"""
wild mixture of
https://github.com/lucidrains/denoising-diffusion-pytorch/blob/7706bdfc6f527f58d33f84b7b522e61e6e3164b3/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py
https://github.com/openai/improved-diffusion/blob/e94489283bb876ac1477d5dd7709bbbd2d9902ce/improved_diffusion/gaussian_diffusion.py
https://github.com/CompVis/taming-transformers
-- merci
"""
# File modified by authors of InstructPix2Pix from original (https://github.com/CompVis/stable-diffusion).
# See more details in LICENSE.
import torch
import torch.nn as nn
import numpy as np
import pytorch_lightning as pl
from torch.optim.lr_scheduler import LambdaLR
from einops import rearrange, repeat
from contextlib import contextmanager
from functools import partial
from tqdm import tqdm
from torchvision.utils import make_grid
from pytorch_lightning.utilities.distributed import rank_zero_only
from ldm.util import log_txt_as_img, exists, default, ismap, isimage, mean_flat, count_params, instantiate_from_config
from ldm.modules.ema import LitEma
from ldm.modules.distributions.distributions import normal_kl, DiagonalGaussianDistribution
from ldm.models.autoencoder import IdentityFirstStage, AutoencoderKL
from ldm.modules.diffusionmodules.util import make_beta_schedule, extract_into_tensor, noise_like
from ldm.models.diffusion.ddim import DDIMSampler
try:
from ldm.models.autoencoder import VQModelInterface
except Exception:
class VQModelInterface:
pass
__conditioning_keys__ = {'concat': 'c_concat',
'crossattn': 'c_crossattn',
'adm': 'y'}
def disabled_train(self, mode=True):
"""Overwrite model.train with this function to make sure train/eval mode
does not change anymore."""
return self
def uniform_on_device(r1, r2, shape, device):
return (r1 - r2) * torch.rand(*shape, device=device) + r2
class DDPM(pl.LightningModule):
# classic DDPM with Gaussian diffusion, in image space
def __init__(self,
unet_config,
timesteps=1000,
beta_schedule="linear",
loss_type="l2",
ckpt_path=None,
ignore_keys=None,
load_only_unet=False,
monitor="val/loss",
use_ema=True,
first_stage_key="image",
image_size=256,
channels=3,
log_every_t=100,
clip_denoised=True,
linear_start=1e-4,
linear_end=2e-2,
cosine_s=8e-3,
given_betas=None,
original_elbo_weight=0.,
v_posterior=0., # weight for choosing posterior variance as sigma = (1-v) * beta_tilde + v * beta
l_simple_weight=1.,
conditioning_key=None,
parameterization="eps", # all assuming fixed variance schedules
scheduler_config=None,
use_positional_encodings=False,
learn_logvar=False,
logvar_init=0.,
load_ema=True,
):
super().__init__()
assert parameterization in ["eps", "x0"], 'currently only supporting "eps" and "x0"'
self.parameterization = parameterization
print(f"{self.__class__.__name__}: Running in {self.parameterization}-prediction mode")
self.cond_stage_model = None
self.clip_denoised = clip_denoised
self.log_every_t = log_every_t
self.first_stage_key = first_stage_key
self.image_size = image_size # try conv?
self.channels = channels
| 