app.py

import gradio as gr
import numpy as np
import random
from diffusers import DiffusionPipeline
import torch
from PIL import Image, ImageOps

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

def infer(prompt_part1, color, dress_type, front_design, back_design, prompt_part5, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
    front_prompt = f"front view of {prompt_part1} {color} colored plain {dress_type} with {front_design} design, {prompt_part5}"
    back_prompt = f"back view of {prompt_part1} {color} colored plain {dress_type} with {back_design} design, {prompt_part5}"
    
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
        
    generator = torch.Generator().manual_seed(seed)
    
    front_image = pipe(
        prompt=front_prompt, 
        negative_prompt=negative_prompt,
        guidance_scale=guidance_scale, 
        num_inference_steps=num_inference_steps, 
        width=width, 
        height=height,
        generator=generator
    ).images[0]
    
    back_image = pipe(
        prompt=back_prompt, 
        negative_prompt=negative_prompt,
        guidance_scale=guidance_scale, 
        num_inference_steps=num_inference_steps, 
        width=width, 
        height=height,
        generator=generator
    ).images[0]
    
    return front_image, back_image

examples = [
    ["red", "t-shirt", "yellow stripes", "polka dots"],
    ["blue", "hoodie", "minimalist", "abstract art"],
    ["red", "sweat shirt", "geometric design", "plain"],
]

if torch.cuda.is_available():
    power_device = "GPU"
else:
    power_device = "CPU"

def edit_image(img_data, operation, *args):
    image = Image.open(img_data)
    
    if operation == "rotate":
        angle = int(args[0])
        image = image.rotate(angle, expand=True)
    elif operation == "crop":
        left, top, right, bottom = map(int, args)
        image = image.crop((left, top, right, bottom))
    elif operation == "resize":
        width, height = map(int, args)
        image = image.resize((width, height))
    elif operation == "flip":
        if args[0] == "horizontal":
            image = ImageOps.mirror(image)
        else:
            image = ImageOps.flip(image)
    
    return image

with gr.Blocks() as demo:
    
    with gr.Column():
        gr.Markdown(f"""
        # GenZ Couture
        Currently running on {power_device}.
        """)
        
        prompt_part1 = gr.Textbox(value="a single", label="Prompt Part 1")
        prompt_part2 = gr.Textbox(label="color", placeholder="color (e.g., red, blue)")
        prompt_part3 = gr.Textbox(label="dress_type", placeholder="dress_type (e.g., t-shirt, hoodie)")
        prompt_part4_front = gr.Textbox(label="front design", placeholder="front design")
        prompt_part4_back = gr.Textbox(label="back design", placeholder="back design")
        prompt_part5 = gr.Textbox(value="hanging on the plain wall", label="Prompt Part 5")
        
        run_button = gr.Button("Generate Designs")

        front_result = gr.Image(label="Front View Result", type="pil", interactive=True)
        back_result = gr.Image(label="Back View Result", type="pil", interactive=True)

        gr.Examples(examples=examples, inputs=[prompt_part2, prompt_part3, prompt_part4_front, prompt_part4_back])

    run_button.click(
        fn=infer,
        inputs=[prompt_part1, prompt_part2, prompt_part3, prompt_part4_front, prompt_part4_back, prompt_part5],
        outputs=[front_result, back_result]
    )

    gr.Markdown("## Creative Touch")

    edit_operation = gr.Dropdown(choices=["rotate", "crop", "resize", "flip"], label="Edit Operation")
    edit_args = gr.Textbox(label="Edit Arguments (comma-separated)", placeholder="For rotate: angle, For crop: left,top,right,bottom, For resize: width,height, For flip: horizontal/vertical")
    
    edit_button = gr.Button("Edit Front Design")

    edit_button.click(
        fn=lambda img_data, operation, args: edit_image(img_data, operation, *args.split(',')),
        inputs=[front_result, edit_operation, edit_args],
        outputs=[front_result]
    )

demo.queue().launch()