app.py

import gradio as gr
import torch
import modin.pandas as pd
from diffusers import DiffusionPipeline 

device = "cuda" if torch.cuda.is_available() else "cpu"
if torch.cuda.is_available():
    PYTORCH_CUDA_ALLOC_CONF={'max_split_size_mb': 6000}
    torch.cuda.max_memory_allocated(device=device)
    torch.cuda.empty_cache()
    pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
    pipe.enable_xformers_memory_efficient_attention()
    pipe = pipe.to(device)
    torch.cuda.empty_cache()
    refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True, torch_dtype=torch.float16, variant="fp16")
    refiner.enable_xformers_memory_efficient_attention()
    refiner.enable_sequential_cpu_offload()
else: 
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", use_safetensors=True)
pipe = pipe.to(device)
refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True)
refiner = refiner.to(device)

def genie (prompt, negative_prompt, scale, steps, seed):
     generator = torch.Generator(device=device).manual_seed(seed)
     int_image = pipe(prompt, negative_prompt=negative_prompt, num_inference_steps=steps, guidance_scale=scale, num_images_per_prompt=1, generator=generator, width=768, height=768, output_type="latent").images 
     image = refiner(prompt=prompt, negative_prompt=negative_prompt, image=int_image).images[0]
     return image
    
gr.Interface(fn=genie, inputs=[gr.Textbox(label='What you want the AI to generate. 77 Token Limit.'), gr.Textbox(label='What you Do Not want the AI to generate.'), gr.Slider(1, 15, 10), gr.Slider(25, maximum=50, value=25, step=1), gr.Slider(minimum=1, step=1, maximum=999999999999999999, randomize=True)], outputs='image', title="Stable Diffusion XL 1.0 CPU", description="SDXL 1.0 CPU. <b>WARNING:</b> Extremely Slow. 65s/Iteration. Expect 25-50mins an image for 25-50 iterations respectively.", article = "Code Monkey: <a href=\"https://huggingface.co/Manjushri\">Manjushri</a>").launch(debug=True, max_threads=80)