MinDalle_StableDiff/scripts/stable_diff.py

132 lines
4.4 KiB
Python

import json
import os
import shutil
from argparse import ArgumentParser
import time
from time import gmtime, strftime
from PIL import Image
import torch
from torch import autocast
from tqdm.auto import tqdm
import numpy as np
import piexif
import piexif.helper
from diffusers import (
DDIMScheduler,
#PNDMScheduler,
)
from diffusers import StableDiffusionImg2ImgPipeline
t = torch.cuda.get_device_properties(0).total_memory
if t <=8500000000:
print("Not enough GPU memory to generate pictures")
else:
file1 = open("prompt.txt","r+")
text = file1.read()
print(text)
##Generating with stable diffusion
device = "cuda"
model_path = "CompVis/stable-diffusion-v1-4"
# Using DDIMScheduler as anexample,this also works with PNDMScheduler
# uncomment this line if you want to use it.
#scheduler = PNDMScheduler.from_config(model_path, subfolder="scheduler", use_auth_token=True)
scheduler = DDIMScheduler(beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", clip_sample=False, set_alpha_to_one=False)
pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
model_path,
scheduler=scheduler,
revision="fp16",
torch_dtype=torch.float16,
use_auth_token=True
).to(device)
if t <= 10500000000:
pipe.enable_attention_slicing()
def dummy_checker(images, **kwargs):
return images, False
pipe.safety_checker = dummy_checker
def preprocess(image):
w, h = image.size
w, h = map(lambda x: x - x % 32, (w, h)) # resize to integer multiple of 32
image = image.resize((w, h), Image.Resampling.LANCZOS)
image = np.array(image).astype(np.float32) / 255.0
image = image[None].transpose(0, 3, 1, 2)
image = torch.from_numpy(image)
return 2.*image - 1.
path_img = []
startStrength = 0.86
deltaStrength = 0.02
endStrength = 0.941
startScale = 7.5
deltaScale = 2.5
endScale = 15.0
startSeed = 1022
endSeed = 1024
directory_in = "./data/input"
if not os.path.exists(directory_in):
os.makedirs(directory_in)
for root, subdirectories, files in os.walk(directory_in):
for filename in files:
if filename.endswith(".png"):
path_img.append(os.path.join(root, filename))
print("Found " +str(len(path_img)) +" pictures")
start_time = time.time()
counterr=0
allwork=0
directory="./data/out/" + strftime("%Y-%m-%d_%H-%M-%S", gmtime()) + "/"
if not os.path.exists(directory):
os.makedirs(directory)
with open(directory+"prompt.txt", 'w') as f:
f.write(text)
shutil.copytree(directory_in, directory+"input")
for i in path_img:
print(i)
if not os.path.exists(directory+str(counterr)):
os.makedirs(directory+str(counterr))
init_img = Image.open(i)
init_img = init_img.resize((768, 512))
init_image = preprocess(init_img)
prompt = text
for seed in range(endSeed-startSeed+1):
generator = torch.Generator(device=device).manual_seed(startSeed+seed)
guidance_scale = startScale
while guidance_scale <= endScale:
strenght = startStrength
while strenght <= endStrength:
with autocast("cuda"):
image = pipe(prompt=prompt, init_image=init_image, strength=strenght, guidance_scale=guidance_scale, generator=generator)["sample"][0]
image.save(directory+str(counterr)+"/" + str(allwork) +".jpg")
exif_dict = piexif.load(directory+str(counterr)+"/" + str(allwork) +".jpg")
userCommentAsDict = {}
userCommentAsDict['Seed']=str(seed+startSeed)
userCommentAsDict['Strength']=str(strenght)
userCommentAsDict['Guidance_scale']=str(guidance_scale)
user_comment = piexif.helper.UserComment.dump(json.dumps(userCommentAsDict))
exif_dict["Exif"][piexif.ExifIFD.UserComment] = user_comment
exif_bytes = piexif.dump(exif_dict)
piexif.insert(exif_bytes, directory+str(counterr)+"/" + str(allwork) +".jpg")
allwork+=1
strenght+=deltaStrength
guidance_scale+=deltaScale
counterr+=1
print("Made " + str(allwork) + " pictures in " + str(time.time()-start_time) + " seconds")