0][2:]-boxes[0][:2]); 
        ratio = min(ratio, max_upscale)
        if VERBOSE: print('up by', ratio)

    if fixed_ratio>0:
      if VERBOSE: print('fixed ratio')
      ratio = fixed_ratio
 
    x*=ratio
    y*=ratio
 
    #downscale to fit into max res 
    res = x*y
    if res > max_res:
      ratio = pow(res/max_res,1/2); 
      if VERBOSE: print(ratio)
      x=int(x/ratio)
      y=int(y/ratio)
 
    #make dimensions even, because usually NNs fail on uneven dimensions due skip connection size mismatch
    x = makeEven(int(x))
    y = makeEven(int(y))
    
    size = (x, y)

    return _img.resize(size)

""" 
    A useful scaler algorithm, based on face detection.
    Takes PIL.Image, returns a uniformly scaled PIL.Image
    boxes: a list of detected bboxes
    _img: PIL.Image
    max_res: maximum pixel area to fit into. Use to stay below the VRAM limits of your GPU.
    target_face: desired face size. Upscale or downscale the whole image to fit the detected face into that dimension.
    fixed_ratio: fixed scale. Ignores the face size, but doesn't ignore the max_res limit.
    max_upscale: maximum upscale ratio. Prevents from scaling images with tiny faces to a blurry mess.
"""

def scale_by_face_size(_img, max_res=1_500_000, target_face=256, fix_ratio=0, max_upscale=2, VERBOSE=False):
    boxes = None
    boxes, _ = detect(_img)
    if VERBOSE: print('boxes',boxes)
    img_resized = scale(boxes, _img, max_res, target_face, fix_ratio, max_upscale, VERBOSE)
    return img_resized


size = 256

means = [0.485, 0.456, 0.406]
stds = [0.229, 0.224, 0.225]

t_stds = torch.tensor(stds).cpu().half().float()[:,None,None]
t_means = torch.tensor(means).cpu().half().float()[:,None,None]

def makeEven(_x):
  return int(_x) if (_x % 2 == 0) else int(_x+1)

img_transforms = transforms.Compose([                        
            transforms.ToTensor(),
            transforms.Normalize(means,stds)])
 
def tensor2im(var):
     return var.mul(t_stds).add(t_means).mul(255.).clamp(0,255).permute(1,2,0)

def proc_pil_img(input_image, model):
    transformed_image = img_transforms(input_image)[None,...].cpu().half().float()
            
    with torch.no_grad():
        result_image = model(transformed_image)[0]
        output_image = tensor2im(result_image)
        output_image = output_image.detach().cpu().numpy().astype('uint8')
        output_image = PIL.Image.fromarray(output_image)
    return output_image
    
    
 
modelv4 = torch.jit.load(modelarcanev4,map_location='cpu').eval().cpu().half().float()
modelv3 = torch.jit.load(modelarcanev3,map_location='cpu').eval().cpu().half().float()
modelv2 = torch.jit.load(modelarcanev2,map_location='cpu').eval().cpu().half().float()

def version4(im):
    im = scale_by_face_size(im, target_face=256, max_res=1_500_000, max_upscale=1)
    res = proc_pil_img(im, modelv4)
    return res

def version3(im):
    im = scale_by_face_size(im, target_face=256, max_res=1_500_000, max_upscale=1)
    res = proc_pil_img(im, modelv3)
    return res

def version2(im):
    im = scale_by_face_size(im, target_face=256, max_res=1_500_000, max_upscale=1)
    res = proc_pil_img(im, modelv2)
    return res
     
block = gr.Blocks()

with block:
    gr.Markdown("Gradio Demo for ArcaneGAN, portrait to Arcane style. To use it, simply upload your image. Try out the different versions by clicking on the tabs. Please use a cropped portrait picture for best results.")
    
    with gr.Tab("version four"):
        with gr.Row():
            facepaint4 = gr.inputs.Image(type="pil",shape=(512,512))
            faceout4 = gr.outputs.Image(type="pil")
        face_run = gr.Button("Run")
        face_run.click(version4, inputs=facepaint4, outputs=faceout4)

    with gr.Tab("version three"):
        with gr.Row():
            facepaint3 = gr.inputs.Image(type="pil")
            faceout3 = gr.outputs.Image(type="pil")
        face_run = gr.Button("Run")
        face_run.click(version3, inputs=facepaint3, outputs=faceout3)
    with gr.Tab("version two"):
        with gr.Row():
            facepaint2 = gr.inputs.Image(type="pil")
            faceout2 = gr.outputs.Image(type="pil")
        face_run = gr.Button("Run")
        face_run.click(version2, inputs=facepaint2, outputs=faceout2)

block.launch(enable_queue=True)