import sys
sys.path.append('./')
from typing import Tuple
import os
import cv2
import math
import torch
import random
import numpy as np
import argparse
import PIL
from PIL import Image
import diffusers
from diffusers.utils import load_image
from diffusers.models import ControlNetModel
from diffusers import LCMScheduler
from huggingface_hub import hf_hub_download
import insightface
from insightface.app import FaceAnalysis
from style_template import styles
from pipeline_stable_diffusion_xl_instantid_full import StableDiffusionXLInstantIDPipeline
from model_util import load_models_xl, get_torch_device, torch_gc
# global variable
MAX_SEED = np.iinfo(np.int32).max
device = get_torch_device()
dtype = torch.float16 if str(device).__contains__("cuda") else torch.float32
STYLE_NAMES = list(styles.keys())
DEFAULT_STYLE_NAME = "Watercolor"
# Load face encoder
app = FaceAnalysis(name='antelopev2', root='./', providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])
app.prepare(ctx_id=0, det_size=(320, 320))
# 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=dtype)
logo = Image.open("./gradio_demo/logo.png")
from cv2 import imencode
import base64
# def encode_pil_to_base64_new(pil_image):
# print("AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA")
# image_arr = np.asarray(pil_image)[:,:,::-1]
# _, byte_data = imencode('.png', image_arr)
# base64_data = base64.b64encode(byte_data)
# base64_string_opencv = base64_data.decode("utf-8")
# return "data:image/png;base64," + base64_string_opencv
import gradio as gr
# gr.processing_utils.encode_pil_to_base64 = encode_pil_to_base64_new
def main(pretrained_model_name_or_path="wangqixun/YamerMIX_v8", enable_lcm_arg=False):
if pretrained_model_name_or_path.endswith(
".ckpt"
) or pretrained_model_name_or_path.endswith(".safetensors"):
scheduler_kwargs = hf_hub_download(
repo_id="wangqixun/YamerMIX_v8",
subfolder="scheduler",
filename="scheduler_config.json",
)
(tokenizers, text_encoders, unet, _, vae) = load_models_xl(
pretrained_model_name_or_path=pretrained_model_name_or_path,
scheduler_name=None,
weight_dtype=dtype,
)
scheduler = diffusers.EulerDiscreteScheduler.from_config(scheduler_kwargs)
pipe = StableDiffusionXLInstantIDPipeline(
vae=vae,
text_encoder=text_encoders[0],
text_encoder_2=text_encoders[1],
tokenizer=tokenizers[0],
tokenizer_2=tokenizers[1],
unet=unet,
scheduler=scheduler,
controlnet=controlnet,
).to(device)
else:
pipe = StableDiffusionXLInstantIDPipeline.from_pretrained(
pretrained_model_name_or_path,
controlnet=controlnet,
torch_dtype=dtype,
safety_checker=None,
feature_extractor=None,
).to(device)
pipe.scheduler = diffusers.EulerDiscreteScheduler.from_config(pipe.scheduler.config)
pipe.load_ip_adapter_instantid(face_adapter)
# load and disable LCM
pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
pipe.disable_lora()
def remove_tips():
print("GG")
return gr.update(visible=False)
# prompts = [
# ["superman","Vibrant Color"], ["japanese anime character with white/neon hair","Watercolor"],
# # ["Suited professional","(No style)"],
# ["Scooba diver","Line art"], ["eskimo","Snow"]
# ]
def convert_from_cv2_to_image(img: np.ndarray) -> Image:
return Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
def convert_from_image_to_cv2(img: Image) -> np.ndarray:
return cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
def run_for_prompts1(face_file,style,progress=gr.Progress(track_tqdm=True)):
# if email != "":
p,n = styles.get(style, styles.get(STYLE_NAMES[1]))
return generate_image(face_file, p[0], n)
# else:
# raise gr.Error("Email ID is compulsory")
def run_for_prompts2(face_file,style,progress=gr.Progress(track_tqdm=True)):
# if email != "":
p,n = styles.get(style, styles.get(STYLE_NAMES[1]))
return generate_image(face_file, p[1], n)
def run_for_prompts3(face_file,style,progress=gr.Progress(track_tqdm=True)):
# if email != "":
p,n = styles.get(style, styles.get(STYLE_NAMES[1]))
return generate_image(face_file, p[2], n)
def run_for_prompts4(face_file,style,progress=gr.Progress(track_tqdm=True)):
# if email != "":
p,n = styles.get(style, styles.get(STYLE_NAMES[1]))
return generate_image(face_file, p[3], n)
# def validate_and_process(face_file, style, email):
# # Your processing logic here
# gallery1, gallery2, gallery3, gallery4 = run_for_prompts1(face_file, style), run_for_prompts2(face_file, style), run_for_prompts3(face_file, style), run_for_prompts4(face_file, style)
# return gallery1, gallery2, gallery3, gallery4
def draw_kps(image_pil, kps, color_list=[(255,0,0), (0,255,0), (0,0,255), (255,255,0), (255,0,255)]):
stickwidth = 4
limbSeq = np.array([[0, 2], [1, 2], [3, 2], [4, 2]])
kps = np.array(kps)
w, h = image_pil.size
out_img = np.zeros([h, w, 3])
for i in range(len(limbSeq)):
index = limbSeq[i]
color = color_list[index[0]]
x = kps[index][:, 0]
y = kps[index][:, 1]
length = ((x[0] - x[1]) ** 2 + (y[0] - y[1]) ** 2) ** 0.5
angle = math.degrees(math.atan2(y[0] - y[1], x[0] - x[1]))
polygon = cv2.ellipse2Poly((int(np.mean(x)), int(np.mean(y))), (int(length / 2), stickwidth), int(angle), 0, 360, 1)
out_img = cv2.fillConvexPoly(out_img.copy(), polygon, color)
out_img = (out_img * 0.6).astype(np.uint8)
for idx_kp, kp in enumerate(kps):
color = color_list[idx_kp]
x, y = kp
out_img = cv2.circle(out_img.copy(), (int(x), int(y)), 10, color, -1)
out_img_pil = Image.fromarray(out_img.astype(np.uint8))
return out_img_pil
def resize_img(input_image, max_side=640, min_side=640, size=None,
pad_to_max_side=True, mode=PIL.Image.BILINEAR, base_pixel_number=64):
w, h = input_image.size
print(w)
print(h)
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
# def apply_style(style_name: str, positive: str, negative: str = "") -> Tuple[str, str]:
# p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME])
# return p.replace("{prompt}", positive), n + ' ' + negative
def generate_image(face_image,prompt,negative_prompt):
pose_image_path = None
# prompt = "superman"
enable_LCM = False
identitynet_strength_ratio = 0.95
adapter_strength_ratio = 0.60
num_steps = 15
guidance_scale = 8.5
seed = random.randint(0, MAX_SEED)
# negative_prompt = ""
# negative_prompt += neg
enhance_face_region = True
if enable_LCM:
pipe.enable_lora()
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
else:
pipe.disable_lora()
pipe.scheduler = diffusers.EulerDiscreteScheduler.from_config(pipe.scheduler.config)
if face_image is None:
raise gr.Error(f"Cannot find any input face image! Please upload the face image")
# if prompt is None:
# prompt = "a person"
# apply the style template
# prompt, negative_prompt = apply_style(style_name, prompt, negative_prompt)
# face_image = load_image(face_image_path)
face_image = resize_img(face_image)
face_image_cv2 = convert_from_image_to_cv2(face_image)
height, width, _ = face_image_cv2.shape
# Extract face features
face_info = app.get(face_image_cv2)
if len(face_info) == 0:
raise gr.Error(f"Cannot find any face in the image! Please upload another person image")
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(convert_from_cv2_to_image(face_image_cv2), face_info['kps'])
if pose_image_path is not None:
pose_image = load_image(pose_image_path)
pose_image = resize_img(pose_image)
pose_image_cv2 = convert_from_image_to_cv2(pose_image)
face_info = app.get(pose_image_cv2)
if len(face_info) == 0:
raise gr.Error(f"Cannot find any face in the reference image! Please upload another person image")
face_info = face_info[-1]
face_kps = draw_kps(pose_image, face_info['kps'])
width, height = face_kps.size
if enhance_face_region:
control_mask = np.zeros([height, width, 3])
x1, y1, x2, y2 = face_info["bbox"]
x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2)
control_mask[y1:y2, x1:x2] = 255
control_mask = Image.fromarray(control_mask.astype(np.uint8))
else:
control_mask = None
generator = torch.Generator(device=device).manual_seed(seed)
print("Start inference...")
print(f"[Debug] Prompt: {prompt}, \n[Debug] Neg Prompt: {negative_prompt}")
pipe.set_ip_adapter_scale(adapter_strength_ratio)
images = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
image_embeds=face_emb,
image=face_kps,
control_mask=control_mask,
controlnet_conditioning_scale=float(identitynet_strength_ratio),
num_inference_steps=num_steps,
guidance_scale=guidance_scale,
height=height,
width=width,
generator=generator,
# num_images_per_prompt = 4
).images
return images[0]
### Description
title = r"""
<h1 align="center">Choose your AVATAR</h1>
"""
description = r"""
<h2> Powered by IDfy </h2>"""
article = r""""""
tips = r""""""
# js = ''' '''
css = '''
.gradio-container {width: 95% !important; background-color: #E6F3FF;}
.image-gallery {height: 100vh !important; overflow: auto;}
.gradio-row .gradio-element { margin: 0 !important; }
'''
# with gr.Blocks(css=css, js=js) as demo:
# # description
# gr.Markdown(title)
# with gr.Row():
# gr.Image("./gradio_demo/logo.png",scale=0,min_width=50,show_label=False,show_download_button=False)
# gr.Markdown(description)
# with gr.Row():
# with gr.Column():
# style = gr.Dropdown(label="Choose your STYLE", choices=STYLE_NAMES)
# face_file = gr.Image(label="Upload a photo of your face", type="pil",sources="webcam")
# submit = gr.Button("Submit", variant="primary")
# with gr.Column():
# with gr.Row():
# gallery1 = gr.Image(label="Generated Images")
# gallery2 = gr.Image(label="Generated Images")
# with gr.Row():
# gallery3 = gr.Image(label="Generated Images")
# gallery4 = gr.Image(label="Generated Images")
# email = gr.Textbox(label="Email",
# info="Enter your email address",
# value="")
# # submit1 = gr.Button("Store")
# usage_tips = gr.Markdown(label="Usage tips of InstantID", value=tips ,visible=False)
# face_file.upload(
# fn=remove_tips,
# outputs=usage_tips,
# queue=True,
# api_name=False,
# show_progress = "full"
# ).then(
# fn=run_for_prompts1,
# inputs=[face_file,style],
# outputs=[gallery1]
# ).then(
# fn=run_for_prompts2,
# inputs=[face_file,style],
# outputs=[gallery2]
# ).then(
# fn=run_for_prompts3,
# inputs=[face_file,style],
# outputs=[gallery3]
# ).then(
# fn=run_for_prompts4,
# inputs=[face_file,style],
# outputs=[gallery4]
# )
# submit.click(
# fn=remove_tips,
# outputs=usage_tips,
# queue=True,
# api_name=False,
# show_progress = "full"
# ).then(
# fn=run_for_prompts1,
# inputs=[face_file,style],
# outputs=[gallery1]
# ).then(
# fn=run_for_prompts2,
# inputs=[face_file,style],
# outputs=[gallery2]
# ).then(
# fn=run_for_prompts3,
# inputs=[face_file,style],
# outputs=[gallery3]
# ).then(
# fn=run_for_prompts4,
# inputs=[face_file,style],
# outputs=[gallery4]
# )
# # submit1.click(
# # fn=store_images,
# # inputs=[email,gallery1,gallery2,gallery3,gallery4],
# # outputs=None)
# gr.Markdown(article)
# demo.launch(share=True)
with gr.Blocks(css=css) as demo:
# description
gr.Markdown(title)
with gr.Row():
gr.Image("./gradio_demo/logo.png",scale=0,min_width=50,show_label=False,show_download_button=False)
gr.Markdown(description)
with gr.Row():
with gr.Column():
style = gr.Dropdown(label="Choose your STYLE", choices=STYLE_NAMES)
face_file = gr.Image(label="Upload a photo of your face", type="pil",sources="webcam")
submit = gr.Button("Submit", variant="primary")
with gr.Column():
with gr.Row():
gallery1 = gr.Image(label="Generated Images")
gallery2 = gr.Image(label="Generated Images")
with gr.Row():
gallery3 = gr.Image(label="Generated Images")
gallery4 = gr.Image(label="Generated Images")
email = gr.Textbox(label="Email",
info="Enter your email address",
value="")
usage_tips = gr.Markdown(label="Usage tips of InstantID", value=tips ,visible=False)
# identitynet_strength_ratio = gr.Slider(
# label="IdentityNet strength (for fidelity)",
# minimum=0,
# maximum=1.5,
# step=0.05,
# value=0.95,
# )
# adapter_strength_ratio = gr.Slider(
# label="Image adapter strength (for detail)",
# minimum=0,
# maximum=1.5,
# step=0.05,
# value=0.60,
# )
# negative_prompt = gr.Textbox(
# label="Negative Prompt",
# placeholder="low quality",
# value="(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
# )
# num_steps = gr.Slider(
# label="Number of sample steps",
# minimum=15,
# maximum=100,
# step=1,
# value=5 if enable_lcm_arg else 15,
# )
# guidance_scale = gr.Slider(
# label="Guidance scale",
# minimum=0.1,
# maximum=10.0,
# step=0.1,
# value=0 if enable_lcm_arg else 8.5,
# )
# if email is None:
# print("STOPPPP")
# raise gr.Error("Email ID is compulsory")
face_file.upload(
fn=remove_tips,
outputs=usage_tips,
queue=True,
api_name=False,
show_progress = "full"
).then(
fn=run_for_prompts1,
inputs=[face_file,style],
outputs=[gallery1]
).then(
fn=run_for_prompts2,
inputs=[face_file,style],
outputs=[gallery2]
).then(
fn=run_for_prompts3,
inputs=[face_file,style],
outputs=[gallery3]
).then(
fn=run_for_prompts4,
inputs=[face_file,style],
outputs=[gallery4]
)
submit.click(
fn=remove_tips,
outputs=usage_tips,
queue=True,
api_name=False,
show_progress = "full"
).then(
fn=run_for_prompts1,
inputs=[face_file,style],
outputs=[gallery1]
).then(
fn=run_for_prompts2,
inputs=[face_file,style],
outputs=[gallery2]
).then(
fn=run_for_prompts3,
inputs=[face_file,style],
outputs=[gallery3]
).then(
fn=run_for_prompts4,
inputs=[face_file,style],
outputs=[gallery4]
)
gr.Markdown(article)
demo.launch(share=True)
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--pretrained_model_name_or_path", type=str, default="wangqixun/YamerMIX_v8")
args = parser.parse_args()
main(args.pretrained_model_name_or_path, False)
# import sys
# sys.path.append('./')
# from typing import Tuple
# import os
# import cv2
# import math
# import torch
# import random
# import numpy as np
# import argparse
# import PIL
# from PIL import Image
# import diffusers
# from diffusers.utils import load_image
# from diffusers.models import ControlNetModel
# from diffusers import LCMScheduler
# from huggingface_hub import hf_hub_download
# import insightface
# from insightface.app import FaceAnalysis
# from style_template import styles
# from pipeline_stable_diffusion_xl_instantid_full import StableDiffusionXLInstantIDPipeline
# from model_util import load_models_xl, get_torch_device, torch_gc
# # global variable
# MAX_SEED = np.iinfo(np.int32).max
# device = get_torch_device()
# dtype = torch.float16 if str(device).__contains__("cuda") else torch.float32
# STYLE_NAMES = list(styles.keys())
# DEFAULT_STYLE_NAME = "Watercolor"
# # Load face encoder
# app = FaceAnalysis(name='antelopev2', root='./', providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])
# app.prepare(ctx_id=0, det_size=(320, 320))
# # 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=dtype)
# logo = Image.open("./gradio_demo/logo.png")
# from cv2 import imencode
# import base64
# # def encode_pil_to_base64_new(pil_image):
# # print("AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA")
# # image_arr = np.asarray(pil_image)[:,:,::-1]
# # _, byte_data = imencode('.png', image_arr)
# # base64_data = base64.b64encode(byte_data)
# # base64_string_opencv = base64_data.decode("utf-8")
# # return "data:image/png;base64," + base64_string_opencv
# import gradio as gr
# # gr.processing_utils.encode_pil_to_base64 = encode_pil_to_base64_new
# def main(pretrained_model_name_or_path="wangqixun/YamerMIX_v8", enable_lcm_arg=False):
# if pretrained_model_name_or_path.endswith(
# ".ckpt"
# ) or pretrained_model_name_or_path.endswith(".safetensors"):
# scheduler_kwargs = hf_hub_download(
# repo_id="wangqixun/YamerMIX_v8",
# subfolder="scheduler",
# filename="scheduler_config.json",
# )
# (tokenizers, text_encoders, unet, _, vae) = load_models_xl(
# pretrained_model_name_or_path=pretrained_model_name_or_path,
# scheduler_name=None,
# weight_dtype=dtype,
# )
# scheduler = diffusers.EulerDiscreteScheduler.from_config(scheduler_kwargs)
# pipe = StableDiffusionXLInstantIDPipeline(
# vae=vae,
# text_encoder=text_encoders[0],
# text_encoder_2=text_encoders[1],
# tokenizer=tokenizers[0],
# tokenizer_2=tokenizers[1],
# unet=unet,
# scheduler=scheduler,
# controlnet=controlnet,
# ).to(device)
# else:
# pipe = StableDiffusionXLInstantIDPipeline.from_pretrained(
# pretrained_model_name_or_path,
# controlnet=controlnet,
# torch_dtype=dtype,
# safety_checker=None,
# feature_extractor=None,
# ).to(device)
# pipe.scheduler = diffusers.EulerDiscreteScheduler.from_config(pipe.scheduler.config)
# pipe.load_ip_adapter_instantid(face_adapter)
# # load and disable LCM
# pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
# pipe.disable_lora()
# def remove_tips():
# return gr.update(visible=False)
# # prompts = [
# # ["superman","Vibrant Color"], ["japanese anime character with white/neon hair","Watercolor"],
# # # ["Suited professional","(No style)"],
# # ["Scooba diver","Line art"], ["eskimo","Snow"]
# # ]
# def convert_from_cv2_to_image(img: np.ndarray) -> Image:
# return Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
# def convert_from_image_to_cv2(img: Image) -> np.ndarray:
# return cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
# def run_for_prompts1(face_file,style,progress=gr.Progress(track_tqdm=True)):
# # if email != "":
# p,n = styles.get(style, styles.get(STYLE_NAMES[1]))
# return generate_image(face_file, p[0], n)
# # else:
# # raise gr.Error("Email ID is compulsory")
# def run_for_prompts2(face_file,style,progress=gr.Progress(track_tqdm=True)):
# # if email != "":
# p,n = styles.get(style, styles.get(STYLE_NAMES[1]))
# return generate_image(face_file, p[1], n)
# def run_for_prompts3(face_file,style,progress=gr.Progress(track_tqdm=True)):
# # if email != "":
# p,n = styles.get(style, styles.get(STYLE_NAMES[1]))
# return generate_image(face_file, p[2], n)
# def run_for_prompts4(face_file,style,progress=gr.Progress(track_tqdm=True)):
# # if email != "":
# p,n = styles.get(style, styles.get(STYLE_NAMES[1]))
# return generate_image(face_file, p[3], n)
# # def validate_and_process(face_file, style, email):
# # # Your processing logic here
# # gallery1, gallery2, gallery3, gallery4 = run_for_prompts1(face_file, style), run_for_prompts2(face_file, style), run_for_prompts3(face_file, style), run_for_prompts4(face_file, style)
# # return gallery1, gallery2, gallery3, gallery4
# def draw_kps(image_pil, kps, color_list=[(255,0,0), (0,255,0), (0,0,255), (255,255,0), (255,0,255)]):
# stickwidth = 4
# limbSeq = np.array([[0, 2], [1, 2], [3, 2], [4, 2]])
# kps = np.array(kps)
# w, h = image_pil.size
# out_img = np.zeros([h, w, 3])
# for i in range(len(limbSeq)):
# index = limbSeq[i]
# color = color_list[index[0]]
# x = kps[index][:, 0]
# y = kps[index][:, 1]
# length = ((x[0] - x[1]) ** 2 + (y[0] - y[1]) ** 2) ** 0.5
# angle = math.degrees(math.atan2(y[0] - y[1], x[0] - x[1]))
# polygon = cv2.ellipse2Poly((int(np.mean(x)), int(np.mean(y))), (int(length / 2), stickwidth), int(angle), 0, 360, 1)
# out_img = cv2.fillConvexPoly(out_img.copy(), polygon, color)
# out_img = (out_img * 0.6).astype(np.uint8)
# for idx_kp, kp in enumerate(kps):
# color = color_list[idx_kp]
# x, y = kp
# out_img = cv2.circle(out_img.copy(), (int(x), int(y)), 10, color, -1)
# out_img_pil = Image.fromarray(out_img.astype(np.uint8))
# return out_img_pil
# def resize_img(input_image, max_side=640, min_side=640, size=None,
# pad_to_max_side=True, mode=PIL.Image.BILINEAR, base_pixel_number=64):
# w, h = input_image.size
# print(w)
# print(h)
# 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
# # def apply_style(style_name: str, positive: str, negative: str = "") -> Tuple[str, str]:
# # p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME])
# # return p.replace("{prompt}", positive), n + ' ' + negative
# def generate_image(face_image,prompt,negative_prompt):
# pose_image_path = None
# # prompt = "superman"
# enable_LCM = False
# identitynet_strength_ratio = 0.95
# adapter_strength_ratio = 0.60
# num_steps = 15
# guidance_scale = 8.5
# seed = random.randint(0, MAX_SEED)
# # negative_prompt = ""
# # negative_prompt += neg
# enhance_face_region = True
# if enable_LCM:
# pipe.enable_lora()
# pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
# else:
# pipe.disable_lora()
# pipe.scheduler = diffusers.EulerDiscreteScheduler.from_config(pipe.scheduler.config)
# if face_image is None:
# raise gr.Error(f"Cannot find any input face image! Please upload the face image")
# # if prompt is None:
# # prompt = "a person"
# # apply the style template
# # prompt, negative_prompt = apply_style(style_name, prompt, negative_prompt)
# # face_image = load_image(face_image_path)
# face_image = resize_img(face_image)
# face_image_cv2 = convert_from_image_to_cv2(face_image)
# height, width, _ = face_image_cv2.shape
# # Extract face features
# face_info = app.get(face_image_cv2)
# if len(face_info) == 0:
# raise gr.Error(f"Cannot find any face in the image! Please upload another person image")
# 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(convert_from_cv2_to_image(face_image_cv2), face_info['kps'])
# if pose_image_path is not None:
# pose_image = load_image(pose_image_path)
# pose_image = resize_img(pose_image)
# pose_image_cv2 = convert_from_image_to_cv2(pose_image)
# face_info = app.get(pose_image_cv2)
# if len(face_info) == 0:
# raise gr.Error(f"Cannot find any face in the reference image! Please upload another person image")
# face_info = face_info[-1]
# face_kps = draw_kps(pose_image, face_info['kps'])
# width, height = face_kps.size
# if enhance_face_region:
# control_mask = np.zeros([height, width, 3])
# x1, y1, x2, y2 = face_info["bbox"]
# x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2)
# control_mask[y1:y2, x1:x2] = 255
# control_mask = Image.fromarray(control_mask.astype(np.uint8))
# else:
# control_mask = None
# generator = torch.Generator(device=device).manual_seed(seed)
# print("Start inference...")
# print(f"[Debug] Prompt: {prompt}, \n[Debug] Neg Prompt: {negative_prompt}")
# pipe.set_ip_adapter_scale(adapter_strength_ratio)
# images = pipe(
# prompt=prompt,
# negative_prompt=negative_prompt,
# image_embeds=face_emb,
# image=face_kps,
# control_mask=control_mask,
# controlnet_conditioning_scale=float(identitynet_strength_ratio),
# num_inference_steps=num_steps,
# guidance_scale=guidance_scale,
# height=height,
# width=width,
# generator=generator,
# # num_images_per_prompt = 4
# ).images
# return images[0]
# ### Description
# title = r"""
# <h1 align="center">Choose your AVATAR</h1>
# """
# description = r"""
# <h2> Powered by IDfy </h2>"""
# article = r""""""
# tips = r""""""
# css = '''
# .gradio-container {width: 95% !important; background-color: #E6F3FF;}
# .image-gallery {height: 100vh !important; overflow: auto;}
# .gradio-row .gradio-element { margin: 0 !important; }
# '''
# with gr.Blocks(css=css) as demo:
# # description
# gr.Markdown(title)
# with gr.Row():
# gr.Image("./gradio_demo/logo.png",scale=0,min_width=50,show_label=False,show_download_button=False)
# gr.Markdown(description)
# with gr.Row():
# with gr.Column():
# style = gr.Dropdown(label="Choose your STYLE", choices=STYLE_NAMES)
# face_file = gr.Image(label="Upload a photo of your face", type="pil",sources="webcam")
# submit = gr.Button("Submit", variant="primary")
# with gr.Column():
# with gr.Row():
# gallery1 = gr.Image(label="Generated Images")
# gallery2 = gr.Image(label="Generated Images")
# with gr.Row():
# gallery3 = gr.Image(label="Generated Images")
# gallery4 = gr.Image(label="Generated Images")
# email = gr.Textbox(label="Email",
# info="Enter your email address",
# value="")
# usage_tips = gr.Markdown(label="Usage tips of InstantID", value=tips ,visible=False)
# # identitynet_strength_ratio = gr.Slider(
# # label="IdentityNet strength (for fidelity)",
# # minimum=0,
# # maximum=1.5,
# # step=0.05,
# # value=0.95,
# # )
# # adapter_strength_ratio = gr.Slider(
# # label="Image adapter strength (for detail)",
# # minimum=0,
# # maximum=1.5,
# # step=0.05,
# # value=0.60,
# # )
# # negative_prompt = gr.Textbox(
# # label="Negative Prompt",
# # placeholder="low quality",
# # value="(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
# # )
# # num_steps = gr.Slider(
# # label="Number of sample steps",
# # minimum=15,
# # maximum=100,
# # step=1,
# # value=5 if enable_lcm_arg else 15,
# # )
# # guidance_scale = gr.Slider(
# # label="Guidance scale",
# # minimum=0.1,
# # maximum=10.0,
# # step=0.1,
# # value=0 if enable_lcm_arg else 8.5,
# # )
# # if email is None:
# # print("STOPPPP")
# # raise gr.Error("Email ID is compulsory")
# face_file.upload(
# fn=remove_tips,
# outputs=usage_tips,
# queue=True,
# api_name=False,
# show_progress = "full"
# ).then(
# fn=run_for_prompts1,
# inputs=[face_file,style],
# outputs=[gallery1]
# ).then(
# fn=run_for_prompts2,
# inputs=[face_file,style],
# outputs=[gallery2]
# ).then(
# fn=run_for_prompts3,
# inputs=[face_file,style],
# outputs=[gallery3]
# ).then(
# fn=run_for_prompts4,
# inputs=[face_file,style],
# outputs=[gallery4]
# )
# submit.click(
# fn=remove_tips,
# outputs=usage_tips,
# queue=True,
# api_name=False,
# show_progress = "full"
# ).then(
# fn=run_for_prompts1,
# inputs=[face_file,style],
# outputs=[gallery1]
# ).then(
# fn=run_for_prompts2,
# inputs=[face_file,style],
# outputs=[gallery2]
# ).then(
# fn=run_for_prompts3,
# inputs=[face_file,style],
# outputs=[gallery3]
# ).then(
# fn=run_for_prompts4,
# inputs=[face_file,style],
# outputs=[gallery4]
# )
# gr.Markdown(article)
# demo.launch(share=True)
# if __name__ == "__main__":
# parser = argparse.ArgumentParser()
# parser.add_argument("--pretrained_model_name_or_path", type=str, default="wangqixun/YamerMIX_v8")
# args = parser.parse_args()
# main(args.pretrained_model_name_or_path, False)