app.py

import gradio as gr
import numpy as np
import random
from diffusers import DiffusionPipeline, StableDiffusionImg2ImgPipeline
from transformers.utils.hub import move_cache
import torch
from PIL import Image

move_cache()

device = "cuda" if torch.cuda.is_available() else "cpu"

# Check if a GPU is available and set the appropriate torch_dtype and device
if torch.cuda.is_available():
    torch_dtype = torch.float16
    device = "cuda"
else:
    torch_dtype = torch.float32
    device = "cpu"


if torch.cuda.is_available():
    torch.cuda.max_memory_allocated(device=device)
    pipe = StableDiffusionImg2ImgPipeline.from_pretrained("Envvi/Inkpunk-Diffusion", torch_dtype=torch_dtype, safety_checker = None, requires_safety_checker = False)
    #pipe = DiffusionPipeline.from_pretrained("Envvi/Inkpunk-Diffusion", torch_dtype=torch.float16, variant="fp16")
    pipe.enable_xformers_memory_efficient_attention()
    pipe = pipe.to(device)
else: 
    pipe = StableDiffusionImg2ImgPipeline.from_pretrained("Envvi/Inkpunk-Diffusion", torch_dtype=torch_dtype, safety_checker = None, requires_safety_checker = False)
    pipe = pipe.to(device)

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024

def generate_image(uploaded_image):
    # Open the uploaded image
    image = Image.open(uploaded_image)        
    return output

def infer(init_img, prompt, negative_prompt, seed, width, height, guidance_scale, strength):
    
    generator = torch.Generator().manual_seed(seed)
    prompt = "nvinkpunk " + prompt
    
    image = pipe(
        image = init_img,
        prompt = prompt, 
        negative_prompt = negative_prompt,
        guidance_scale = guidance_scale, 
        strength = strength, 
        width = width, 
        height = height,
        generator = generator
    ).images[0] 
    
    return image

examples = [
    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
    "An astronaut riding a green horse",
    "A delicious ceviche cheesecake slice",
]

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"""
        # Image-to-Image Demo
        Currently running on {power_device}.
        """)


        with gr.Row():
            init_img = gr.Image(type="pil")

        with gr.Row():
            
            prompt = gr.Text(
                label="Prompt",
                show_label=False,
                max_lines=1,
                placeholder="Enter your prompt",
                container=False,
            )
            
            run_button = gr.Button("Run", scale=0)
        
        result = gr.Image(label="Result", show_label=False)

        with gr.Accordion("Advanced Settings", open=False):

            with gr.Row():
                    negative_prompt = gr.Text(
                    label="Negative prompt",
                    max_lines=1,
                    placeholder="Enter a negative prompt",
                    visible=False,
                )
            
            with gr.Row():
                    seed = gr.Slider(
                    label="Seed",
                    minimum=0,
                    maximum=1024,
                    step=1,
                    value=0,
                )            
            
            with gr.Row():
                
                width = gr.Slider(
                    label="Width",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,
                )
                
                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,
                )
            
            with gr.Row():
                
                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.0,
                    maximum=10.0,
                    step=0.1,
                    value=7.5,
                )
                
                strength = gr.Slider(
                    label="strength",
                    minimum=0.0,
                    maximum=1.0,
                    step=0.1,
                    value=0.5,
                )
        
        gr.Examples(
            examples = examples,
            inputs = [prompt]
        )

    run_button.click(
        fn = infer,
        inputs = [init_img, prompt, negative_prompt, seed, width, height, guidance_scale, strength],
        outputs = [result]
    )

demo.queue().launch()