mirror of
https://github.com/sd-webui/stable-diffusion-webui.git
synced 2024-12-14 23:02:00 +03:00
010b27ce9a
* repo-merge * cutdown size * Create setup.py * webui.cmd * ldm * Update environment.yaml * Update environment.yaml
297 lines
8.2 KiB
Python
297 lines
8.2 KiB
Python
import argparse, os, sys, glob, random
|
|
import torch
|
|
import numpy as np
|
|
import copy
|
|
from omegaconf import OmegaConf
|
|
from PIL import Image
|
|
from tqdm import tqdm, trange
|
|
from itertools import islice
|
|
from einops import rearrange
|
|
from torchvision.utils import make_grid
|
|
import time
|
|
from pytorch_lightning import seed_everything
|
|
from torch import autocast
|
|
from contextlib import contextmanager, nullcontext
|
|
from ldm.util import instantiate_from_config
|
|
|
|
|
|
def chunk(it, size):
|
|
it = iter(it)
|
|
return iter(lambda: tuple(islice(it, size)), ())
|
|
|
|
|
|
def load_model_from_config(ckpt, verbose=False):
|
|
print(f"Loading model from {ckpt}")
|
|
pl_sd = torch.load(ckpt, map_location="cpu")
|
|
if "global_step" in pl_sd:
|
|
print(f"Global Step: {pl_sd['global_step']}")
|
|
sd = pl_sd["state_dict"]
|
|
return sd
|
|
|
|
|
|
config = "optimizedSD/v1-inference.yaml"
|
|
ckpt = "models/ldm/stable-diffusion-v1/model.ckpt"
|
|
device = "cuda"
|
|
|
|
parser = argparse.ArgumentParser()
|
|
|
|
parser.add_argument(
|
|
"--prompt",
|
|
type=str,
|
|
nargs="?",
|
|
default="a painting of a virus monster playing guitar",
|
|
help="the prompt to render"
|
|
)
|
|
parser.add_argument(
|
|
"--outdir",
|
|
type=str,
|
|
nargs="?",
|
|
help="dir to write results to",
|
|
default="outputs/txt2img-samples"
|
|
)
|
|
parser.add_argument(
|
|
"--skip_grid",
|
|
action='store_true',
|
|
help="do not save a grid, only individual samples. Helpful when evaluating lots of samples",
|
|
)
|
|
parser.add_argument(
|
|
"--skip_save",
|
|
action='store_true',
|
|
help="do not save individual samples. For speed measurements.",
|
|
)
|
|
parser.add_argument(
|
|
"--ddim_steps",
|
|
type=int,
|
|
default=50,
|
|
help="number of ddim sampling steps",
|
|
)
|
|
|
|
parser.add_argument(
|
|
"--fixed_code",
|
|
action='store_true',
|
|
help="if enabled, uses the same starting code across samples ",
|
|
)
|
|
parser.add_argument(
|
|
"--ddim_eta",
|
|
type=float,
|
|
default=0.0,
|
|
help="ddim eta (eta=0.0 corresponds to deterministic sampling",
|
|
)
|
|
parser.add_argument(
|
|
"--n_iter",
|
|
type=int,
|
|
default=1,
|
|
help="sample this often",
|
|
)
|
|
parser.add_argument(
|
|
"--H",
|
|
type=int,
|
|
default=512,
|
|
help="image height, in pixel space",
|
|
)
|
|
parser.add_argument(
|
|
"--W",
|
|
type=int,
|
|
default=512,
|
|
help="image width, in pixel space",
|
|
)
|
|
parser.add_argument(
|
|
"--C",
|
|
type=int,
|
|
default=4,
|
|
help="latent channels",
|
|
)
|
|
parser.add_argument(
|
|
"--f",
|
|
type=int,
|
|
default=8,
|
|
help="downsampling factor",
|
|
)
|
|
parser.add_argument(
|
|
"--n_samples",
|
|
type=int,
|
|
default=5,
|
|
help="how many samples to produce for each given prompt. A.k.a. batch size",
|
|
)
|
|
parser.add_argument(
|
|
"--n_rows",
|
|
type=int,
|
|
default=0,
|
|
help="rows in the grid (default: n_samples)",
|
|
)
|
|
parser.add_argument(
|
|
"--scale",
|
|
type=float,
|
|
default=7.5,
|
|
help="unconditional guidance scale: eps = eps(x, empty) + scale * (eps(x, cond) - eps(x, empty))",
|
|
)
|
|
parser.add_argument(
|
|
"--from-file",
|
|
type=str,
|
|
help="if specified, load prompts from this file",
|
|
)
|
|
parser.add_argument(
|
|
"--seed",
|
|
type=int,
|
|
default=42,
|
|
help="the seed (for reproducible sampling)",
|
|
)
|
|
parser.add_argument(
|
|
"--small_batch",
|
|
action='store_true',
|
|
help="Reduce inference time when generate a smaller batch of images",
|
|
)
|
|
parser.add_argument(
|
|
"--precision",
|
|
type=str,
|
|
help="evaluate at this precision",
|
|
choices=["full", "autocast"],
|
|
default="autocast"
|
|
)
|
|
opt = parser.parse_args()
|
|
|
|
tic = time.time()
|
|
os.makedirs(opt.outdir, exist_ok=True)
|
|
outpath = opt.outdir
|
|
|
|
sample_path = os.path.join(outpath, "samples", "_".join(opt.prompt.split())[:255])
|
|
os.makedirs(sample_path, exist_ok=True)
|
|
base_count = len(os.listdir(sample_path))
|
|
grid_count = len(os.listdir(outpath)) - 1
|
|
seed_everything(opt.seed)
|
|
|
|
sd = load_model_from_config(f"{ckpt}")
|
|
li = []
|
|
lo = []
|
|
for key, value in sd.items():
|
|
sp = key.split('.')
|
|
if(sp[0]) == 'model':
|
|
if('input_blocks' in sp):
|
|
li.append(key)
|
|
elif('middle_block' in sp):
|
|
li.append(key)
|
|
elif('time_embed' in sp):
|
|
li.append(key)
|
|
else:
|
|
lo.append(key)
|
|
for key in li:
|
|
sd['model1.' + key[6:]] = sd.pop(key)
|
|
for key in lo:
|
|
sd['model2.' + key[6:]] = sd.pop(key)
|
|
|
|
config = OmegaConf.load(f"{config}")
|
|
config.modelUNet.params.ddim_steps = opt.ddim_steps
|
|
|
|
if opt.small_batch:
|
|
config.modelUNet.params.small_batch = True
|
|
else:
|
|
config.modelUNet.params.small_batch = False
|
|
|
|
|
|
|
|
model = instantiate_from_config(config.modelUNet)
|
|
_, _ = model.load_state_dict(sd, strict=False)
|
|
model.eval()
|
|
|
|
modelCS = instantiate_from_config(config.modelCondStage)
|
|
_, _ = modelCS.load_state_dict(sd, strict=False)
|
|
modelCS.eval()
|
|
|
|
modelFS = instantiate_from_config(config.modelFirstStage)
|
|
_, _ = modelFS.load_state_dict(sd, strict=False)
|
|
modelFS.eval()
|
|
|
|
if opt.precision == "autocast":
|
|
model.half()
|
|
modelCS.half()
|
|
|
|
start_code = None
|
|
if opt.fixed_code:
|
|
start_code = torch.randn([opt.n_samples, opt.C, opt.H // opt.f, opt.W // opt.f], device=device)
|
|
|
|
|
|
batch_size = opt.n_samples
|
|
n_rows = opt.n_rows if opt.n_rows > 0 else batch_size
|
|
if not opt.from_file:
|
|
prompt = opt.prompt
|
|
assert prompt is not None
|
|
data = [batch_size * [prompt]]
|
|
|
|
else:
|
|
print(f"reading prompts from {opt.from_file}")
|
|
with open(opt.from_file, "r") as f:
|
|
data = f.read().splitlines()
|
|
data = list(chunk(data, batch_size))
|
|
|
|
|
|
precision_scope = autocast if opt.precision=="autocast" else nullcontext
|
|
with torch.no_grad():
|
|
|
|
all_samples = list()
|
|
for n in trange(opt.n_iter, desc="Sampling"):
|
|
for prompts in tqdm(data, desc="data"):
|
|
with precision_scope("cuda"):
|
|
modelCS.to(device)
|
|
uc = None
|
|
if opt.scale != 1.0:
|
|
uc = modelCS.get_learned_conditioning(batch_size * [""])
|
|
if isinstance(prompts, tuple):
|
|
prompts = list(prompts)
|
|
|
|
c = modelCS.get_learned_conditioning(prompts)
|
|
shape = [opt.C, opt.H // opt.f, opt.W // opt.f]
|
|
mem = torch.cuda.memory_allocated()/1e6
|
|
modelCS.to("cpu")
|
|
while(torch.cuda.memory_allocated()/1e6 >= mem):
|
|
time.sleep(1)
|
|
|
|
|
|
samples_ddim = model.sample(S=opt.ddim_steps,
|
|
conditioning=c,
|
|
batch_size=opt.n_samples,
|
|
shape=shape,
|
|
verbose=False,
|
|
unconditional_guidance_scale=opt.scale,
|
|
unconditional_conditioning=uc,
|
|
eta=opt.ddim_eta,
|
|
x_T=start_code)
|
|
|
|
modelFS.to(device)
|
|
print("saving images")
|
|
for i in range(batch_size):
|
|
|
|
x_samples_ddim = modelFS.decode_first_stage(samples_ddim[i].unsqueeze(0))
|
|
x_sample = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
|
|
# for x_sample in x_samples_ddim:
|
|
x_sample = 255. * rearrange(x_sample[0].cpu().numpy(), 'c h w -> h w c')
|
|
Image.fromarray(x_sample.astype(np.uint8)).save(
|
|
os.path.join(sample_path, f"{base_count:05}.png"))
|
|
base_count += 1
|
|
|
|
|
|
mem = torch.cuda.memory_allocated()/1e6
|
|
modelFS.to("cpu")
|
|
while(torch.cuda.memory_allocated()/1e6 >= mem):
|
|
time.sleep(1)
|
|
|
|
# if not opt.skip_grid:
|
|
# all_samples.append(x_samples_ddim)
|
|
del samples_ddim
|
|
print("memory_final = ", torch.cuda.memory_allocated()/1e6)
|
|
|
|
# if not skip_grid:
|
|
# # additionally, save as grid
|
|
# grid = torch.stack(all_samples, 0)
|
|
# grid = rearrange(grid, 'n b c h w -> (n b) c h w')
|
|
# grid = make_grid(grid, nrow=n_rows)
|
|
|
|
# # to image
|
|
# grid = 255. * rearrange(grid, 'c h w -> h w c').cpu().numpy()
|
|
# Image.fromarray(grid.astype(np.uint8)).save(os.path.join(outpath, f'grid-{grid_count:04}.png'))
|
|
# grid_count += 1
|
|
|
|
toc = time.time()
|
|
|
|
time_taken = (toc-tic)/60.0
|
|
|
|
print(("Your samples are ready in {0:.2f} minutes and waiting for you here \n" + sample_path).format(time_taken)) |