Spaces:
Runtime error
Runtime error
File size: 5,541 Bytes
522606a |
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 |
# Copyright 2022 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.
from typing import Optional, Tuple, Union
import torch
from ...configuration_utils import FrozenDict
from ...pipeline_utils import DiffusionPipeline, ImagePipelineOutput
from ...utils import deprecate
class DDPMPipeline(DiffusionPipeline):
r"""
This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the
library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)
Parameters:
unet ([`UNet2DModel`]): U-Net architecture to denoise the encoded image.
scheduler ([`SchedulerMixin`]):
A scheduler to be used in combination with `unet` to denoise the encoded image. Can be one of
[`DDPMScheduler`], or [`DDIMScheduler`].
"""
def __init__(self, unet, scheduler):
super().__init__()
self.register_modules(unet=unet, scheduler=scheduler)
@torch.no_grad()
def __call__(
self,
batch_size: int = 1,
generator: Optional[torch.Generator] = None,
num_inference_steps: int = 1000,
output_type: Optional[str] = "pil",
return_dict: bool = True,
**kwargs,
) -> Union[ImagePipelineOutput, Tuple]:
r"""
Args:
batch_size (`int`, *optional*, defaults to 1):
The number of images to generate.
generator (`torch.Generator`, *optional*):
A [torch generator](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation
deterministic.
num_inference_steps (`int`, *optional*, defaults to 1000):
The number of denoising steps. More denoising steps usually lead to a higher quality image at the
expense of slower inference.
output_type (`str`, *optional*, defaults to `"pil"`):
The output format of the generate image. Choose between
[PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
return_dict (`bool`, *optional*, defaults to `True`):
Whether or not to return a [`~pipeline_utils.ImagePipelineOutput`] instead of a plain tuple.
Returns:
[`~pipeline_utils.ImagePipelineOutput`] or `tuple`: [`~pipelines.utils.ImagePipelineOutput`] if
`return_dict` is True, otherwise a `tuple. When returning a tuple, the first element is a list with the
generated images.
"""
message = (
"Please make sure to instantiate your scheduler with `prediction_type` instead. E.g. `scheduler ="
" DDPMScheduler.from_pretrained(<model_id>, prediction_type='epsilon')`."
)
predict_epsilon = deprecate("predict_epsilon", "0.11.0", message, take_from=kwargs)
if predict_epsilon is not None:
new_config = dict(self.scheduler.config)
new_config["prediction_type"] = "epsilon" if predict_epsilon else "sample"
self.scheduler._internal_dict = FrozenDict(new_config)
if generator is not None and generator.device.type != self.device.type and self.device.type != "mps":
message = (
f"The `generator` device is `{generator.device}` and does not match the pipeline "
f"device `{self.device}`, so the `generator` will be ignored. "
f'Please use `torch.Generator(device="{self.device}")` instead.'
)
deprecate(
"generator.device == 'cpu'",
"0.11.0",
message,
)
generator = None
# Sample gaussian noise to begin loop
if isinstance(self.unet.sample_size, int):
image_shape = (batch_size, self.unet.in_channels, self.unet.sample_size, self.unet.sample_size)
else:
image_shape = (batch_size, self.unet.in_channels, *self.unet.sample_size)
if self.device.type == "mps":
# randn does not work reproducibly on mps
image = torch.randn(image_shape, generator=generator)
image = image.to(self.device)
else:
image = torch.randn(image_shape, generator=generator, device=self.device)
# set step values
self.scheduler.set_timesteps(num_inference_steps)
for t in self.progress_bar(self.scheduler.timesteps):
# 1. predict noise model_output
model_output = self.unet(image, t).sample
# 2. compute previous image: x_t -> x_t-1
image = self.scheduler.step(model_output, t, image, generator=generator).prev_sample
image = (image / 2 + 0.5).clamp(0, 1)
image = image.cpu().permute(0, 2, 3, 1).numpy()
if output_type == "pil":
image = self.numpy_to_pil(image)
if not return_dict:
return (image,)
return ImagePipelineOutput(images=image)
|