app.py

import gradio as gr

models =["CompVis/stable-diffusion-v1-4", "runwayml/stable-diffusion-v1-5", "stabilityai/stable-diffusion-2-1", "stabilityai/stable-diffusion-2-1-base"]

model_1=models[1]
model_2=models[2]
model_3=models[3]
model_4=models[4]

gr.Interface.load(f"models/{model_1}",live=False,preprocess=True, postprocess=False).launch()


#import diffusers
#import streamlit as st
#device = "cpu"
#from diffusers import StableDiffusionPipeline
#pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", revision = "fp16", use_auth_token = st.secrets["USER_TOKEN"])
#pipe = pipe.to("cpu")
#from PIL import Image
#import torch
#def StableDiffusionPipeline (prompt, Guide, iSteps, seed):
#    generator = torch.Generator("cpu").manual_seed(seed)
#    image = pipe(prompt, num_inference_steps = iSteps, guidence_scale = Guide).images[0]
#    return image
#iface = gr.Interface(fn = StableDiffusionPipeline, inputs = [
#    gr.Textbox(label = 'Prompt Input Text'),
#    gr.Slider(2, 15, value = 7, label = 'Guidence Scale'),
#    gr.Slider(10, 100, value = 25, step = 1, label = 'Number of Iterations'),
#    gr.Slider(
#        label = "Seed",
#        minimum = 0,
#        maximum = 2147483647,
#        step = 1,
#        randomize = True)
#    ],
#    outputs = 'image')
#iface.launch()