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 import os # try: # # Send a GET request to the URL # response = requests.get("https://storage.googleapis.com/idfy-gff-public/idfy-gff-public%40idfy-eve-ml-training.iam.gserviceaccount.com.json") # # Raise an exception if the request was unsuccessful # response.raise_for_status() # # Save the file to the specified path # with open("serviceaccount.json", 'wb') as file: # file.write(response.content) # print(f"Service account JSON file successfully downloaded") os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "serviceaccount.json" # except requests.exceptions.RequestException as e: # print(f"Failed to download the service account JSON file: {e}") # 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 import gradio as gr from google.cloud import storage from io import BytesIO 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) 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 upload_pil_image_to_gcs(image, destination_blob_name): bucket_name="idfy-gff-public" # Convert PIL image to byte stream image_byte_array = BytesIO() image.save(image_byte_array, format='PNG') # Save image in its original format image_byte_array.seek(0) # Initialize a GCP client storage_client = storage.Client() # Get the bucket bucket = storage_client.bucket(bucket_name) # Create a blob object from the filename blob = bucket.blob(destination_blob_name) # Upload the image to GCS blob.upload_from_file(image_byte_array, content_type=f'image/png') 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 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 store_images(email, gallery1, gallery2, gallery3, gallery4,consent,style): if not email: raise gr.Error("Email Id not provided") if not consent: raise gr.Error("Consent not provided") for i, img in enumerate([gallery1, gallery2, gallery3, gallery4], start=1): if isinstance(img, np.ndarray): img = Image.fromarray(img) dest = f'{email}/img{i}@{style}.png' upload_pil_image_to_gcs(img,dest) gr.Info("Thankyou!! Your avatar is on the way to your inbox") return None,None,None,None,None 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) 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") 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) 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"""