import gradio as gr import numpy as np import random from diffusers import DiffusionPipeline import torch from PIL import Image import matplotlib.pyplot as plt device = "cuda" if torch.cuda.is_available() else "cpu" if torch.cuda.is_available(): torch.cuda.max_memory_allocated(device=device) pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True) pipe.enable_xformers_memory_efficient_attention() pipe = pipe.to(device) else: pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True) pipe = pipe.to(device) MAX_SEED = np.iinfo(np.int32).max MAX_IMAGE_SIZE = 1024 # Function to apply FFT and return an image def apply_fft(image: Image.Image): # Convert the image to grayscale for FFT (can be extended for color images too) image_gray = image.convert("L") # Convert the image to numpy array image_array = np.array(image_gray) # Apply 2D FFT fft_image = np.fft.fft2(image_array) fft_shifted = np.fft.fftshift(fft_image) # Shift the zero frequency to the center # Magnitude spectrum for visualization magnitude_spectrum = 20 * np.log(np.abs(fft_shifted)) # Normalize magnitude spectrum to 0-255 for visualization magnitude_spectrum = np.interp(magnitude_spectrum, (magnitude_spectrum.min(), magnitude_spectrum.max()), (0, 255)) # Convert back to image fft_image_pil = Image.fromarray(magnitude_spectrum.astype(np.uint8)) return fft_image_pil def infer(prompt_part1, color, dress_type, design, prompt_part5, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps): prompt = f"{prompt_part1} {color} colored plain {dress_type} with {design} design, {prompt_part5}" if randomize_seed: seed = random.randint(0, MAX_SEED) generator = torch.Generator().manual_seed(seed) # Generate the image using the diffusion pipeline image = pipe( prompt=prompt, negative_prompt=negative_prompt, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps, width=width, height=height, generator=generator ).images[0] # Apply FFT post-processing to the generated image fft_image = apply_fft(image) return fft_image examples = [ "red, t-shirt, yellow stripes", "blue, hoodie, minimalist", "red, sweat shirt, geometric design", ] css = """ #col-container { margin: 0 auto; max-width: 520px; } """ if torch.cuda.is_available(): power_device = "GPU" else: power_device = "CPU" with gr.Blocks(css=css) as demo: with gr.Column(elem_id="col-container"): gr.Markdown(f""" # Text-to-Image Gradio Template with FFT Post-Processing Currently running on {power_device}. """) with gr.Row(): prompt_part1 = gr.Textbox( value="a single", label="Prompt Part 1", show_label=False, interactive=False, container=False, elem_id="prompt_part1", visible=False, ) prompt_part2 = gr.Textbox( label="color", show_label=False, max_lines=1, placeholder="color (e.g., color category)", container=False, ) prompt_part3 = gr.Textbox( label="dress_type", show_label=False, max_lines=1, placeholder="dress_type (e.g., t-shirt, sweatshirt, shirt, hoodie)", container=False, ) prompt_part4 = gr.Textbox( label="design", show_label=False, max_lines=1, placeholder="design", container=False, ) prompt_part5 = gr.Textbox( value="hanging on the plain wall", label="Prompt Part 5", show_label=False, interactive=False, container=False, elem_id="prompt_part5", visible=False, ) run_button = gr.Button("Run", scale=0) result = gr.Image(label="Result", show_label=False) with gr.Accordion("Advanced Settings", open=False): negative_prompt = gr.Textbox( label="Negative prompt", max_lines=1, placeholder="Enter a negative prompt", visible=False, ) seed = gr.Slider( label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0, ) randomize_seed = gr.Checkbox(label="Randomize seed", value=True) with gr.Row(): width = gr.Slider( label="Width", minimum=256, maximum=MAX_IMAGE_SIZE, step=32, value=512, ) height = gr.Slider( label="Height", minimum=256, maximum=MAX_IMAGE_SIZE, step=32, value=512, ) with gr.Row(): guidance_scale = gr.Slider( label="Guidance scale", minimum=0.0, maximum=10.0, step=0.1, value=0.0, ) num_inference_steps = gr.Slider( label="Number of inference steps", minimum=1, maximum=12, step=1, value=2, ) gr.Examples( examples=examples, inputs=[prompt_part2] ) run_button.click( fn=infer, inputs=[prompt_part1, prompt_part2, prompt_part3, prompt_part4, prompt_part5, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps], outputs=[result] ) demo.queue().launch()