File size: 3,451 Bytes
0791e43
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
import cv2
import torch
import numpy as np
from PIL import Image

from diffusers.utils import load_image
from diffusers.models import ControlNetModel

from insightface.app import FaceAnalysis
from pipeline_stable_diffusion_xl_instantid_img2img import StableDiffusionXLInstantIDImg2ImgPipeline, draw_kps

def resize_img(input_image, max_side=1280, min_side=1024, size=None, 
               pad_to_max_side=False, mode=Image.BILINEAR, base_pixel_number=64):

    w, h = input_image.size
    if size is not None:
        w_resize_new, h_resize_new = size
    else:
        ratio = min_side / min(h, w)
        w, h = round(ratio*w), round(ratio*h)
        ratio = max_side / max(h, w)
        input_image = input_image.resize([round(ratio*w), round(ratio*h)], mode)
        w_resize_new = (round(ratio * w) // base_pixel_number) * base_pixel_number
        h_resize_new = (round(ratio * h) // base_pixel_number) * base_pixel_number
    input_image = input_image.resize([w_resize_new, h_resize_new], mode)

    if pad_to_max_side:
        res = np.ones([max_side, max_side, 3], dtype=np.uint8) * 255
        offset_x = (max_side - w_resize_new) // 2
        offset_y = (max_side - h_resize_new) // 2
        res[offset_y:offset_y+h_resize_new, offset_x:offset_x+w_resize_new] = np.array(input_image)
        input_image = Image.fromarray(res)
    return input_image


if __name__ == "__main__":
    
    # Load face encoder
    app = FaceAnalysis(name='antelopev2', root='./', providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])
    app.prepare(ctx_id=0, det_size=(640, 640))

    # Path to InstantID models
    face_adapter = f'./checkpoints/ip-adapter.bin'
    controlnet_path = f'./checkpoints/ControlNetModel'

    # Load pipeline
    controlnet = ControlNetModel.from_pretrained(controlnet_path, torch_dtype=torch.float16)

    base_model_path = 'stabilityai/stable-diffusion-xl-base-1.0'

    pipe = StableDiffusionXLInstantIDImg2ImgPipeline.from_pretrained(
        base_model_path,
        controlnet=controlnet,
        torch_dtype=torch.float16,
    )
    pipe.cuda()
    pipe.load_ip_adapter_instantid(face_adapter)

    # Infer setting
    prompt = "analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality"
    n_prompt = "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured"

    face_image = load_image("./examples/yann-lecun_resize.jpg")
    face_image = resize_img(face_image)

    face_info = app.get(cv2.cvtColor(np.array(face_image), cv2.COLOR_RGB2BGR))
    face_info = sorted(face_info, key=lambda x:(x['bbox'][2]-x['bbox'][0])*(x['bbox'][3]-x['bbox'][1]))[-1] # only use the maximum face
    face_emb = face_info['embedding']
    face_kps = draw_kps(face_image, face_info['kps'])

    image = pipe(
        prompt=prompt,
        negative_prompt=n_prompt,
        image=face_image,
        image_embeds=face_emb,
        control_image=face_kps,
        controlnet_conditioning_scale=0.8,
        ip_adapter_scale=0.8,
        num_inference_steps=30,
        guidance_scale=5,
        strength=0.85
    ).images[0]

    image.save('result.jpg')