File size: 5,527 Bytes
21231ee |
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 |
# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
# 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 List, Optional, Tuple, Union
import paddle
from ...pipeline_utils import DiffusionPipeline, ImagePipelineOutput
class DDIMPipeline(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 xxxx, 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)
@paddle.no_grad()
def __call__(
self,
batch_size: int = 1,
generator: Optional[Union[paddle.Generator, List[paddle.Generator]]] = None,
eta: float = 0.0,
num_inference_steps: int = 50,
use_clipped_model_output: Optional[bool] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
) -> Union[ImagePipelineOutput, Tuple]:
r"""
Args:
batch_size (`int`, *optional*, defaults to 1):
The number of images to generate.
generator (`paddle.Generator`, *optional*):
One or a list of paddle generator(s) to make generation deterministic.
eta (`float`, *optional*, defaults to 0.0):
The eta parameter which controls the scale of the variance (0 is DDIM and 1 is one type of DDPM).
num_inference_steps (`int`, *optional*, defaults to 50):
The number of denoising steps. More denoising steps usually lead to a higher quality image at the
expense of slower inference.
use_clipped_model_output (`bool`, *optional*, defaults to `None`):
if `True` or `False`, see documentation for `DDIMScheduler.step`. If `None`, nothing is passed
downstream to the scheduler. So use `None` for schedulers which don't support this argument.
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.
"""
# 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 isinstance(generator, list) and len(generator) != batch_size:
raise ValueError(
f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
f" size of {batch_size}. Make sure the batch size matches the length of the generators."
)
if isinstance(generator, list):
shape = (1,) + image_shape[1:]
image = [paddle.randn(shape, generator=generator[i], dtype=self.unet.dtype) for i in range(batch_size)]
image = paddle.concat(image, axis=0)
else:
image = paddle.randn(image_shape, generator=generator, dtype=self.unet.dtype)
# 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. predict previous mean of image x_t-1 and add variance depending on eta
# eta corresponds to η in paper and should be between [0, 1]
# do x_t -> x_t-1
image = self.scheduler.step(
model_output, t, image, eta=eta, use_clipped_model_output=use_clipped_model_output, generator=generator
).prev_sample
image = (image / 2 + 0.5).clip(0, 1)
image = image.transpose([0, 2, 3, 1]).cast("float32").numpy()
if output_type == "pil":
image = self.numpy_to_pil(image)
if not return_dict:
return (image,)
return ImagePipelineOutput(images=image)
|