import streamlit as st
import cv2 as cv
import time
import torch
from diffusers import StableDiffusionPipeline

# "stabilityai/stable-diffusion-2-1-base"
# "CompVis/stable-diffusion-v1-4"
def create_model(loc = "stabilityai/stable-diffusion-2-1-base", mch = 'cpu'):
    pipe = StableDiffusionPipeline.from_pretrained(loc)
    pipe = pipe.to(mch)
    return pipe

t2i = st.title("""
# Text2Image
###### `CHECK "Create_Update_Model"` :
- `FIRST RUN OF THE CODE`
- `CHANGING MODEL`""")

the_type = st.selectbox("Model Name",("stabilityai/stable-diffusion-2-1-base",
                                      "CompVis/stable-diffusion-v1-4"))
create = st.button("Create The Model")

if create:
    st.session_state.t2m_mod = create_model(loc=the_type)


prom = st.text_input("# Prompt",'')

c1,c2,c3 = st.columns([1,1,3])
c4,c5 = st.columns(2)
with c1:
  bu_1 = st.text_input("Seed",'999')
with c2:
  bu_2 = st.text_input("Steps",'12')
with c3:
  bu_3 = st.text_input("Number of Images",'1')
with c4:
  sl_1 = st.slider("Width",256,1024,128)
with c5:
  sl_2 = st.slider("hight",256,1024,128)

create = st.button("Imagine")
if create:
    generator = torch.Generator("cpu").manual_seed(int(bu_1))
    model = st.session_state.t2m_mod
    img = model(prom, width=int(sl_1), height=int(sl_2), num_inference_steps=int(bu_2), generator=generator).images[0]
    st.image(img)