import spaces import os import requests import torch from diffusers import StableDiffusionControlNetImg2ImgPipeline, ControlNetModel, DDIMScheduler, DPMSolverMultistepScheduler, EulerAncestralDiscreteScheduler, EulerDiscreteScheduler from diffusers.pipelines.stable_diffusion import StableDiffusionSafetyChecker from diffusers.models import AutoencoderKL from PIL import Image from RealESRGAN import RealESRGAN import cv2 import numpy as np from diffusers.models.attention_processor import AttnProcessor2_0 import gradio as gr USE_TORCH_COMPILE = 0 ENABLE_CPU_OFFLOAD = 0 # Set up the device device = torch.device("cuda" if torch.cuda.is_available() else "cpu") # Function to download files (from the example) def download_file(url, folder_path, filename): if not os.path.exists(folder_path): os.makedirs(folder_path) file_path = os.path.join(folder_path, filename) if os.path.isfile(file_path): print(f"File already exists: {file_path}") else: response = requests.get(url, stream=True) if response.status_code == 200: with open(file_path, 'wb') as file: for chunk in response.iter_content(chunk_size=1024): file.write(chunk) print(f"File successfully downloaded and saved: {file_path}") else: print(f"Error downloading the file. Status code: {response.status_code}") # Download necessary models and files def download_models(): models = { "MODEL": ("https://huggingface.co/dantea1118/juggernaut_reborn/resolve/main/juggernaut_reborn.safetensors?download=true", "models/models/Stable-diffusion", "juggernaut_reborn.safetensors"), "UPSCALER_X2": ("https://huggingface.co/ai-forever/Real-ESRGAN/resolve/main/RealESRGAN_x2.pth?download=true", "models/upscalers/", "RealESRGAN_x2.pth"), "UPSCALER_X4": ("https://huggingface.co/ai-forever/Real-ESRGAN/resolve/main/RealESRGAN_x4.pth?download=true", "models/upscalers/", "RealESRGAN_x4.pth"), "NEGATIVE_1": ("https://huggingface.co/philz1337x/embeddings/resolve/main/verybadimagenegative_v1.3.pt?download=true", "models/embeddings", "verybadimagenegative_v1.3.pt"), "NEGATIVE_2": ("https://huggingface.co/datasets/AddictiveFuture/sd-negative-embeddings/resolve/main/JuggernautNegative-neg.pt?download=true", "models/embeddings", "JuggernautNegative-neg.pt"), "LORA_1": ("https://huggingface.co/philz1337x/loras/resolve/main/SDXLrender_v2.0.safetensors?download=true", "models/Lora", "SDXLrender_v2.0.safetensors"), "LORA_2": ("https://huggingface.co/philz1337x/loras/resolve/main/more_details.safetensors?download=true", "models/Lora", "more_details.safetensors"), "CONTROLNET": ("https://huggingface.co/lllyasviel/ControlNet-v1-1/resolve/main/control_v11f1e_sd15_tile.pth?download=true", "models/ControlNet", "control_v11f1e_sd15_tile.pth"), "VAE": ("https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.safetensors?download=true", "models/VAE", "vae-ft-mse-840000-ema-pruned.safetensors"), } for model, (url, folder, filename) in models.items(): download_file(url, folder, filename) download_models() class LazyRealESRGAN: def __init__(self, device, scale): self.device = device self.scale = scale self.model = None def load_model(self): if self.model is None: self.model = RealESRGAN(self.device, scale=self.scale) self.model.load_weights(f'models/upscalers/RealESRGAN_x{self.scale}.pth', download=False) def predict(self, img): self.load_model() return self.model.predict(img) # Initialize the lazy models lazy_realesrgan_x2 = LazyRealESRGAN(device, scale=2) lazy_realesrgan_x4 = LazyRealESRGAN(device, scale=4) def resize_and_upscale(input_image, resolution): scale = 2 if resolution == 2048: init_w = 1024 elif resolution == 2560: init_w = 1280 elif resolution == 3072: init_w = 1536 else: init_w = 1024 scale = 4 input_image = input_image.convert("RGB") W, H = input_image.size k = float(init_w) / min(H, W) H *= k W *= k H = int(round(H / 64.0)) * 64 W = int(round(W / 64.0)) * 64 img = input_image.resize((W, H), resample=Image.LANCZOS) model = RealESRGAN(device, scale=scale) model.load_weights(f'models/upscalers/RealESRGAN_x{scale}.pth', download=False) img = model.predict(img) if scale == 2: img = lazy_realesrgan_x2.predict(img) else: img = lazy_realesrgan_x4.predict(img) return img def calculate_brightness_factors(hdr_intensity): factors = [1.0] * 9 if hdr_intensity > 0: factors = [1.0 - 0.9 * hdr_intensity, 1.0 - 0.7 * hdr_intensity, 1.0 - 0.45 * hdr_intensity, 1.0 - 0.25 * hdr_intensity, 1.0, 1.0 + 0.2 * hdr_intensity, 1.0 + 0.4 * hdr_intensity, 1.0 + 0.6 * hdr_intensity, 1.0 + 0.8 * hdr_intensity] return factors def pil_to_cv(pil_image): return cv2.cvtColor(np.array(pil_image), cv2.COLOR_RGB2BGR) def adjust_brightness(cv_image, factor): hsv_image = cv2.cvtColor(cv_image, cv2.COLOR_BGR2HSV) h, s, v = cv2.split(hsv_image) v = np.clip(v * factor, 0, 255).astype('uint8') adjusted_hsv = cv2.merge([h, s, v]) return cv2.cvtColor(adjusted_hsv, cv2.COLOR_HSV2BGR) def create_hdr_effect(original_image, hdr): cv_original = pil_to_cv(original_image) brightness_factors = calculate_brightness_factors(hdr) images = [adjust_brightness(cv_original, factor) for factor in brightness_factors] merge_mertens = cv2.createMergeMertens() hdr_image = merge_mertens.process(images) hdr_image_8bit = np.clip(hdr_image * 255, 0, 255).astype('uint8') hdr_image_pil = Image.fromarray(cv2.cvtColor(hdr_image_8bit, cv2.COLOR_BGR2RGB)) return hdr_image_pil class ImageProcessor: def __init__(self): self.pipe = self.setup_pipeline() def setup_pipeline(self): controlnet = ControlNetModel.from_single_file( "models/ControlNet/control_v11f1e_sd15_tile.pth", torch_dtype=torch.float16 ) safety_checker = StableDiffusionSafetyChecker.from_pretrained("CompVis/stable-diffusion-safety-checker") model_path = "models/models/Stable-diffusion/juggernaut_reborn.safetensors" pipe = StableDiffusionControlNetImg2ImgPipeline.from_single_file( model_path, controlnet=controlnet, torch_dtype=torch.float16, use_safetensors=True, safety_checker=safety_checker ) vae = AutoencoderKL.from_single_file( "models/VAE/vae-ft-mse-840000-ema-pruned.safetensors", torch_dtype=torch.float16 ) pipe.vae = vae pipe.load_textual_inversion("models/embeddings/verybadimagenegative_v1.3.pt") pipe.load_textual_inversion("models/embeddings/JuggernautNegative-neg.pt") pipe.load_lora_weights("models/Lora/SDXLrender_v2.0.safetensors") pipe.fuse_lora(lora_scale=0.5) pipe.load_lora_weights("models/Lora/more_details.safetensors") pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config) pipe.enable_freeu(s1=0.9, s2=0.2, b1=1.3, b2=1.4) return pipe def process_image(self, input_image, prompt, negative_prompt, resolution=2048, num_inference_steps=50, guidance_scale=3, strength=0.35, hdr=0): condition_image = resize_and_upscale(input_image, resolution) condition_image = create_hdr_effect(condition_image, hdr) result = self.pipe( prompt=prompt, negative_prompt=negative_prompt, image=condition_image, control_image=condition_image, width=condition_image.size[0], height=condition_image.size[1], strength=strength, num_inference_steps=num_inference_steps, guidance_scale=guidance_scale, generator=torch.manual_seed(0), ).images[0] return result image_processor = ImageProcessor() @spaces.GPU def gradio_process_image(input_image, resolution, num_inference_steps, strength, hdr, guidance_scale): image_processor.pipe = image_processor.pipe.to(device) image_processor.pipe.unet.set_attn_processor(AttnProcessor2_0()) prompt = "masterpiece, best quality, highres" negative_prompt = "low quality, normal quality, ugly, blurry, blur, lowres, bad anatomy, bad hands, cropped, worst quality, verybadimagenegative_v1.3, JuggernautNegative-neg" result = image_processor.process_image(input_image, prompt, negative_prompt, resolution, num_inference_steps, guidance_scale, strength, hdr) return result # Gradio interface with gr.Blocks() as demo: gr.Markdown("# Image Enhancement with Stable Diffusion") with gr.Row(): with gr.Column(): input_image = gr.Image(type="pil", label="Input Image") run_button = gr.Button("Enhance Image") with gr.Column(): output_image = gr.Image(type="pil", label="Enhanced Image") with gr.Accordion("Advanced Options", open=False): resolution = gr.Slider(minimum=512, maximum=2048, value=1024, step=64, label="Resolution") num_inference_steps = gr.Slider(minimum=1, maximum=100, value=50, step=1, label="Number of Inference Steps") strength = gr.Slider(minimum=0, maximum=1, value=0.35, step=0.05, label="Strength") hdr = gr.Slider(minimum=0, maximum=1, value=0, step=0.1, label="HDR Effect") guidance_scale = gr.Slider(minimum=0, maximum=20, value=3, step=0.5, label="Guidance Scale") run_button.click(fn=gradio_process_image, inputs=[input_image, resolution, num_inference_steps, strength, hdr, guidance_scale], outputs=output_image) demo.launch(share=True)