first commit
This commit is contained in:
YehLi
@@ -0,0 +1,428 @@
|
||||
# Copyright 2024 Stability AI, Katherine Crowson and The HuggingFace Team. All rights reserved.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
import math
|
||||
from dataclasses import dataclass
|
||||
from typing import List, Optional, Tuple, Union
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
from diffusers.configuration_utils import ConfigMixin, register_to_config
|
||||
from diffusers.schedulers.scheduling_utils import SchedulerMixin
|
||||
from diffusers.utils import BaseOutput, is_scipy_available, logging
|
||||
from diffusers.utils.torch_utils import randn_tensor
|
||||
|
||||
if is_scipy_available():
|
||||
import scipy.stats
|
||||
|
||||
logger = logging.get_logger(__name__) # pylint: disable=invalid-name
|
||||
|
||||
|
||||
@dataclass
|
||||
class FlashFlowMatchEulerDiscreteSchedulerOutput(BaseOutput):
|
||||
"""
|
||||
Output class for the scheduler's `step` function output.
|
||||
|
||||
Args:
|
||||
prev_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
|
||||
Computed sample `(x_{t-1})` of previous timestep. `prev_sample` should be used as next model input in the
|
||||
denoising loop.
|
||||
"""
|
||||
|
||||
prev_sample: torch.FloatTensor
|
||||
|
||||
|
||||
class FlashFlowMatchEulerDiscreteScheduler(SchedulerMixin, ConfigMixin):
|
||||
"""
|
||||
Euler scheduler.
|
||||
|
||||
This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass documentation for the generic
|
||||
methods the library implements for all schedulers such as loading and saving.
|
||||
|
||||
Args:
|
||||
num_train_timesteps (`int`, defaults to 1000):
|
||||
The number of diffusion steps to train the model.
|
||||
timestep_spacing (`str`, defaults to `"linspace"`):
|
||||
The way the timesteps should be scaled. Refer to Table 2 of the [Common Diffusion Noise Schedules and
|
||||
Sample Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information.
|
||||
shift (`float`, defaults to 1.0):
|
||||
The shift value for the timestep schedule.
|
||||
"""
|
||||
|
||||
_compatibles = []
|
||||
order = 1
|
||||
|
||||
@register_to_config
|
||||
def __init__(
|
||||
self,
|
||||
num_train_timesteps: int = 1000,
|
||||
shift: float = 1.0,
|
||||
use_dynamic_shifting=False,
|
||||
base_shift: Optional[float] = 0.5,
|
||||
max_shift: Optional[float] = 1.15,
|
||||
base_image_seq_len: Optional[int] = 256,
|
||||
max_image_seq_len: Optional[int] = 4096,
|
||||
invert_sigmas: bool = False,
|
||||
use_karras_sigmas: Optional[bool] = False,
|
||||
use_exponential_sigmas: Optional[bool] = False,
|
||||
use_beta_sigmas: Optional[bool] = False,
|
||||
):
|
||||
if self.config.use_beta_sigmas and not is_scipy_available():
|
||||
raise ImportError("Make sure to install scipy if you want to use beta sigmas.")
|
||||
if sum([self.config.use_beta_sigmas, self.config.use_exponential_sigmas, self.config.use_karras_sigmas]) > 1:
|
||||
raise ValueError(
|
||||
"Only one of `config.use_beta_sigmas`, `config.use_exponential_sigmas`, `config.use_karras_sigmas` can be used."
|
||||
)
|
||||
timesteps = np.linspace(1, num_train_timesteps, num_train_timesteps, dtype=np.float32)[::-1].copy()
|
||||
timesteps = torch.from_numpy(timesteps).to(dtype=torch.float32)
|
||||
|
||||
sigmas = timesteps / num_train_timesteps
|
||||
if not use_dynamic_shifting:
|
||||
# when use_dynamic_shifting is True, we apply the timestep shifting on the fly based on the image resolution
|
||||
sigmas = shift * sigmas / (1 + (shift - 1) * sigmas)
|
||||
|
||||
self.timesteps = sigmas * num_train_timesteps
|
||||
|
||||
self._step_index = None
|
||||
self._begin_index = None
|
||||
|
||||
self.sigmas = sigmas.to("cpu") # to avoid too much CPU/GPU communication
|
||||
self.sigma_min = self.sigmas[-1].item()
|
||||
self.sigma_max = self.sigmas[0].item()
|
||||
|
||||
@property
|
||||
def step_index(self):
|
||||
"""
|
||||
The index counter for current timestep. It will increase 1 after each scheduler step.
|
||||
"""
|
||||
return self._step_index
|
||||
|
||||
@property
|
||||
def begin_index(self):
|
||||
"""
|
||||
The index for the first timestep. It should be set from pipeline with `set_begin_index` method.
|
||||
"""
|
||||
return self._begin_index
|
||||
|
||||
# Copied from diffusers.schedulers.scheduling_dpmsolver_multistep.DPMSolverMultistepScheduler.set_begin_index
|
||||
def set_begin_index(self, begin_index: int = 0):
|
||||
"""
|
||||
Sets the begin index for the scheduler. This function should be run from pipeline before the inference.
|
||||
|
||||
Args:
|
||||
begin_index (`int`):
|
||||
The begin index for the scheduler.
|
||||
"""
|
||||
self._begin_index = begin_index
|
||||
|
||||
def scale_noise(
|
||||
self,
|
||||
sample: torch.FloatTensor,
|
||||
timestep: Union[float, torch.FloatTensor],
|
||||
noise: Optional[torch.FloatTensor] = None,
|
||||
) -> torch.FloatTensor:
|
||||
"""
|
||||
Forward process in flow-matching
|
||||
|
||||
Args:
|
||||
sample (`torch.FloatTensor`):
|
||||
The input sample.
|
||||
timestep (`int`, *optional*):
|
||||
The current timestep in the diffusion chain.
|
||||
|
||||
Returns:
|
||||
`torch.FloatTensor`:
|
||||
A scaled input sample.
|
||||
"""
|
||||
# Make sure sigmas and timesteps have the same device and dtype as original_samples
|
||||
sigmas = self.sigmas.to(device=sample.device, dtype=sample.dtype)
|
||||
|
||||
if sample.device.type == "mps" and torch.is_floating_point(timestep):
|
||||
# mps does not support float64
|
||||
schedule_timesteps = self.timesteps.to(sample.device, dtype=torch.float32)
|
||||
timestep = timestep.to(sample.device, dtype=torch.float32)
|
||||
else:
|
||||
schedule_timesteps = self.timesteps.to(sample.device)
|
||||
timestep = timestep.to(sample.device)
|
||||
|
||||
# self.begin_index is None when scheduler is used for training, or pipeline does not implement set_begin_index
|
||||
if self.begin_index is None:
|
||||
step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timestep]
|
||||
elif self.step_index is not None:
|
||||
# add_noise is called after first denoising step (for inpainting)
|
||||
step_indices = [self.step_index] * timestep.shape[0]
|
||||
else:
|
||||
# add noise is called before first denoising step to create initial latent(img2img)
|
||||
step_indices = [self.begin_index] * timestep.shape[0]
|
||||
|
||||
sigma = sigmas[step_indices].flatten()
|
||||
while len(sigma.shape) < len(sample.shape):
|
||||
sigma = sigma.unsqueeze(-1)
|
||||
|
||||
sample = sigma * noise + (1.0 - sigma) * sample
|
||||
|
||||
return sample
|
||||
|
||||
def _sigma_to_t(self, sigma):
|
||||
return sigma * self.config.num_train_timesteps
|
||||
|
||||
def time_shift(self, mu: float, sigma: float, t: torch.Tensor):
|
||||
return math.exp(mu) / (math.exp(mu) + (1 / t - 1) ** sigma)
|
||||
|
||||
def set_timesteps(
|
||||
self,
|
||||
num_inference_steps: int = None,
|
||||
device: Union[str, torch.device] = None,
|
||||
sigmas: Optional[List[float]] = None,
|
||||
mu: Optional[float] = None,
|
||||
):
|
||||
"""
|
||||
Sets the discrete timesteps used for the diffusion chain (to be run before inference).
|
||||
|
||||
Args:
|
||||
num_inference_steps (`int`):
|
||||
The number of diffusion steps used when generating samples with a pre-trained model.
|
||||
device (`str` or `torch.device`, *optional*):
|
||||
The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
|
||||
"""
|
||||
if self.config.use_dynamic_shifting and mu is None:
|
||||
raise ValueError(" you have a pass a value for `mu` when `use_dynamic_shifting` is set to be `True`")
|
||||
|
||||
if sigmas is None:
|
||||
timesteps = np.linspace(
|
||||
self._sigma_to_t(self.sigma_max), self._sigma_to_t(self.sigma_min), num_inference_steps
|
||||
)
|
||||
|
||||
sigmas = timesteps / self.config.num_train_timesteps
|
||||
else:
|
||||
sigmas = np.array(sigmas).astype(np.float32)
|
||||
num_inference_steps = len(sigmas)
|
||||
self.num_inference_steps = num_inference_steps
|
||||
|
||||
if self.config.use_dynamic_shifting:
|
||||
sigmas = self.time_shift(mu, 1.0, sigmas)
|
||||
else:
|
||||
sigmas = self.config.shift * sigmas / (1 + (self.config.shift - 1) * sigmas)
|
||||
|
||||
if self.config.use_karras_sigmas:
|
||||
sigmas = self._convert_to_karras(in_sigmas=sigmas, num_inference_steps=num_inference_steps)
|
||||
|
||||
elif self.config.use_exponential_sigmas:
|
||||
sigmas = self._convert_to_exponential(in_sigmas=sigmas, num_inference_steps=num_inference_steps)
|
||||
|
||||
elif self.config.use_beta_sigmas:
|
||||
sigmas = self._convert_to_beta(in_sigmas=sigmas, num_inference_steps=num_inference_steps)
|
||||
|
||||
sigmas = torch.from_numpy(sigmas).to(dtype=torch.float32, device=device)
|
||||
timesteps = sigmas * self.config.num_train_timesteps
|
||||
|
||||
if self.config.invert_sigmas:
|
||||
sigmas = 1.0 - sigmas
|
||||
timesteps = sigmas * self.config.num_train_timesteps
|
||||
sigmas = torch.cat([sigmas, torch.ones(1, device=sigmas.device)])
|
||||
else:
|
||||
sigmas = torch.cat([sigmas, torch.zeros(1, device=sigmas.device)])
|
||||
|
||||
self.timesteps = timesteps.to(device=device)
|
||||
self.sigmas = sigmas
|
||||
self._step_index = None
|
||||
self._begin_index = None
|
||||
|
||||
def index_for_timestep(self, timestep, schedule_timesteps=None):
|
||||
if schedule_timesteps is None:
|
||||
schedule_timesteps = self.timesteps
|
||||
|
||||
indices = (schedule_timesteps == timestep).nonzero()
|
||||
|
||||
# The sigma index that is taken for the **very** first `step`
|
||||
# is always the second index (or the last index if there is only 1)
|
||||
# This way we can ensure we don't accidentally skip a sigma in
|
||||
# case we start in the middle of the denoising schedule (e.g. for image-to-image)
|
||||
pos = 1 if len(indices) > 1 else 0
|
||||
|
||||
return indices[pos].item()
|
||||
|
||||
def _init_step_index(self, timestep):
|
||||
if self.begin_index is None:
|
||||
if isinstance(timestep, torch.Tensor):
|
||||
timestep = timestep.to(self.timesteps.device)
|
||||
self._step_index = self.index_for_timestep(timestep)
|
||||
else:
|
||||
self._step_index = self._begin_index
|
||||
|
||||
def step(
|
||||
self,
|
||||
model_output: torch.FloatTensor,
|
||||
timestep: Union[float, torch.FloatTensor],
|
||||
sample: torch.FloatTensor,
|
||||
s_churn: float = 0.0,
|
||||
s_tmin: float = 0.0,
|
||||
s_tmax: float = float("inf"),
|
||||
s_noise: float = 1.0,
|
||||
generator: Optional[torch.Generator] = None,
|
||||
return_dict: bool = True,
|
||||
) -> Union[FlashFlowMatchEulerDiscreteSchedulerOutput, Tuple]:
|
||||
"""
|
||||
Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion
|
||||
process from the learned model outputs (most often the predicted noise).
|
||||
|
||||
Args:
|
||||
model_output (`torch.FloatTensor`):
|
||||
The direct output from learned diffusion model.
|
||||
timestep (`float`):
|
||||
The current discrete timestep in the diffusion chain.
|
||||
sample (`torch.FloatTensor`):
|
||||
A current instance of a sample created by the diffusion process.
|
||||
s_churn (`float`):
|
||||
s_tmin (`float`):
|
||||
s_tmax (`float`):
|
||||
s_noise (`float`, defaults to 1.0):
|
||||
Scaling factor for noise added to the sample.
|
||||
generator (`torch.Generator`, *optional*):
|
||||
A random number generator.
|
||||
return_dict (`bool`):
|
||||
Whether or not to return a [`~schedulers.scheduling_euler_discrete.EulerDiscreteSchedulerOutput`] or
|
||||
tuple.
|
||||
|
||||
Returns:
|
||||
[`~schedulers.scheduling_euler_discrete.EulerDiscreteSchedulerOutput`] or `tuple`:
|
||||
If return_dict is `True`, [`~schedulers.scheduling_euler_discrete.EulerDiscreteSchedulerOutput`] is
|
||||
returned, otherwise a tuple is returned where the first element is the sample tensor.
|
||||
"""
|
||||
|
||||
if (
|
||||
isinstance(timestep, int)
|
||||
or isinstance(timestep, torch.IntTensor)
|
||||
or isinstance(timestep, torch.LongTensor)
|
||||
):
|
||||
raise ValueError(
|
||||
(
|
||||
"Passing integer indices (e.g. from `enumerate(timesteps)`) as timesteps to"
|
||||
" `EulerDiscreteScheduler.step()` is not supported. Make sure to pass"
|
||||
" one of the `scheduler.timesteps` as a timestep."
|
||||
),
|
||||
)
|
||||
|
||||
if self.step_index is None:
|
||||
self._init_step_index(timestep)
|
||||
|
||||
# Upcast to avoid precision issues when computing prev_sample
|
||||
|
||||
sigma = self.sigmas[self.step_index]
|
||||
|
||||
# Upcast to avoid precision issues when computing prev_sample
|
||||
sample = sample.to(torch.float32)
|
||||
|
||||
denoised = sample - model_output * sigma
|
||||
|
||||
if self.step_index < self.num_inference_steps - 1:
|
||||
sigma_next = self.sigmas[self.step_index + 1]
|
||||
noise = randn_tensor(
|
||||
model_output.shape,
|
||||
generator=generator,
|
||||
device=model_output.device,
|
||||
dtype=denoised.dtype,
|
||||
)
|
||||
sample = sigma_next * noise + (1.0 - sigma_next) * denoised
|
||||
|
||||
self._step_index += 1
|
||||
sample = sample.to(model_output.dtype)
|
||||
|
||||
if not return_dict:
|
||||
return (sample,)
|
||||
|
||||
return FlashFlowMatchEulerDiscreteSchedulerOutput(prev_sample=sample)
|
||||
|
||||
# Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler._convert_to_karras
|
||||
def _convert_to_karras(self, in_sigmas: torch.Tensor, num_inference_steps) -> torch.Tensor:
|
||||
"""Constructs the noise schedule of Karras et al. (2022)."""
|
||||
|
||||
# Hack to make sure that other schedulers which copy this function don't break
|
||||
# TODO: Add this logic to the other schedulers
|
||||
if hasattr(self.config, "sigma_min"):
|
||||
sigma_min = self.config.sigma_min
|
||||
else:
|
||||
sigma_min = None
|
||||
|
||||
if hasattr(self.config, "sigma_max"):
|
||||
sigma_max = self.config.sigma_max
|
||||
else:
|
||||
sigma_max = None
|
||||
|
||||
sigma_min = sigma_min if sigma_min is not None else in_sigmas[-1].item()
|
||||
sigma_max = sigma_max if sigma_max is not None else in_sigmas[0].item()
|
||||
|
||||
rho = 7.0 # 7.0 is the value used in the paper
|
||||
ramp = np.linspace(0, 1, num_inference_steps)
|
||||
min_inv_rho = sigma_min ** (1 / rho)
|
||||
max_inv_rho = sigma_max ** (1 / rho)
|
||||
sigmas = (max_inv_rho + ramp * (min_inv_rho - max_inv_rho)) ** rho
|
||||
return sigmas
|
||||
|
||||
# Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler._convert_to_exponential
|
||||
def _convert_to_exponential(self, in_sigmas: torch.Tensor, num_inference_steps: int) -> torch.Tensor:
|
||||
"""Constructs an exponential noise schedule."""
|
||||
|
||||
# Hack to make sure that other schedulers which copy this function don't break
|
||||
# TODO: Add this logic to the other schedulers
|
||||
if hasattr(self.config, "sigma_min"):
|
||||
sigma_min = self.config.sigma_min
|
||||
else:
|
||||
sigma_min = None
|
||||
|
||||
if hasattr(self.config, "sigma_max"):
|
||||
sigma_max = self.config.sigma_max
|
||||
else:
|
||||
sigma_max = None
|
||||
|
||||
sigma_min = sigma_min if sigma_min is not None else in_sigmas[-1].item()
|
||||
sigma_max = sigma_max if sigma_max is not None else in_sigmas[0].item()
|
||||
|
||||
sigmas = np.exp(np.linspace(math.log(sigma_max), math.log(sigma_min), num_inference_steps))
|
||||
return sigmas
|
||||
|
||||
# Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler._convert_to_beta
|
||||
def _convert_to_beta(
|
||||
self, in_sigmas: torch.Tensor, num_inference_steps: int, alpha: float = 0.6, beta: float = 0.6
|
||||
) -> torch.Tensor:
|
||||
"""From "Beta Sampling is All You Need" [arXiv:2407.12173] (Lee et. al, 2024)"""
|
||||
|
||||
# Hack to make sure that other schedulers which copy this function don't break
|
||||
# TODO: Add this logic to the other schedulers
|
||||
if hasattr(self.config, "sigma_min"):
|
||||
sigma_min = self.config.sigma_min
|
||||
else:
|
||||
sigma_min = None
|
||||
|
||||
if hasattr(self.config, "sigma_max"):
|
||||
sigma_max = self.config.sigma_max
|
||||
else:
|
||||
sigma_max = None
|
||||
|
||||
sigma_min = sigma_min if sigma_min is not None else in_sigmas[-1].item()
|
||||
sigma_max = sigma_max if sigma_max is not None else in_sigmas[0].item()
|
||||
|
||||
sigmas = np.array(
|
||||
[
|
||||
sigma_min + (ppf * (sigma_max - sigma_min))
|
||||
for ppf in [
|
||||
scipy.stats.beta.ppf(timestep, alpha, beta)
|
||||
for timestep in 1 - np.linspace(0, 1, num_inference_steps)
|
||||
]
|
||||
]
|
||||
)
|
||||
return sigmas
|
||||
|
||||
def __len__(self):
|
||||
return self.config.num_train_timesteps
|
||||
@@ -0,0 +1,800 @@
|
||||
# Copied from https://github.com/huggingface/diffusers/blob/v0.31.0/src/diffusers/schedulers/scheduling_unipc_multistep.py
|
||||
# Convert unipc for flow matching
|
||||
# Copyright 2024-2025 The Alibaba Wan Team Authors. All rights reserved.
|
||||
|
||||
import math
|
||||
from typing import List, Optional, Tuple, Union
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
from diffusers.configuration_utils import ConfigMixin, register_to_config
|
||||
from diffusers.schedulers.scheduling_utils import (KarrasDiffusionSchedulers,
|
||||
SchedulerMixin,
|
||||
SchedulerOutput)
|
||||
from diffusers.utils import deprecate, is_scipy_available
|
||||
|
||||
if is_scipy_available():
|
||||
import scipy.stats
|
||||
|
||||
|
||||
class FlowUniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
|
||||
"""
|
||||
`UniPCMultistepScheduler` is a training-free framework designed for the fast sampling of diffusion models.
|
||||
|
||||
This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass documentation for the generic
|
||||
methods the library implements for all schedulers such as loading and saving.
|
||||
|
||||
Args:
|
||||
num_train_timesteps (`int`, defaults to 1000):
|
||||
The number of diffusion steps to train the model.
|
||||
solver_order (`int`, default `2`):
|
||||
The UniPC order which can be any positive integer. The effective order of accuracy is `solver_order + 1`
|
||||
due to the UniC. It is recommended to use `solver_order=2` for guided sampling, and `solver_order=3` for
|
||||
unconditional sampling.
|
||||
prediction_type (`str`, defaults to "flow_prediction"):
|
||||
Prediction type of the scheduler function; must be `flow_prediction` for this scheduler, which predicts
|
||||
the flow of the diffusion process.
|
||||
thresholding (`bool`, defaults to `False`):
|
||||
Whether to use the "dynamic thresholding" method. This is unsuitable for latent-space diffusion models such
|
||||
as Stable Diffusion.
|
||||
dynamic_thresholding_ratio (`float`, defaults to 0.995):
|
||||
The ratio for the dynamic thresholding method. Valid only when `thresholding=True`.
|
||||
sample_max_value (`float`, defaults to 1.0):
|
||||
The threshold value for dynamic thresholding. Valid only when `thresholding=True` and `predict_x0=True`.
|
||||
predict_x0 (`bool`, defaults to `True`):
|
||||
Whether to use the updating algorithm on the predicted x0.
|
||||
solver_type (`str`, default `bh2`):
|
||||
Solver type for UniPC. It is recommended to use `bh1` for unconditional sampling when steps < 10, and `bh2`
|
||||
otherwise.
|
||||
lower_order_final (`bool`, default `True`):
|
||||
Whether to use lower-order solvers in the final steps. Only valid for < 15 inference steps. This can
|
||||
stabilize the sampling of DPMSolver for steps < 15, especially for steps <= 10.
|
||||
disable_corrector (`list`, default `[]`):
|
||||
Decides which step to disable the corrector to mitigate the misalignment between `epsilon_theta(x_t, c)`
|
||||
and `epsilon_theta(x_t^c, c)` which can influence convergence for a large guidance scale. Corrector is
|
||||
usually disabled during the first few steps.
|
||||
solver_p (`SchedulerMixin`, default `None`):
|
||||
Any other scheduler that if specified, the algorithm becomes `solver_p + UniC`.
|
||||
use_karras_sigmas (`bool`, *optional*, defaults to `False`):
|
||||
Whether to use Karras sigmas for step sizes in the noise schedule during the sampling process. If `True`,
|
||||
the sigmas are determined according to a sequence of noise levels {σi}.
|
||||
use_exponential_sigmas (`bool`, *optional*, defaults to `False`):
|
||||
Whether to use exponential sigmas for step sizes in the noise schedule during the sampling process.
|
||||
timestep_spacing (`str`, defaults to `"linspace"`):
|
||||
The way the timesteps should be scaled. Refer to Table 2 of the [Common Diffusion Noise Schedules and
|
||||
Sample Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information.
|
||||
steps_offset (`int`, defaults to 0):
|
||||
An offset added to the inference steps, as required by some model families.
|
||||
final_sigmas_type (`str`, defaults to `"zero"`):
|
||||
The final `sigma` value for the noise schedule during the sampling process. If `"sigma_min"`, the final
|
||||
sigma is the same as the last sigma in the training schedule. If `zero`, the final sigma is set to 0.
|
||||
"""
|
||||
|
||||
_compatibles = [e.name for e in KarrasDiffusionSchedulers]
|
||||
order = 1
|
||||
|
||||
@register_to_config
|
||||
def __init__(
|
||||
self,
|
||||
num_train_timesteps: int = 1000,
|
||||
solver_order: int = 2,
|
||||
prediction_type: str = "flow_prediction",
|
||||
shift: Optional[float] = 1.0,
|
||||
use_dynamic_shifting=False,
|
||||
thresholding: bool = False,
|
||||
dynamic_thresholding_ratio: float = 0.995,
|
||||
sample_max_value: float = 1.0,
|
||||
predict_x0: bool = True,
|
||||
solver_type: str = "bh2",
|
||||
lower_order_final: bool = True,
|
||||
disable_corrector: List[int] = [],
|
||||
solver_p: SchedulerMixin = None,
|
||||
timestep_spacing: str = "linspace",
|
||||
steps_offset: int = 0,
|
||||
final_sigmas_type: Optional[str] = "zero", # "zero", "sigma_min"
|
||||
):
|
||||
|
||||
if solver_type not in ["bh1", "bh2"]:
|
||||
if solver_type in ["midpoint", "heun", "logrho"]:
|
||||
self.register_to_config(solver_type="bh2")
|
||||
else:
|
||||
raise NotImplementedError(
|
||||
f"{solver_type} is not implemented for {self.__class__}")
|
||||
|
||||
self.predict_x0 = predict_x0
|
||||
# setable values
|
||||
self.num_inference_steps = None
|
||||
alphas = np.linspace(1, 1 / num_train_timesteps,
|
||||
num_train_timesteps)[::-1].copy()
|
||||
sigmas = 1.0 - alphas
|
||||
sigmas = torch.from_numpy(sigmas).to(dtype=torch.float32)
|
||||
|
||||
if not use_dynamic_shifting:
|
||||
# when use_dynamic_shifting is True, we apply the timestep shifting on the fly based on the image resolution
|
||||
sigmas = shift * sigmas / (1 +
|
||||
(shift - 1) * sigmas) # pyright: ignore
|
||||
|
||||
self.sigmas = sigmas
|
||||
self.timesteps = sigmas * num_train_timesteps
|
||||
|
||||
self.model_outputs = [None] * solver_order
|
||||
self.timestep_list = [None] * solver_order
|
||||
self.lower_order_nums = 0
|
||||
self.disable_corrector = disable_corrector
|
||||
self.solver_p = solver_p
|
||||
self.last_sample = None
|
||||
self._step_index = None
|
||||
self._begin_index = None
|
||||
|
||||
self.sigmas = self.sigmas.to(
|
||||
"cpu") # to avoid too much CPU/GPU communication
|
||||
self.sigma_min = self.sigmas[-1].item()
|
||||
self.sigma_max = self.sigmas[0].item()
|
||||
|
||||
@property
|
||||
def step_index(self):
|
||||
"""
|
||||
The index counter for current timestep. It will increase 1 after each scheduler step.
|
||||
"""
|
||||
return self._step_index
|
||||
|
||||
@property
|
||||
def begin_index(self):
|
||||
"""
|
||||
The index for the first timestep. It should be set from pipeline with `set_begin_index` method.
|
||||
"""
|
||||
return self._begin_index
|
||||
|
||||
# Copied from diffusers.schedulers.scheduling_dpmsolver_multistep.DPMSolverMultistepScheduler.set_begin_index
|
||||
def set_begin_index(self, begin_index: int = 0):
|
||||
"""
|
||||
Sets the begin index for the scheduler. This function should be run from pipeline before the inference.
|
||||
|
||||
Args:
|
||||
begin_index (`int`):
|
||||
The begin index for the scheduler.
|
||||
"""
|
||||
self._begin_index = begin_index
|
||||
|
||||
# Modified from diffusers.schedulers.scheduling_flow_match_euler_discrete.FlowMatchEulerDiscreteScheduler.set_timesteps
|
||||
def set_timesteps(
|
||||
self,
|
||||
num_inference_steps: Union[int, None] = None,
|
||||
device: Union[str, torch.device] = None,
|
||||
sigmas: Optional[List[float]] = None,
|
||||
mu: Optional[Union[float, None]] = None,
|
||||
shift: Optional[Union[float, None]] = None,
|
||||
):
|
||||
"""
|
||||
Sets the discrete timesteps used for the diffusion chain (to be run before inference).
|
||||
Args:
|
||||
num_inference_steps (`int`):
|
||||
Total number of the spacing of the time steps.
|
||||
device (`str` or `torch.device`, *optional*):
|
||||
The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
|
||||
"""
|
||||
|
||||
if self.config.use_dynamic_shifting and mu is None:
|
||||
raise ValueError(
|
||||
" you have to pass a value for `mu` when `use_dynamic_shifting` is set to be `True`"
|
||||
)
|
||||
|
||||
if sigmas is None:
|
||||
sigmas = np.linspace(self.sigma_max, self.sigma_min,
|
||||
num_inference_steps +
|
||||
1).copy()[:-1] # pyright: ignore
|
||||
|
||||
if self.config.use_dynamic_shifting:
|
||||
sigmas = self.time_shift(mu, 1.0, sigmas) # pyright: ignore
|
||||
else:
|
||||
if shift is None:
|
||||
shift = self.config.shift
|
||||
sigmas = shift * sigmas / (1 +
|
||||
(shift - 1) * sigmas) # pyright: ignore
|
||||
|
||||
if self.config.final_sigmas_type == "sigma_min":
|
||||
sigma_last = ((1 - self.alphas_cumprod[0]) /
|
||||
self.alphas_cumprod[0])**0.5
|
||||
elif self.config.final_sigmas_type == "zero":
|
||||
sigma_last = 0
|
||||
else:
|
||||
raise ValueError(
|
||||
f"`final_sigmas_type` must be one of 'zero', or 'sigma_min', but got {self.config.final_sigmas_type}"
|
||||
)
|
||||
|
||||
timesteps = sigmas * self.config.num_train_timesteps
|
||||
sigmas = np.concatenate([sigmas, [sigma_last]
|
||||
]).astype(np.float32) # pyright: ignore
|
||||
|
||||
self.sigmas = torch.from_numpy(sigmas)
|
||||
self.timesteps = torch.from_numpy(timesteps).to(
|
||||
device=device, dtype=torch.int64)
|
||||
|
||||
self.num_inference_steps = len(timesteps)
|
||||
|
||||
self.model_outputs = [
|
||||
None,
|
||||
] * self.config.solver_order
|
||||
self.lower_order_nums = 0
|
||||
self.last_sample = None
|
||||
if self.solver_p:
|
||||
self.solver_p.set_timesteps(self.num_inference_steps, device=device)
|
||||
|
||||
# add an index counter for schedulers that allow duplicated timesteps
|
||||
self._step_index = None
|
||||
self._begin_index = None
|
||||
self.sigmas = self.sigmas.to(
|
||||
"cpu") # to avoid too much CPU/GPU communication
|
||||
|
||||
# Copied from diffusers.schedulers.scheduling_ddpm.DDPMScheduler._threshold_sample
|
||||
def _threshold_sample(self, sample: torch.Tensor) -> torch.Tensor:
|
||||
"""
|
||||
"Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the
|
||||
prediction of x_0 at timestep t), and if s > 1, then we threshold xt0 to the range [-s, s] and then divide by
|
||||
s. Dynamic thresholding pushes saturated pixels (those near -1 and 1) inwards, thereby actively preventing
|
||||
pixels from saturation at each step. We find that dynamic thresholding results in significantly better
|
||||
photorealism as well as better image-text alignment, especially when using very large guidance weights."
|
||||
|
||||
https://arxiv.org/abs/2205.11487
|
||||
"""
|
||||
dtype = sample.dtype
|
||||
batch_size, channels, *remaining_dims = sample.shape
|
||||
|
||||
if dtype not in (torch.float32, torch.float64):
|
||||
sample = sample.float(
|
||||
) # upcast for quantile calculation, and clamp not implemented for cpu half
|
||||
|
||||
# Flatten sample for doing quantile calculation along each image
|
||||
sample = sample.reshape(batch_size, channels * np.prod(remaining_dims))
|
||||
|
||||
abs_sample = sample.abs() # "a certain percentile absolute pixel value"
|
||||
|
||||
s = torch.quantile(
|
||||
abs_sample, self.config.dynamic_thresholding_ratio, dim=1)
|
||||
s = torch.clamp(
|
||||
s, min=1, max=self.config.sample_max_value
|
||||
) # When clamped to min=1, equivalent to standard clipping to [-1, 1]
|
||||
s = s.unsqueeze(
|
||||
1) # (batch_size, 1) because clamp will broadcast along dim=0
|
||||
sample = torch.clamp(
|
||||
sample, -s, s
|
||||
) / s # "we threshold xt0 to the range [-s, s] and then divide by s"
|
||||
|
||||
sample = sample.reshape(batch_size, channels, *remaining_dims)
|
||||
sample = sample.to(dtype)
|
||||
|
||||
return sample
|
||||
|
||||
# Copied from diffusers.schedulers.scheduling_flow_match_euler_discrete.FlowMatchEulerDiscreteScheduler._sigma_to_t
|
||||
def _sigma_to_t(self, sigma):
|
||||
return sigma * self.config.num_train_timesteps
|
||||
|
||||
def _sigma_to_alpha_sigma_t(self, sigma):
|
||||
return 1 - sigma, sigma
|
||||
|
||||
# Copied from diffusers.schedulers.scheduling_flow_match_euler_discrete.set_timesteps
|
||||
def time_shift(self, mu: float, sigma: float, t: torch.Tensor):
|
||||
return math.exp(mu) / (math.exp(mu) + (1 / t - 1)**sigma)
|
||||
|
||||
def convert_model_output(
|
||||
self,
|
||||
model_output: torch.Tensor,
|
||||
*args,
|
||||
sample: torch.Tensor = None,
|
||||
**kwargs,
|
||||
) -> torch.Tensor:
|
||||
r"""
|
||||
Convert the model output to the corresponding type the UniPC algorithm needs.
|
||||
|
||||
Args:
|
||||
model_output (`torch.Tensor`):
|
||||
The direct output from the learned diffusion model.
|
||||
timestep (`int`):
|
||||
The current discrete timestep in the diffusion chain.
|
||||
sample (`torch.Tensor`):
|
||||
A current instance of a sample created by the diffusion process.
|
||||
|
||||
Returns:
|
||||
`torch.Tensor`:
|
||||
The converted model output.
|
||||
"""
|
||||
timestep = args[0] if len(args) > 0 else kwargs.pop("timestep", None)
|
||||
if sample is None:
|
||||
if len(args) > 1:
|
||||
sample = args[1]
|
||||
else:
|
||||
raise ValueError(
|
||||
"missing `sample` as a required keyward argument")
|
||||
if timestep is not None:
|
||||
deprecate(
|
||||
"timesteps",
|
||||
"1.0.0",
|
||||
"Passing `timesteps` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
|
||||
)
|
||||
|
||||
sigma = self.sigmas[self.step_index]
|
||||
alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma)
|
||||
|
||||
if self.predict_x0:
|
||||
if self.config.prediction_type == "flow_prediction":
|
||||
sigma_t = self.sigmas[self.step_index]
|
||||
x0_pred = sample - sigma_t * model_output
|
||||
else:
|
||||
raise ValueError(
|
||||
f"prediction_type given as {self.config.prediction_type} must be one of `epsilon`, `sample`,"
|
||||
" `v_prediction` or `flow_prediction` for the UniPCMultistepScheduler."
|
||||
)
|
||||
|
||||
if self.config.thresholding:
|
||||
x0_pred = self._threshold_sample(x0_pred)
|
||||
|
||||
return x0_pred
|
||||
else:
|
||||
if self.config.prediction_type == "flow_prediction":
|
||||
sigma_t = self.sigmas[self.step_index]
|
||||
epsilon = sample - (1 - sigma_t) * model_output
|
||||
else:
|
||||
raise ValueError(
|
||||
f"prediction_type given as {self.config.prediction_type} must be one of `epsilon`, `sample`,"
|
||||
" `v_prediction` or `flow_prediction` for the UniPCMultistepScheduler."
|
||||
)
|
||||
|
||||
if self.config.thresholding:
|
||||
sigma_t = self.sigmas[self.step_index]
|
||||
x0_pred = sample - sigma_t * model_output
|
||||
x0_pred = self._threshold_sample(x0_pred)
|
||||
epsilon = model_output + x0_pred
|
||||
|
||||
return epsilon
|
||||
|
||||
def multistep_uni_p_bh_update(
|
||||
self,
|
||||
model_output: torch.Tensor,
|
||||
*args,
|
||||
sample: torch.Tensor = None,
|
||||
order: int = None, # pyright: ignore
|
||||
**kwargs,
|
||||
) -> torch.Tensor:
|
||||
"""
|
||||
One step for the UniP (B(h) version). Alternatively, `self.solver_p` is used if is specified.
|
||||
|
||||
Args:
|
||||
model_output (`torch.Tensor`):
|
||||
The direct output from the learned diffusion model at the current timestep.
|
||||
prev_timestep (`int`):
|
||||
The previous discrete timestep in the diffusion chain.
|
||||
sample (`torch.Tensor`):
|
||||
A current instance of a sample created by the diffusion process.
|
||||
order (`int`):
|
||||
The order of UniP at this timestep (corresponds to the *p* in UniPC-p).
|
||||
|
||||
Returns:
|
||||
`torch.Tensor`:
|
||||
The sample tensor at the previous timestep.
|
||||
"""
|
||||
prev_timestep = args[0] if len(args) > 0 else kwargs.pop(
|
||||
"prev_timestep", None)
|
||||
if sample is None:
|
||||
if len(args) > 1:
|
||||
sample = args[1]
|
||||
else:
|
||||
raise ValueError(
|
||||
" missing `sample` as a required keyward argument")
|
||||
if order is None:
|
||||
if len(args) > 2:
|
||||
order = args[2]
|
||||
else:
|
||||
raise ValueError(
|
||||
" missing `order` as a required keyward argument")
|
||||
if prev_timestep is not None:
|
||||
deprecate(
|
||||
"prev_timestep",
|
||||
"1.0.0",
|
||||
"Passing `prev_timestep` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
|
||||
)
|
||||
model_output_list = self.model_outputs
|
||||
|
||||
s0 = self.timestep_list[-1]
|
||||
m0 = model_output_list[-1]
|
||||
x = sample
|
||||
|
||||
if self.solver_p:
|
||||
x_t = self.solver_p.step(model_output, s0, x).prev_sample
|
||||
return x_t
|
||||
|
||||
sigma_t, sigma_s0 = self.sigmas[self.step_index + 1], self.sigmas[
|
||||
self.step_index] # pyright: ignore
|
||||
alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma_t)
|
||||
alpha_s0, sigma_s0 = self._sigma_to_alpha_sigma_t(sigma_s0)
|
||||
|
||||
lambda_t = torch.log(alpha_t) - torch.log(sigma_t)
|
||||
lambda_s0 = torch.log(alpha_s0) - torch.log(sigma_s0)
|
||||
|
||||
h = lambda_t - lambda_s0
|
||||
device = sample.device
|
||||
|
||||
rks = []
|
||||
D1s = []
|
||||
for i in range(1, order):
|
||||
si = self.step_index - i # pyright: ignore
|
||||
mi = model_output_list[-(i + 1)]
|
||||
alpha_si, sigma_si = self._sigma_to_alpha_sigma_t(self.sigmas[si])
|
||||
lambda_si = torch.log(alpha_si) - torch.log(sigma_si)
|
||||
rk = (lambda_si - lambda_s0) / h
|
||||
rks.append(rk)
|
||||
D1s.append((mi - m0) / rk) # pyright: ignore
|
||||
|
||||
rks.append(1.0)
|
||||
rks = torch.tensor(rks, device=device)
|
||||
|
||||
R = []
|
||||
b = []
|
||||
|
||||
hh = -h if self.predict_x0 else h
|
||||
h_phi_1 = torch.expm1(hh) # h\phi_1(h) = e^h - 1
|
||||
h_phi_k = h_phi_1 / hh - 1
|
||||
|
||||
factorial_i = 1
|
||||
|
||||
if self.config.solver_type == "bh1":
|
||||
B_h = hh
|
||||
elif self.config.solver_type == "bh2":
|
||||
B_h = torch.expm1(hh)
|
||||
else:
|
||||
raise NotImplementedError()
|
||||
|
||||
for i in range(1, order + 1):
|
||||
R.append(torch.pow(rks, i - 1))
|
||||
b.append(h_phi_k * factorial_i / B_h)
|
||||
factorial_i *= i + 1
|
||||
h_phi_k = h_phi_k / hh - 1 / factorial_i
|
||||
|
||||
R = torch.stack(R)
|
||||
b = torch.tensor(b, device=device)
|
||||
|
||||
if len(D1s) > 0:
|
||||
D1s = torch.stack(D1s, dim=1) # (B, K)
|
||||
# for order 2, we use a simplified version
|
||||
if order == 2:
|
||||
rhos_p = torch.tensor([0.5], dtype=x.dtype, device=device)
|
||||
else:
|
||||
rhos_p = torch.linalg.solve(R[:-1, :-1],
|
||||
b[:-1]).to(device).to(x.dtype)
|
||||
else:
|
||||
D1s = None
|
||||
|
||||
if self.predict_x0:
|
||||
x_t_ = sigma_t / sigma_s0 * x - alpha_t * h_phi_1 * m0
|
||||
if D1s is not None:
|
||||
pred_res = torch.einsum("k,bkc...->bc...", rhos_p,
|
||||
D1s) # pyright: ignore
|
||||
else:
|
||||
pred_res = 0
|
||||
x_t = x_t_ - alpha_t * B_h * pred_res
|
||||
else:
|
||||
x_t_ = alpha_t / alpha_s0 * x - sigma_t * h_phi_1 * m0
|
||||
if D1s is not None:
|
||||
pred_res = torch.einsum("k,bkc...->bc...", rhos_p,
|
||||
D1s) # pyright: ignore
|
||||
else:
|
||||
pred_res = 0
|
||||
x_t = x_t_ - sigma_t * B_h * pred_res
|
||||
|
||||
x_t = x_t.to(x.dtype)
|
||||
return x_t
|
||||
|
||||
def multistep_uni_c_bh_update(
|
||||
self,
|
||||
this_model_output: torch.Tensor,
|
||||
*args,
|
||||
last_sample: torch.Tensor = None,
|
||||
this_sample: torch.Tensor = None,
|
||||
order: int = None, # pyright: ignore
|
||||
**kwargs,
|
||||
) -> torch.Tensor:
|
||||
"""
|
||||
One step for the UniC (B(h) version).
|
||||
|
||||
Args:
|
||||
this_model_output (`torch.Tensor`):
|
||||
The model outputs at `x_t`.
|
||||
this_timestep (`int`):
|
||||
The current timestep `t`.
|
||||
last_sample (`torch.Tensor`):
|
||||
The generated sample before the last predictor `x_{t-1}`.
|
||||
this_sample (`torch.Tensor`):
|
||||
The generated sample after the last predictor `x_{t}`.
|
||||
order (`int`):
|
||||
The `p` of UniC-p at this step. The effective order of accuracy should be `order + 1`.
|
||||
|
||||
Returns:
|
||||
`torch.Tensor`:
|
||||
The corrected sample tensor at the current timestep.
|
||||
"""
|
||||
this_timestep = args[0] if len(args) > 0 else kwargs.pop(
|
||||
"this_timestep", None)
|
||||
if last_sample is None:
|
||||
if len(args) > 1:
|
||||
last_sample = args[1]
|
||||
else:
|
||||
raise ValueError(
|
||||
" missing`last_sample` as a required keyward argument")
|
||||
if this_sample is None:
|
||||
if len(args) > 2:
|
||||
this_sample = args[2]
|
||||
else:
|
||||
raise ValueError(
|
||||
" missing`this_sample` as a required keyward argument")
|
||||
if order is None:
|
||||
if len(args) > 3:
|
||||
order = args[3]
|
||||
else:
|
||||
raise ValueError(
|
||||
" missing`order` as a required keyward argument")
|
||||
if this_timestep is not None:
|
||||
deprecate(
|
||||
"this_timestep",
|
||||
"1.0.0",
|
||||
"Passing `this_timestep` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
|
||||
)
|
||||
|
||||
model_output_list = self.model_outputs
|
||||
|
||||
m0 = model_output_list[-1]
|
||||
x = last_sample
|
||||
x_t = this_sample
|
||||
model_t = this_model_output
|
||||
|
||||
sigma_t, sigma_s0 = self.sigmas[self.step_index], self.sigmas[
|
||||
self.step_index - 1] # pyright: ignore
|
||||
alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma_t)
|
||||
alpha_s0, sigma_s0 = self._sigma_to_alpha_sigma_t(sigma_s0)
|
||||
|
||||
lambda_t = torch.log(alpha_t) - torch.log(sigma_t)
|
||||
lambda_s0 = torch.log(alpha_s0) - torch.log(sigma_s0)
|
||||
|
||||
h = lambda_t - lambda_s0
|
||||
device = this_sample.device
|
||||
|
||||
rks = []
|
||||
D1s = []
|
||||
for i in range(1, order):
|
||||
si = self.step_index - (i + 1) # pyright: ignore
|
||||
mi = model_output_list[-(i + 1)]
|
||||
alpha_si, sigma_si = self._sigma_to_alpha_sigma_t(self.sigmas[si])
|
||||
lambda_si = torch.log(alpha_si) - torch.log(sigma_si)
|
||||
rk = (lambda_si - lambda_s0) / h
|
||||
rks.append(rk)
|
||||
D1s.append((mi - m0) / rk) # pyright: ignore
|
||||
|
||||
rks.append(1.0)
|
||||
rks = torch.tensor(rks, device=device)
|
||||
|
||||
R = []
|
||||
b = []
|
||||
|
||||
hh = -h if self.predict_x0 else h
|
||||
h_phi_1 = torch.expm1(hh) # h\phi_1(h) = e^h - 1
|
||||
h_phi_k = h_phi_1 / hh - 1
|
||||
|
||||
factorial_i = 1
|
||||
|
||||
if self.config.solver_type == "bh1":
|
||||
B_h = hh
|
||||
elif self.config.solver_type == "bh2":
|
||||
B_h = torch.expm1(hh)
|
||||
else:
|
||||
raise NotImplementedError()
|
||||
|
||||
for i in range(1, order + 1):
|
||||
R.append(torch.pow(rks, i - 1))
|
||||
b.append(h_phi_k * factorial_i / B_h)
|
||||
factorial_i *= i + 1
|
||||
h_phi_k = h_phi_k / hh - 1 / factorial_i
|
||||
|
||||
R = torch.stack(R)
|
||||
b = torch.tensor(b, device=device)
|
||||
|
||||
if len(D1s) > 0:
|
||||
D1s = torch.stack(D1s, dim=1)
|
||||
else:
|
||||
D1s = None
|
||||
|
||||
# for order 1, we use a simplified version
|
||||
if order == 1:
|
||||
rhos_c = torch.tensor([0.5], dtype=x.dtype, device=device)
|
||||
else:
|
||||
rhos_c = torch.linalg.solve(R, b).to(device).to(x.dtype)
|
||||
|
||||
if self.predict_x0:
|
||||
x_t_ = sigma_t / sigma_s0 * x - alpha_t * h_phi_1 * m0
|
||||
if D1s is not None:
|
||||
corr_res = torch.einsum("k,bkc...->bc...", rhos_c[:-1], D1s)
|
||||
else:
|
||||
corr_res = 0
|
||||
D1_t = model_t - m0
|
||||
x_t = x_t_ - alpha_t * B_h * (corr_res + rhos_c[-1] * D1_t)
|
||||
else:
|
||||
x_t_ = alpha_t / alpha_s0 * x - sigma_t * h_phi_1 * m0
|
||||
if D1s is not None:
|
||||
corr_res = torch.einsum("k,bkc...->bc...", rhos_c[:-1], D1s)
|
||||
else:
|
||||
corr_res = 0
|
||||
D1_t = model_t - m0
|
||||
x_t = x_t_ - sigma_t * B_h * (corr_res + rhos_c[-1] * D1_t)
|
||||
x_t = x_t.to(x.dtype)
|
||||
return x_t
|
||||
|
||||
def index_for_timestep(self, timestep, schedule_timesteps=None):
|
||||
if schedule_timesteps is None:
|
||||
schedule_timesteps = self.timesteps
|
||||
|
||||
indices = (schedule_timesteps == timestep).nonzero()
|
||||
|
||||
# The sigma index that is taken for the **very** first `step`
|
||||
# is always the second index (or the last index if there is only 1)
|
||||
# This way we can ensure we don't accidentally skip a sigma in
|
||||
# case we start in the middle of the denoising schedule (e.g. for image-to-image)
|
||||
pos = 1 if len(indices) > 1 else 0
|
||||
|
||||
return indices[pos].item()
|
||||
|
||||
# Copied from diffusers.schedulers.scheduling_dpmsolver_multistep.DPMSolverMultistepScheduler._init_step_index
|
||||
def _init_step_index(self, timestep):
|
||||
"""
|
||||
Initialize the step_index counter for the scheduler.
|
||||
"""
|
||||
|
||||
if self.begin_index is None:
|
||||
if isinstance(timestep, torch.Tensor):
|
||||
timestep = timestep.to(self.timesteps.device)
|
||||
self._step_index = self.index_for_timestep(timestep)
|
||||
else:
|
||||
self._step_index = self._begin_index
|
||||
|
||||
def step(self,
|
||||
model_output: torch.Tensor,
|
||||
timestep: Union[int, torch.Tensor],
|
||||
sample: torch.Tensor,
|
||||
return_dict: bool = True,
|
||||
generator=None) -> Union[SchedulerOutput, Tuple]:
|
||||
"""
|
||||
Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with
|
||||
the multistep UniPC.
|
||||
|
||||
Args:
|
||||
model_output (`torch.Tensor`):
|
||||
The direct output from learned diffusion model.
|
||||
timestep (`int`):
|
||||
The current discrete timestep in the diffusion chain.
|
||||
sample (`torch.Tensor`):
|
||||
A current instance of a sample created by the diffusion process.
|
||||
return_dict (`bool`):
|
||||
Whether or not to return a [`~schedulers.scheduling_utils.SchedulerOutput`] or `tuple`.
|
||||
|
||||
Returns:
|
||||
[`~schedulers.scheduling_utils.SchedulerOutput`] or `tuple`:
|
||||
If return_dict is `True`, [`~schedulers.scheduling_utils.SchedulerOutput`] is returned, otherwise a
|
||||
tuple is returned where the first element is the sample tensor.
|
||||
|
||||
"""
|
||||
if self.num_inference_steps is None:
|
||||
raise ValueError(
|
||||
"Number of inference steps is 'None', you need to run 'set_timesteps' after creating the scheduler"
|
||||
)
|
||||
|
||||
if self.step_index is None:
|
||||
self._init_step_index(timestep)
|
||||
|
||||
use_corrector = (
|
||||
self.step_index > 0 and
|
||||
self.step_index - 1 not in self.disable_corrector and
|
||||
self.last_sample is not None # pyright: ignore
|
||||
)
|
||||
|
||||
model_output_convert = self.convert_model_output(
|
||||
model_output, sample=sample)
|
||||
if use_corrector:
|
||||
sample = self.multistep_uni_c_bh_update(
|
||||
this_model_output=model_output_convert,
|
||||
last_sample=self.last_sample,
|
||||
this_sample=sample,
|
||||
order=self.this_order,
|
||||
)
|
||||
|
||||
for i in range(self.config.solver_order - 1):
|
||||
self.model_outputs[i] = self.model_outputs[i + 1]
|
||||
self.timestep_list[i] = self.timestep_list[i + 1]
|
||||
|
||||
self.model_outputs[-1] = model_output_convert
|
||||
self.timestep_list[-1] = timestep # pyright: ignore
|
||||
|
||||
if self.config.lower_order_final:
|
||||
this_order = min(self.config.solver_order,
|
||||
len(self.timesteps) -
|
||||
self.step_index) # pyright: ignore
|
||||
else:
|
||||
this_order = self.config.solver_order
|
||||
|
||||
self.this_order = min(this_order,
|
||||
self.lower_order_nums + 1) # warmup for multistep
|
||||
assert self.this_order > 0
|
||||
|
||||
self.last_sample = sample
|
||||
prev_sample = self.multistep_uni_p_bh_update(
|
||||
model_output=model_output, # pass the original non-converted model output, in case solver-p is used
|
||||
sample=sample,
|
||||
order=self.this_order,
|
||||
)
|
||||
|
||||
if self.lower_order_nums < self.config.solver_order:
|
||||
self.lower_order_nums += 1
|
||||
|
||||
# upon completion increase step index by one
|
||||
self._step_index += 1 # pyright: ignore
|
||||
|
||||
if not return_dict:
|
||||
return (prev_sample,)
|
||||
|
||||
return SchedulerOutput(prev_sample=prev_sample)
|
||||
|
||||
def scale_model_input(self, sample: torch.Tensor, *args,
|
||||
**kwargs) -> torch.Tensor:
|
||||
"""
|
||||
Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
|
||||
current timestep.
|
||||
|
||||
Args:
|
||||
sample (`torch.Tensor`):
|
||||
The input sample.
|
||||
|
||||
Returns:
|
||||
`torch.Tensor`:
|
||||
A scaled input sample.
|
||||
"""
|
||||
return sample
|
||||
|
||||
# Copied from diffusers.schedulers.scheduling_dpmsolver_multistep.DPMSolverMultistepScheduler.add_noise
|
||||
def add_noise(
|
||||
self,
|
||||
original_samples: torch.Tensor,
|
||||
noise: torch.Tensor,
|
||||
timesteps: torch.IntTensor,
|
||||
) -> torch.Tensor:
|
||||
# Make sure sigmas and timesteps have the same device and dtype as original_samples
|
||||
sigmas = self.sigmas.to(
|
||||
device=original_samples.device, dtype=original_samples.dtype)
|
||||
if original_samples.device.type == "mps" and torch.is_floating_point(
|
||||
timesteps):
|
||||
# mps does not support float64
|
||||
schedule_timesteps = self.timesteps.to(
|
||||
original_samples.device, dtype=torch.float32)
|
||||
timesteps = timesteps.to(
|
||||
original_samples.device, dtype=torch.float32)
|
||||
else:
|
||||
schedule_timesteps = self.timesteps.to(original_samples.device)
|
||||
timesteps = timesteps.to(original_samples.device)
|
||||
|
||||
# begin_index is None when the scheduler is used for training or pipeline does not implement set_begin_index
|
||||
if self.begin_index is None:
|
||||
step_indices = [
|
||||
self.index_for_timestep(t, schedule_timesteps)
|
||||
for t in timesteps
|
||||
]
|
||||
elif self.step_index is not None:
|
||||
# add_noise is called after first denoising step (for inpainting)
|
||||
step_indices = [self.step_index] * timesteps.shape[0]
|
||||
else:
|
||||
# add noise is called before first denoising step to create initial latent(img2img)
|
||||
step_indices = [self.begin_index] * timesteps.shape[0]
|
||||
|
||||
sigma = sigmas[step_indices].flatten()
|
||||
while len(sigma.shape) < len(original_samples.shape):
|
||||
sigma = sigma.unsqueeze(-1)
|
||||
|
||||
alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma)
|
||||
noisy_samples = alpha_t * original_samples + sigma_t * noise
|
||||
return noisy_samples
|
||||
|
||||
def __len__(self):
|
||||
return self.config.num_train_timesteps
|
||||
Reference in New Issue
Block a user