Spaces:
Running
on
Zero
Running
on
Zero
File size: 10,402 Bytes
d65c9b3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 |
from diffusers import DDPMScheduler, LCMScheduler
from diffusers.utils import BaseOutput
from diffusers.utils.torch_utils import randn_tensor
import torch
from typing import List, Optional, Tuple, Union
import numpy as np
class DDPMSchedulerOutput(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.
pred_original_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
The predicted denoised sample `(x_{0})` based on the model output from the current timestep.
`pred_original_sample` can be used to preview progress or for guidance.
"""
prev_sample: torch.FloatTensor
pred_original_sample: Optional[torch.FloatTensor] = None
class MyDDPMScheduler(DDPMScheduler):
def set_noise_list(self, noise_list):
self.noise_list = noise_list
def step_and_update(
self,
model_output: torch.FloatTensor,
timestep: int,
sample: torch.FloatTensor,
next_sample: torch.FloatTensor = None,
generator=None,
return_dict: bool = True,
) -> Union[DDPMSchedulerOutput, 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.
generator (`torch.Generator`, *optional*):
A random number generator.
return_dict (`bool`, *optional*, defaults to `True`):
Whether or not to return a [`~schedulers.scheduling_ddpm.DDPMSchedulerOutput`] or `tuple`.
Returns:
[`~schedulers.scheduling_ddpm.DDPMSchedulerOutput`] or `tuple`:
If return_dict is `True`, [`~schedulers.scheduling_ddpm.DDPMSchedulerOutput`] is returned, otherwise a
tuple is returned where the first element is the sample tensor.
"""
t = timestep
prev_t = self.previous_timestep(t)
if model_output.shape[1] == sample.shape[1] * 2 and self.variance_type in ["learned", "learned_range"]:
model_output, predicted_variance = torch.split(model_output, sample.shape[1], dim=1)
else:
predicted_variance = None
# 1. compute alphas, betas
alpha_prod_t = self.alphas_cumprod[t]
alpha_prod_t_prev = self.alphas_cumprod[prev_t] if prev_t >= 0 else self.one
beta_prod_t = 1 - alpha_prod_t
beta_prod_t_prev = 1 - alpha_prod_t_prev
current_alpha_t = alpha_prod_t / alpha_prod_t_prev
current_beta_t = 1 - current_alpha_t
# 2. compute predicted original sample from predicted noise also called
# "predicted x_0" of formula (15) from https://arxiv.org/pdf/2006.11239.pdf
if self.config.prediction_type == "epsilon":
pred_original_sample = (sample - beta_prod_t ** (0.5) * model_output) / alpha_prod_t ** (0.5)
elif self.config.prediction_type == "sample":
pred_original_sample = model_output
elif self.config.prediction_type == "v_prediction":
pred_original_sample = (alpha_prod_t**0.5) * sample - (beta_prod_t**0.5) * model_output
else:
raise ValueError(
f"prediction_type given as {self.config.prediction_type} must be one of `epsilon`, `sample` or"
" `v_prediction` for the DDPMScheduler."
)
# 3. Clip or threshold "predicted x_0"
if self.config.thresholding:
pred_original_sample = self._threshold_sample(pred_original_sample)
elif self.config.clip_sample:
pred_original_sample = pred_original_sample.clamp(
-self.config.clip_sample_range, self.config.clip_sample_range
)
# 4. Compute coefficients for pred_original_sample x_0 and current sample x_t
# See formula (7) from https://arxiv.org/pdf/2006.11239.pdf
pred_original_sample_coeff = (alpha_prod_t_prev ** (0.5) * current_beta_t) / beta_prod_t
current_sample_coeff = current_alpha_t ** (0.5) * beta_prod_t_prev / beta_prod_t
# 5. Compute predicted previous sample µ_t
# See formula (7) from https://arxiv.org/pdf/2006.11239.pdf
pred_prev_sample = pred_original_sample_coeff * pred_original_sample + current_sample_coeff * sample
# 6. Add noise
variance = 0
if t > 0:
v = (self._get_variance(t, predicted_variance=predicted_variance) ** 0.5)
if v > 1e-9:
self.noise_list[int(t.item() // (1000 // self.num_inference_steps))] = (next_sample - pred_prev_sample) / v
variance_noise = self.noise_list[int(t.item() // (1000 // self.num_inference_steps))]
variance = v * variance_noise
pred_prev_sample = pred_prev_sample + variance
if not return_dict:
return (pred_prev_sample,)
return DDPMSchedulerOutput(prev_sample=pred_prev_sample, pred_original_sample=pred_original_sample)
def step(
self,
model_output: torch.FloatTensor,
timestep: int,
sample: torch.FloatTensor,
generator=None,
return_dict: bool = True,
) -> Union[DDPMSchedulerOutput, 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.
generator (`torch.Generator`, *optional*):
A random number generator.
return_dict (`bool`, *optional*, defaults to `True`):
Whether or not to return a [`~schedulers.scheduling_ddpm.DDPMSchedulerOutput`] or `tuple`.
Returns:
[`~schedulers.scheduling_ddpm.DDPMSchedulerOutput`] or `tuple`:
If return_dict is `True`, [`~schedulers.scheduling_ddpm.DDPMSchedulerOutput`] is returned, otherwise a
tuple is returned where the first element is the sample tensor.
"""
t = timestep
prev_t = self.previous_timestep(t)
if model_output.shape[1] == sample.shape[1] * 2 and self.variance_type in ["learned", "learned_range"]:
model_output, predicted_variance = torch.split(model_output, sample.shape[1], dim=1)
else:
predicted_variance = None
# 1. compute alphas, betas
alpha_prod_t = self.alphas_cumprod[t]
alpha_prod_t_prev = self.alphas_cumprod[prev_t] if prev_t >= 0 else self.one
beta_prod_t = 1 - alpha_prod_t
beta_prod_t_prev = 1 - alpha_prod_t_prev
current_alpha_t = alpha_prod_t / alpha_prod_t_prev
current_beta_t = 1 - current_alpha_t
# 2. compute predicted original sample from predicted noise also called
# "predicted x_0" of formula (15) from https://arxiv.org/pdf/2006.11239.pdf
if self.config.prediction_type == "epsilon":
pred_original_sample = (sample - beta_prod_t ** (0.5) * model_output) / alpha_prod_t ** (0.5)
elif self.config.prediction_type == "sample":
pred_original_sample = model_output
elif self.config.prediction_type == "v_prediction":
pred_original_sample = (alpha_prod_t**0.5) * sample - (beta_prod_t**0.5) * model_output
else:
raise ValueError(
f"prediction_type given as {self.config.prediction_type} must be one of `epsilon`, `sample` or"
" `v_prediction` for the DDPMScheduler."
)
# 3. Clip or threshold "predicted x_0"
if self.config.thresholding:
pred_original_sample = self._threshold_sample(pred_original_sample)
elif self.config.clip_sample:
pred_original_sample = pred_original_sample.clamp(
-self.config.clip_sample_range, self.config.clip_sample_range
)
# 4. Compute coefficients for pred_original_sample x_0 and current sample x_t
# See formula (7) from https://arxiv.org/pdf/2006.11239.pdf
pred_original_sample_coeff = (alpha_prod_t_prev ** (0.5) * current_beta_t) / beta_prod_t
current_sample_coeff = current_alpha_t ** (0.5) * beta_prod_t_prev / beta_prod_t
# 5. Compute predicted previous sample µ_t
# See formula (7) from https://arxiv.org/pdf/2006.11239.pdf
pred_prev_sample = pred_original_sample_coeff * pred_original_sample + current_sample_coeff * sample
# 6. Add noise
variance = 0
if t > 0:
device = model_output.device
variance_noise = self.noise_list[int(t.item() // (1000 // self.num_inference_steps))]
if self.variance_type == "fixed_small_log":
variance = self._get_variance(t, predicted_variance=predicted_variance) * variance_noise
elif self.variance_type == "learned_range":
variance = self._get_variance(t, predicted_variance=predicted_variance)
variance = torch.exp(0.5 * variance) * variance_noise
else:
variance = (self._get_variance(t, predicted_variance=predicted_variance) ** 0.5) * variance_noise
pred_prev_sample = pred_prev_sample + variance
if not return_dict:
return (pred_prev_sample,)
return DDPMSchedulerOutput(prev_sample=pred_prev_sample, pred_original_sample=pred_original_sample)
|