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 pandas as pd 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=(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=dtype) logo = Image.open("./gradio_demo/watermark.png") logo = logo.resize((100, 100)) 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=1280, min_side=1280, size=None, pad_to_max_side=True, mode=PIL.Image.BILINEAR, base_pixel_number=64): w, h = input_image.size print(f"Original Size --> {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) print(f"Final modified image size --> {input_image.size}") 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 store_images(email, gallery1, gallery2, gallery3, gallery4,consent): if not consent: raise gr.Error("Consent not provided") galleries = [] for i, img in enumerate([gallery1, gallery2, gallery3, gallery4], start=1): if isinstance(img, np.ndarray): img = Image.fromarray(img) print(f"Gallery {i} type after conversion: {type(img)}") galleries.append(img) # Create the images directory if it doesn't exist if not os.path.exists('images'): os.makedirs('images') # Define image file paths image_paths = [] for i, img in enumerate(galleries, start=1): img_path = f'images/{email}_gallery{i}.png' img.save(img_path) image_paths.append(img_path) # Define the CSV file path csv_file_path = 'image_data.csv' # Create a DataFrame for the email and image paths df = pd.DataFrame({ 'email': [email], 'img1_path': [image_paths[0]], 'img2_path': [image_paths[1]], 'img3_path': [image_paths[2]], 'img4_path': [image_paths[3]], }) # Write to CSV (append if the file exists, create a new one if it doesn't) if not os.path.isfile(csv_file_path): df.to_csv(csv_file_path, index=False) else: df.to_csv(csv_file_path, mode='a', header=False, index=False) gr.Info("Thankyou!! Your avatar is on the way to your inbox") def add_watermark(image, watermark=logo, opacity=128, position="bottom_right", padding=10): # Convert NumPy array to PIL Image if needed if isinstance(image, np.ndarray): image = Image.fromarray(image) if isinstance(watermark, np.ndarray): watermark = Image.fromarray(watermark) # Convert images to 'RGBA' mode to handle transparency image = image.convert("RGBA") watermark = watermark.convert("RGBA") # Adjust the watermark opacity watermark = watermark.copy() watermark.putalpha(opacity) # Calculate the position for the watermark if position == "bottom_right": x = image.width - watermark.width - padding y = image.height - watermark.height - padding elif position == "bottom_left": x = padding y = image.height - watermark.height - padding elif position == "top_right": x = image.width - watermark.width - padding y = padding elif position == "top_left": x = padding y = padding else: raise ValueError("Unsupported position. Choose from 'bottom_right', 'bottom_left', 'top_right', 'top_left'.") # Paste the watermark onto the image image.paste(watermark, (x, y), watermark) # Convert back to 'RGB' if the original image was not 'RGBA' if image.mode != "RGBA": image = image.convert("RGB") # return resize_img(image) return image def generate_image(face_image,prompt,negative_prompt): pose_image_path = None # prompt = "superman" enable_LCM = False identitynet_strength_ratio = 0.90 adapter_strength_ratio = 0.60 num_steps = 15 guidance_scale = 5 seed = random.randint(0, MAX_SEED) print(f"Seed --> {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 watermarked_image = add_watermark(images[0]) # return images[0] return watermarked_image ### Description title = r"""

Choose your AVATAR

""" description = r"""

Powered by IDfy

""" article = r"""""" tips = r"""""" # css = ''' # .gradio-container { # width: 95% !important; # background-image: url('./InstantID/gradio_demo/logo.png'); # background-size: cover; # background-position: center; # } # .image-gallery { # height: 100vh !important; # overflow: auto; # } # .gradio-row .gradio-element { # margin: 0 !important; # } # ''' css = ''' .gradio-container {width: 100% !important; color: white; background: linear-gradient(135deg, #1C43B9, #254977, #343434);} .gradio-row .gradio-element { margin: 0 !important; } .centered-column { display: flex; justify-content: center; align-items: center; width: 100%;} sub-btn,#store-btn { background: linear-gradient(to right, #ffffff, #f2bb13); !important; color: #254977 !important; } ''' with gr.Blocks(css=css) as demo: # description gr.Markdown(title) with gr.Column(): with gr.Row(): gr.Image("./gradio_demo/logo.png", scale=0, min_width=50, show_label=False, show_download_button=False) gr.Markdown(description) style = gr.Dropdown(label="Choose your STYLE", choices=STYLE_NAMES) with gr.Row(equal_height=True): # Center the face file with gr.Column(elem_id="centered-face", elem_classes=["centered-column"]): # Use CSS class for centering face_file = gr.Image(label="Upload a photo of your face", type="pil", height=400, width=500) submit = gr.Button("Submit", variant="primary",elem_id="sub-btn") 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="") consent = gr.Checkbox(label="I am giving my consent to use my data to share my AI Avtar and IDfy relevant information from time to time") submit1 = gr.Button("SUBMIT",elem_id="store-btn") # with gr.Blocks(css=css) as demo: # # description # gr.Markdown(title) # with gr.Column(): # with gr.Row(): # gr.Image("./gradio_demo/logo.png",scale=0,min_width=50,show_label=False,show_download_button=False) # gr.Markdown(description) # 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", height=400, width=500) # 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="") # consent = gr.Checkbox(label="I am giving my consent to use my data to share my AI Avtar and IDfy relevant information from time to time") # submit1 = gr.Button("STORE", variant="primary") # # 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,consent], outputs=None) gr.Markdown(article) demo.launch(share=True) # 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="") # 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)