thijn/Dreambooth-Stable-Diffusion
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

init

Browse Source
This commit is contained in:
Thijn
2022-09-28 21:11:28 +02:00
commit c68bd15bb8
98 changed files with 16302 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
scripts/download_first_stages.sh Normal file
View File

@@ -0,0 +1,41 @@
#!/bin/bash
wget -O models/first_stage_models/kl-f4/model.zip https://ommer-lab.com/files/latent-diffusion/kl-f4.zip
wget -O models/first_stage_models/kl-f8/model.zip https://ommer-lab.com/files/latent-diffusion/kl-f8.zip
wget -O models/first_stage_models/kl-f16/model.zip https://ommer-lab.com/files/latent-diffusion/kl-f16.zip
wget -O models/first_stage_models/kl-f32/model.zip https://ommer-lab.com/files/latent-diffusion/kl-f32.zip
wget -O models/first_stage_models/vq-f4/model.zip https://ommer-lab.com/files/latent-diffusion/vq-f4.zip
wget -O models/first_stage_models/vq-f4-noattn/model.zip https://ommer-lab.com/files/latent-diffusion/vq-f4-noattn.zip
wget -O models/first_stage_models/vq-f8/model.zip https://ommer-lab.com/files/latent-diffusion/vq-f8.zip
wget -O models/first_stage_models/vq-f8-n256/model.zip https://ommer-lab.com/files/latent-diffusion/vq-f8-n256.zip
wget -O models/first_stage_models/vq-f16/model.zip https://ommer-lab.com/files/latent-diffusion/vq-f16.zip
cd models/first_stage_models/kl-f4
unzip -o model.zip
cd ../kl-f8
unzip -o model.zip
cd ../kl-f16
unzip -o model.zip
cd ../kl-f32
unzip -o model.zip
cd ../vq-f4
unzip -o model.zip
cd ../vq-f4-noattn
unzip -o model.zip
cd ../vq-f8
unzip -o model.zip
cd ../vq-f8-n256
unzip -o model.zip
cd ../vq-f16
unzip -o model.zip
cd ../..

49
scripts/download_models.sh Normal file
View File

@@ -0,0 +1,49 @@
#!/bin/bash
wget -O models/ldm/celeba256/celeba-256.zip https://ommer-lab.com/files/latent-diffusion/celeba.zip
wget -O models/ldm/ffhq256/ffhq-256.zip https://ommer-lab.com/files/latent-diffusion/ffhq.zip
wget -O models/ldm/lsun_churches256/lsun_churches-256.zip https://ommer-lab.com/files/latent-diffusion/lsun_churches.zip
wget -O models/ldm/lsun_beds256/lsun_beds-256.zip https://ommer-lab.com/files/latent-diffusion/lsun_bedrooms.zip
wget -O models/ldm/text2img256/model.zip https://ommer-lab.com/files/latent-diffusion/text2img.zip
wget -O models/ldm/cin256/model.zip https://ommer-lab.com/files/latent-diffusion/cin.zip
wget -O models/ldm/semantic_synthesis512/model.zip https://ommer-lab.com/files/latent-diffusion/semantic_synthesis.zip
wget -O models/ldm/semantic_synthesis256/model.zip https://ommer-lab.com/files/latent-diffusion/semantic_synthesis256.zip
wget -O models/ldm/bsr_sr/model.zip https://ommer-lab.com/files/latent-diffusion/sr_bsr.zip
wget -O models/ldm/layout2img-openimages256/model.zip https://ommer-lab.com/files/latent-diffusion/layout2img_model.zip
wget -O models/ldm/inpainting_big/model.zip https://ommer-lab.com/files/latent-diffusion/inpainting_big.zip
cd models/ldm/celeba256
unzip -o celeba-256.zip
cd ../ffhq256
unzip -o ffhq-256.zip
cd ../lsun_churches256
unzip -o lsun_churches-256.zip
cd ../lsun_beds256
unzip -o lsun_beds-256.zip
cd ../text2img256
unzip -o model.zip
cd ../cin256
unzip -o model.zip
cd ../semantic_synthesis512
unzip -o model.zip
cd ../semantic_synthesis256
unzip -o model.zip
cd ../bsr_sr
unzip -o model.zip
cd ../layout2img-openimages256
unzip -o model.zip
cd ../inpainting_big
unzip -o model.zip
cd ../..

89
scripts/evaluate_model.py Normal file
View File

@@ -0,0 +1,89 @@
import argparse, os, sys, glob
sys.path.append(os.path.join(sys.path[0], '..'))
import torch
import numpy as np
from omegaconf import OmegaConf
from PIL import Image
from tqdm import tqdm, trange
from einops import rearrange
from torchvision.utils import make_grid
from ldm.util import instantiate_from_config
from ldm.models.diffusion.ddim import DDIMSampler
from ldm.models.diffusion.plms import PLMSSampler
from ldm.data.personalized import PersonalizedBase
from evaluation.clip_eval import LDMCLIPEvaluator
def load_model_from_config(config, ckpt, verbose=False):
print(f"Loading model from {ckpt}")
pl_sd = torch.load(ckpt, map_location="cpu")
sd = pl_sd["state_dict"]
model = instantiate_from_config(config.model)
m, u = model.load_state_dict(sd, strict=False)
if len(m) > 0 and verbose:
print("missing keys:")
print(m)
if len(u) > 0 and verbose:
print("unexpected keys:")
print(u)
model.cuda()
model.eval()
return model
if __name__ == "__main__":
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(
"--ckpt_path",
type=str,
default="/data/pretrained_models/ldm/text2img-large/model.ckpt",
help="Path to pretrained ldm text2img model")
parser.add_argument(
"--embedding_path",
type=str,
help="Path to a pre-trained embedding manager checkpoint")
parser.add_argument(
"--data_dir",
type=str,
help="Path to directory with images used to train the embedding vectors"
)
opt = parser.parse_args()
config = OmegaConf.load("configs/latent-diffusion/txt2img-1p4B-eval_with_tokens.yaml") # TODO: Optionally download from same location as ckpt and chnage this logic
model = load_model_from_config(config, opt.ckpt_path) # TODO: check path
model.embedding_manager.load(opt.embedding_path)
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
model = model.to(device)
evaluator = LDMCLIPEvaluator(device)
prompt = opt.prompt
data_loader = PersonalizedBase(opt.data_dir, size=256, flip_p=0.0)
images = [torch.from_numpy(data_loader[i]["image"]).permute(2, 0, 1) for i in range(data_loader.num_images)]
images = torch.stack(images, axis=0)
sim_img, sim_text = evaluator.evaluate(model, images, opt.prompt)
output_dir = os.path.join(opt.out_dir, prompt.replace(" ", "-"))
print("Image similarity: ", sim_img)
print("Text similarity: ", sim_text)

98
scripts/inpaint.py Normal file
View File

@@ -0,0 +1,98 @@
import argparse, os, sys, glob
from omegaconf import OmegaConf
from PIL import Image
from tqdm import tqdm
import numpy as np
import torch
from main import instantiate_from_config
from ldm.models.diffusion.ddim import DDIMSampler
def make_batch(image, mask, device):
image = np.array(Image.open(image).convert("RGB"))
image = image.astype(np.float32)/255.0
image = image[None].transpose(0,3,1,2)
image = torch.from_numpy(image)
mask = np.array(Image.open(mask).convert("L"))
mask = mask.astype(np.float32)/255.0
mask = mask[None,None]
mask[mask < 0.5] = 0
mask[mask >= 0.5] = 1
mask = torch.from_numpy(mask)
masked_image = (1-mask)*image
batch = {"image": image, "mask": mask, "masked_image": masked_image}
for k in batch:
batch[k] = batch[k].to(device=device)
batch[k] = batch[k]*2.0-1.0
return batch
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument(
"--indir",
type=str,
nargs="?",
help="dir containing image-mask pairs (`example.png` and `example_mask.png`)",
)
parser.add_argument(
"--outdir",
type=str,
nargs="?",
help="dir to write results to",
)
parser.add_argument(
"--steps",
type=int,
default=50,
help="number of ddim sampling steps",
)
opt = parser.parse_args()
masks = sorted(glob.glob(os.path.join(opt.indir, "*_mask.png")))
images = [x.replace("_mask.png", ".png") for x in masks]
print(f"Found {len(masks)} inputs.")
config = OmegaConf.load("models/ldm/inpainting_big/config.yaml")
model = instantiate_from_config(config.model)
model.load_state_dict(torch.load("models/ldm/inpainting_big/last.ckpt")["state_dict"],
strict=False)
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
model = model.to(device)
sampler = DDIMSampler(model)
os.makedirs(opt.outdir, exist_ok=True)
with torch.no_grad():
with model.ema_scope():
for image, mask in tqdm(zip(images, masks)):
outpath = os.path.join(opt.outdir, os.path.split(image)[1])
batch = make_batch(image, mask, device=device)
# encode masked image and concat downsampled mask
c = model.cond_stage_model.encode(batch["masked_image"])
cc = torch.nn.functional.interpolate(batch["mask"],
size=c.shape[-2:])
c = torch.cat((c, cc), dim=1)
shape = (c.shape[1]-1,)+c.shape[2:]
samples_ddim, _ = sampler.sample(S=opt.steps,
conditioning=c,
batch_size=c.shape[0],
shape=shape,
verbose=False)
x_samples_ddim = model.decode_first_stage(samples_ddim)
image = torch.clamp((batch["image"]+1.0)/2.0,
min=0.0, max=1.0)
mask = torch.clamp((batch["mask"]+1.0)/2.0,
min=0.0, max=1.0)
predicted_image = torch.clamp((x_samples_ddim+1.0)/2.0,
min=0.0, max=1.0)
inpainted = (1-mask)*image+mask*predicted_image
inpainted = inpainted.cpu().numpy().transpose(0,2,3,1)[0]*255
Image.fromarray(inpainted.astype(np.uint8)).save(outpath)

429
scripts/latent_imagenet_diffusion.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

58
scripts/prune-ckpt.py Normal file
View File

@@ -0,0 +1,58 @@
import os
import torch
import argparse
import glob
parser = argparse.ArgumentParser(description='Pruning')
parser.add_argument('--ckpt', type=str, default=None, help='path to model ckpt')
args = parser.parse_args()
ckpt = args.ckpt
def prune_it(p, keep_only_ema=False):
print(f"prunin' in path: {p}")
size_initial = os.path.getsize(p)
nsd = dict()
sd = torch.load(p, map_location="cpu")
print(sd.keys())
for k in sd.keys():
if k != "optimizer_states":
nsd[k] = sd[k]
else:
print(f"removing optimizer states for path {p}")
if "global_step" in sd:
print(f"This is global step {sd['global_step']}.")
if keep_only_ema:
sd = nsd["state_dict"].copy()
# infer ema keys
ema_keys = {k: "model_ema." + k[6:].replace(".", ".") for k in sd.keys() if k.startswith("model.")}
new_sd = dict()
for k in sd:
if k in ema_keys:
new_sd[k] = sd[ema_keys[k]].half()
elif not k.startswith("model_ema.") or k in ["model_ema.num_updates", "model_ema.decay"]:
new_sd[k] = sd[k].half()
assert len(new_sd) == len(sd) - len(ema_keys)
nsd["state_dict"] = new_sd
else:
sd = nsd['state_dict'].copy()
new_sd = dict()
for k in sd:
new_sd[k] = sd[k].half()
nsd['state_dict'] = new_sd
fn = f"{os.path.splitext(p)[0]}-pruned.ckpt" if not keep_only_ema else f"{os.path.splitext(p)[0]}-ema-pruned.ckpt"
print(f"saving pruned checkpoint at: {fn}")
torch.save(nsd, fn)
newsize = os.path.getsize(fn)
MSG = f"New ckpt size: {newsize*1e-9:.2f} GB. " + \
f"Saved {(size_initial - newsize)*1e-9:.2f} GB by removing optimizer states"
if keep_only_ema:
MSG += " and non-EMA weights"
print(MSG)
if __name__ == "__main__":
prune_it(ckpt)

313
scripts/sample_diffusion.py Normal file
View File

@@ -0,0 +1,313 @@
import argparse, os, sys, glob, datetime, yaml
import torch
import time
import numpy as np
from tqdm import trange
from omegaconf import OmegaConf
from PIL import Image
from ldm.models.diffusion.ddim import DDIMSampler
from ldm.util import instantiate_from_config
rescale = lambda x: (x + 1.) / 2.
def custom_to_pil(x):
x = x.detach().cpu()
x = torch.clamp(x, -1., 1.)
x = (x + 1.) / 2.
x = x.permute(1, 2, 0).numpy()
x = (255 * x).astype(np.uint8)
x = Image.fromarray(x)
if not x.mode == "RGB":
x = x.convert("RGB")
return x
def custom_to_np(x):
# saves the batch in adm style as in https://github.com/openai/guided-diffusion/blob/main/scripts/image_sample.py
sample = x.detach().cpu()
sample = ((sample + 1) * 127.5).clamp(0, 255).to(torch.uint8)
sample = sample.permute(0, 2, 3, 1)
sample = sample.contiguous()
return sample
def logs2pil(logs, keys=["sample"]):
imgs = dict()
for k in logs:
try:
if len(logs[k].shape) == 4:
img = custom_to_pil(logs[k][0, ...])
elif len(logs[k].shape) == 3:
img = custom_to_pil(logs[k])
else:
print(f"Unknown format for key {k}. ")
img = None
except:
img = None
imgs[k] = img
return imgs
@torch.no_grad()
def convsample(model, shape, return_intermediates=True,
verbose=True,
make_prog_row=False):
if not make_prog_row:
return model.p_sample_loop(None, shape,
return_intermediates=return_intermediates, verbose=verbose)
else:
return model.progressive_denoising(
None, shape, verbose=True
)
@torch.no_grad()
def convsample_ddim(model, steps, shape, eta=1.0
):
ddim = DDIMSampler(model)
bs = shape[0]
shape = shape[1:]
samples, intermediates = ddim.sample(steps, batch_size=bs, shape=shape, eta=eta, verbose=False,)
return samples, intermediates
@torch.no_grad()
def make_convolutional_sample(model, batch_size, vanilla=False, custom_steps=None, eta=1.0,):
log = dict()
shape = [batch_size,
model.model.diffusion_model.in_channels,
model.model.diffusion_model.image_size,
model.model.diffusion_model.image_size]
with model.ema_scope("Plotting"):
t0 = time.time()
if vanilla:
sample, progrow = convsample(model, shape,
make_prog_row=True)
else:
sample, intermediates = convsample_ddim(model, steps=custom_steps, shape=shape,
eta=eta)
t1 = time.time()
x_sample = model.decode_first_stage(sample)
log["sample"] = x_sample
log["time"] = t1 - t0
log['throughput'] = sample.shape[0] / (t1 - t0)
print(f'Throughput for this batch: {log["throughput"]}')
return log
def run(model, logdir, batch_size=50, vanilla=False, custom_steps=None, eta=None, n_samples=50000, nplog=None):
if vanilla:
print(f'Using Vanilla DDPM sampling with {model.num_timesteps} sampling steps.')
else:
print(f'Using DDIM sampling with {custom_steps} sampling steps and eta={eta}')
tstart = time.time()
n_saved = len(glob.glob(os.path.join(logdir,'*.png')))-1
# path = logdir
if model.cond_stage_model is None:
all_images = []
print(f"Running unconditional sampling for {n_samples} samples")
for _ in trange(n_samples // batch_size, desc="Sampling Batches (unconditional)"):
logs = make_convolutional_sample(model, batch_size=batch_size,
vanilla=vanilla, custom_steps=custom_steps,
eta=eta)
n_saved = save_logs(logs, logdir, n_saved=n_saved, key="sample")
all_images.extend([custom_to_np(logs["sample"])])
if n_saved >= n_samples:
print(f'Finish after generating {n_saved} samples')
break
all_img = np.concatenate(all_images, axis=0)
all_img = all_img[:n_samples]
shape_str = "x".join([str(x) for x in all_img.shape])
nppath = os.path.join(nplog, f"{shape_str}-samples.npz")
np.savez(nppath, all_img)
else:
raise NotImplementedError('Currently only sampling for unconditional models supported.')
print(f"sampling of {n_saved} images finished in {(time.time() - tstart) / 60.:.2f} minutes.")
def save_logs(logs, path, n_saved=0, key="sample", np_path=None):
for k in logs:
if k == key:
batch = logs[key]
if np_path is None:
for x in batch:
img = custom_to_pil(x)
imgpath = os.path.join(path, f"{key}_{n_saved:06}.png")
img.save(imgpath)
n_saved += 1
else:
npbatch = custom_to_np(batch)
shape_str = "x".join([str(x) for x in npbatch.shape])
nppath = os.path.join(np_path, f"{n_saved}-{shape_str}-samples.npz")
np.savez(nppath, npbatch)
n_saved += npbatch.shape[0]
return n_saved
def get_parser():
parser = argparse.ArgumentParser()
parser.add_argument(
"-r",
"--resume",
type=str,
nargs="?",
help="load from logdir or checkpoint in logdir",
)
parser.add_argument(
"-n",
"--n_samples",
type=int,
nargs="?",
help="number of samples to draw",
default=50000
)
parser.add_argument(
"-e",
"--eta",
type=float,
nargs="?",
help="eta for ddim sampling (0.0 yields deterministic sampling)",
default=1.0
)
parser.add_argument(
"-v",
"--vanilla_sample",
default=False,
action='store_true',
help="vanilla sampling (default option is DDIM sampling)?",
)
parser.add_argument(
"-l",
"--logdir",
type=str,
nargs="?",
help="extra logdir",
default="none"
)
parser.add_argument(
"-c",
"--custom_steps",
type=int,
nargs="?",
help="number of steps for ddim and fastdpm sampling",
default=50
)
parser.add_argument(
"--batch_size",
type=int,
nargs="?",
help="the bs",
default=10
)
return parser
def load_model_from_config(config, sd):
model = instantiate_from_config(config)
model.load_state_dict(sd,strict=False)
model.cuda()
model.eval()
return model
def load_model(config, ckpt, gpu, eval_mode):
if ckpt:
print(f"Loading model from {ckpt}")
pl_sd = torch.load(ckpt, map_location="cpu")
global_step = pl_sd["global_step"]
else:
pl_sd = {"state_dict": None}
global_step = None
model = load_model_from_config(config.model,
pl_sd["state_dict"])
return model, global_step
if __name__ == "__main__":
now = datetime.datetime.now().strftime("%Y-%m-%d-%H-%M-%S")
sys.path.append(os.getcwd())
command = " ".join(sys.argv)
parser = get_parser()
opt, unknown = parser.parse_known_args()
ckpt = None
if not os.path.exists(opt.resume):
raise ValueError("Cannot find {}".format(opt.resume))
if os.path.isfile(opt.resume):
# paths = opt.resume.split("/")
try:
logdir = '/'.join(opt.resume.split('/')[:-1])
# idx = len(paths)-paths[::-1].index("logs")+1
print(f'Logdir is {logdir}')
except ValueError:
paths = opt.resume.split("/")
idx = -2 # take a guess: path/to/logdir/checkpoints/model.ckpt
logdir = "/".join(paths[:idx])
ckpt = opt.resume
else:
assert os.path.isdir(opt.resume), f"{opt.resume} is not a directory"
logdir = opt.resume.rstrip("/")
ckpt = os.path.join(logdir, "model.ckpt")
base_configs = sorted(glob.glob(os.path.join(logdir, "config.yaml")))
opt.base = base_configs
configs = [OmegaConf.load(cfg) for cfg in opt.base]
cli = OmegaConf.from_dotlist(unknown)
config = OmegaConf.merge(*configs, cli)
gpu = True
eval_mode = True
if opt.logdir != "none":
locallog = logdir.split(os.sep)[-1]
if locallog == "": locallog = logdir.split(os.sep)[-2]
print(f"Switching logdir from '{logdir}' to '{os.path.join(opt.logdir, locallog)}'")
logdir = os.path.join(opt.logdir, locallog)
print(config)
model, global_step = load_model(config, ckpt, gpu, eval_mode)
print(f"global step: {global_step}")
print(75 * "=")
print("logging to:")
logdir = os.path.join(logdir, "samples", f"{global_step:08}", now)
imglogdir = os.path.join(logdir, "img")
numpylogdir = os.path.join(logdir, "numpy")
os.makedirs(imglogdir)
os.makedirs(numpylogdir)
print(logdir)
print(75 * "=")
# write config out
sampling_file = os.path.join(logdir, "sampling_config.yaml")
sampling_conf = vars(opt)
with open(sampling_file, 'w') as f:
yaml.dump(sampling_conf, f, default_flow_style=False)
print(sampling_conf)
run(model, imglogdir, eta=opt.eta,
vanilla=opt.vanilla_sample, n_samples=opt.n_samples, custom_steps=opt.custom_steps,
batch_size=opt.batch_size, nplog=numpylogdir)
print("done.")

292
scripts/stable_txt2img.py Normal file
View File

@@ -0,0 +1,292 @@
import argparse, os, sys, glob
import torch
import numpy as np
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, save_image
import time
from pytorch_lightning import seed_everything
from torch import autocast
from contextlib import contextmanager, nullcontext
from ldm.util import instantiate_from_config
from ldm.models.diffusion.ddim import DDIMSampler
from ldm.models.diffusion.plms import PLMSSampler
def chunk(it, size):
it = iter(it)
return iter(lambda: tuple(islice(it, size)), ())
def load_model_from_config(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"]
model = instantiate_from_config(config.model)
m, u = model.load_state_dict(sd, strict=False)
if len(m) > 0 and verbose:
print("missing keys:")
print(m)
if len(u) > 0 and verbose:
print("unexpected keys:")
print(u)
model.cuda()
model.eval()
return model
def main():
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(
"--plms",
action='store_true',
help="use plms sampling",
)
parser.add_argument(
"--laion400m",
action='store_true',
help="uses the LAION400M model",
)
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=2,
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=3,
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(
"--config",
type=str,
default="configs/stable-diffusion/v1-inference.yaml",
help="path to config which constructs model",
)
parser.add_argument(
"--ckpt",
type=str,
default="models/ldm/stable-diffusion-v1/model.ckpt",
help="path to checkpoint of model",
)
parser.add_argument(
"--seed",
type=int,
default=42,
help="the seed (for reproducible sampling)",
)
parser.add_argument(
"--precision",
type=str,
help="evaluate at this precision",
choices=["full", "autocast"],
default="autocast"
)
parser.add_argument(
"--embedding_path",
type=str,
help="Path to a pre-trained embedding manager checkpoint")
opt = parser.parse_args()
if opt.laion400m:
print("Falling back to LAION 400M model...")
opt.config = "configs/latent-diffusion/txt2img-1p4B-eval.yaml"
opt.ckpt = "models/ldm/text2img-large/model.ckpt"
opt.outdir = "outputs/txt2img-samples-laion400m"
seed_everything(opt.seed)
config = OmegaConf.load(f"{opt.config}")
model = load_model_from_config(config, f"{opt.ckpt}")
#model.embedding_manager.load(opt.embedding_path)
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
model = model.to(device)
if opt.plms:
sampler = PLMSSampler(model)
else:
sampler = DDIMSampler(model)
os.makedirs(opt.outdir, exist_ok=True)
outpath = opt.outdir
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))
sample_path = os.path.join(outpath, "samples")
os.makedirs(sample_path, exist_ok=True)
base_count = len(os.listdir(sample_path))
grid_count = len(os.listdir(outpath)) - 1
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)
precision_scope = autocast if opt.precision=="autocast" else nullcontext
with torch.no_grad():
with precision_scope("cuda"):
with model.ema_scope():
tic = time.time()
all_samples = list()
for n in trange(opt.n_iter, desc="Sampling"):
for prompts in tqdm(data, desc="data"):
uc = None
if opt.scale != 1.0:
uc = model.get_learned_conditioning(batch_size * [""])
if isinstance(prompts, tuple):
prompts = list(prompts)
c = model.get_learned_conditioning(prompts)
shape = [opt.C, opt.H // opt.f, opt.W // opt.f]
samples_ddim, _ = sampler.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)
x_samples_ddim = model.decode_first_stage(samples_ddim)
x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
if not opt.skip_save:
for x_sample in x_samples_ddim:
x_sample = 255. * rearrange(x_sample.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}.jpg"))
base_count += 1
if not opt.skip_grid:
all_samples.append(x_samples_ddim)
if not opt.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')
for i in range(grid.size(0)):
save_image(grid[i, :, :, :], os.path.join(outpath,opt.prompt+'_{}.png'.format(i)))
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'{prompt.replace(" ", "-")}-{grid_count:04}.jpg'))
grid_count += 1
toc = time.time()
print(f"Your samples are ready and waiting for you here: \n{outpath} \n"
f" \nEnjoy.")
if __name__ == "__main__":
main()

184
scripts/txt2img.py Normal file
View File

@@ -0,0 +1,184 @@
import argparse, os, sys, glob
import torch
import numpy as np
from omegaconf import OmegaConf
from PIL import Image
from tqdm import tqdm, trange
from einops import rearrange
from torchvision.utils import make_grid, save_image
from ldm.util import instantiate_from_config
from ldm.models.diffusion.ddim import DDIMSampler
from ldm.models.diffusion.plms import PLMSSampler
def load_model_from_config(config, ckpt, verbose=False):
print(f"Loading model from {ckpt}")
pl_sd = torch.load(ckpt, map_location="cpu")
sd = pl_sd["state_dict"]
model = instantiate_from_config(config.model)
m, u = model.load_state_dict(sd, strict=False)
if len(m) > 0 and verbose:
print("missing keys:")
print(m)
if len(u) > 0 and verbose:
print("unexpected keys:")
print(u)
model.cuda()
model.eval()
return model
if __name__ == "__main__":
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(
"--ddim_steps",
type=int,
default=200,
help="number of ddim sampling steps",
)
parser.add_argument(
"--plms",
action='store_true',
help="use plms sampling",
)
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=256,
help="image height, in pixel space",
)
parser.add_argument(
"--W",
type=int,
default=256,
help="image width, in pixel space",
)
parser.add_argument(
"--n_samples",
type=int,
default=4,
help="how many samples to produce for the given prompt",
)
parser.add_argument(
"--scale",
type=float,
default=5.0,
help="unconditional guidance scale: eps = eps(x, empty) + scale * (eps(x, cond) - eps(x, empty))",
)
parser.add_argument(
"--ckpt_path",
type=str,
default="/data/pretrained_models/ldm/text2img-large/model.ckpt",
help="Path to pretrained ldm text2img model")
parser.add_argument(
"--embedding_path",
type=str,
help="Path to a pre-trained embedding manager checkpoint")
opt = parser.parse_args()
config = OmegaConf.load("configs/latent-diffusion/txt2img-1p4B-eval_with_tokens.yaml") # TODO: Optionally download from same location as ckpt and chnage this logic
model = load_model_from_config(config, opt.ckpt_path) # TODO: check path
#model.embedding_manager.load(opt.embedding_path)
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
model = model.to(device)
if opt.plms:
sampler = PLMSSampler(model)
else:
sampler = DDIMSampler(model)
os.makedirs(opt.outdir, exist_ok=True)
outpath = opt.outdir
prompt = opt.prompt
sample_path = os.path.join(outpath, "samples")
os.makedirs(sample_path, exist_ok=True)
base_count = len(os.listdir(sample_path))
all_samples=list()
with torch.no_grad():
with model.ema_scope():
uc = None
if opt.scale != 1.0:
uc = model.get_learned_conditioning(opt.n_samples * [""])
for n in trange(opt.n_iter, desc="Sampling"):
c = model.get_learned_conditioning(opt.n_samples * [prompt])
shape = [4, opt.H//8, opt.W//8]
samples_ddim, _ = sampler.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_samples_ddim = model.decode_first_stage(samples_ddim)
x_samples_ddim = 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.cpu().numpy(), 'c h w -> h w c')
Image.fromarray(x_sample.astype(np.uint8)).save(os.path.join(sample_path, f"{base_count:04}.jpg"))
base_count += 1
all_samples.append(x_samples_ddim)
# additionally, save as grid
grid = torch.stack(all_samples, 0)
grid = rearrange(grid, 'n b c h w -> (n b) c h w')
for i in range(grid.size(0)):
save_image(grid[i, :, :, :], os.path.join(outpath,opt.prompt+'_{}.png'.format(i)))
grid = make_grid(grid, nrow=opt.n_samples)
# 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'{prompt.replace(" ", "-")}.jpg'))
print(f"Your samples are ready and waiting four you here: \n{outpath} \nEnjoy.")