import gradio as gr import torch import modin.pandas as pd from PIL import Image from io import BytesIO from diffusers import StableDiffusionLatentUpscalePipeline, StableDiffusionUpscalePipeline device = "cuda" if torch.cuda.is_available() else "cpu" # Define the models model_2x = "stabilityai/sd-x2-latent-upscaler" model_4x = "stabilityai/stable-diffusion-x4-upscaler" # Load the models sd_2_0_2x = StableDiffusionLatentUpscalePipeline.from_pretrained(model_2x, torch_dtype=torch.float16, revision="fp16") if torch.cuda.is_available() else StableDiffusionLatentUpscalePipeline.from_pretrained(model_2x) sd_2_1_4x = StableDiffusionUpscalePipeline.from_pretrained(model_4x, torch_dtype=torch.float16, revision="fp16") if torch.cuda.is_available() else StableDiffusionUpscalePipeline.from_pretrained(model_4x) # Define the function that will be called when the interface is used def upscale_image(model, input_image, prompt, guidance): # Convert the image generator = torch.manual_seed(999999) input_image = Image.open(input_image).convert("RGB") # Upscale the image using the selected model if model == "SD 2.1 4x Upscaler": low_res_img = input_image.resize((128, 128)) upscaled_image = sd_2_1_4x(prompt, image=low_res_img, num_inference_steps=5, guidance_scale=guidance).images[0] else: upscaled_image = sd_2_0_2x(prompt, image=input_image, num_inference_steps=5, guidance_scale=guidance).images[0] # Return the upscaled image return upscaled_image # Define the Gradio interface gr.Interface( fn=upscale_image, inputs=[gr.Radio(["SD 2.0 2x Latent Upscaler", "SD 2.1 4x Upscaler"], label="Models:"), gr.Image(type="filepath", label = "Raw Image"), gr.Textbox(label='Guide the AI Upscaling'), gr.Slider(minimum=0, value=0, maximum=3, label='Guidance Scale')], outputs=gr.Image(type="filepath", label = "Upscaled Image"), title="SD Image Upscaler", description="Upscale an image using either the SD 2.0 2x Latent Upscaler or the SD 2.1 4x Upscaler. Use the 4x Upscaler for images lower than 512x512. Use the 2x Upscaler for images 512x512 to 768x768" ).launch(debug=True)