from diffusers import AutoPipelineForText2Image, DiffusionPipeline, UniPCMultistepScheduler, EulerAncestralDiscreteScheduler
import torch
import gradio as gr
from PIL import Image
import os, random
import PIL.Image
from transformers import pipeline
from diffusers.utils import load_image
from accelerate import Accelerator

accelerator = Accelerator()
apol=[]
pipe = accelerator.prepare(DiffusionPipeline.from_single_file("https://huggingface.co/lllyasviel/fav_models/fav/DreamShaper_8_pruned.safetensors",torch_dtype=torch.float32, variant=None, use_safetensors=True, safety_checker=None))
##pipe.scheduler = accelerator.prepare(EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config))
pipe.unet.to(memory_format=torch.channels_last)
pipe = accelerator.prepare(pipe.to("cpu"))
def plex(prompt,neg_prompt,stips,scaly,nut):
    apol=[]
    if nut == 0:
        nm = random.randint(1, 2147483616)
        while nm % 32 != 0:
            nm = random.randint(1, 2147483616)
    else:
        nm=nut
    generator = torch.Generator(device="cpu").manual_seed(nm)
    image = pipe(prompt=prompt, negative_prompt=neg_prompt, generator=generator, num_inference_steps=stips, guidance_scale=scaly)
    for a, imze in enumerate(image["images"]):
        apol.append(imze)
    return apol

iface = gr.Interface(fn=plex,inputs=[gr.Textbox(label="Prompt"), gr.Textbox(label="negative_prompt", value="low quality, bad quality"), gr.Slider(label="num inference steps",minimum=1,step=1,maximum=20,value=15), gr.Slider(label="guidance_scale",minimum=1,step=1,maximum=10,value=7),gr.Slider(label="manual seed (leave 0 for random)",minimum=0,step=32,maximum=2147483616,value=0)],outputs=gr.Gallery(label="Generated Output Image", columns=1), title="Txt2Img_DrmDrp_v1_SD",description="Running on cpu, very slow!")
iface.queue(max_size=1,api_open=False)
iface.launch(max_threads=1)