Spaces:
Runtime error
Runtime error
# 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 ...models import UNet2DModel | |
from ...pipeline_utils import DiffusionPipeline, ImagePipelineOutput | |
from ...schedulers import ScoreSdeVeScheduler | |
class ScoreSdeVePipeline(DiffusionPipeline): | |
r""" | |
Parameters: | |
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.) | |
unet ([`UNet2DModel`]): U-Net architecture to denoise the encoded image. scheduler ([`SchedulerMixin`]): | |
The [`ScoreSdeVeScheduler`] scheduler to be used in combination with `unet` to denoise the encoded image. | |
""" | |
unet: UNet2DModel | |
scheduler: ScoreSdeVeScheduler | |
def __init__(self, unet: UNet2DModel, scheduler: DiffusionPipeline): | |
super().__init__() | |
self.register_modules(unet=unet, scheduler=scheduler) | |
def __call__( | |
self, | |
batch_size: int = 1, | |
num_inference_steps: int = 2000, | |
generator: Optional[Union[paddle.Generator, List[paddle.Generator]]] = None, | |
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 (`paddle.Generator`, *optional*): | |
One or a list of paddle generator(s) to make generation deterministic. | |
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. | |
""" | |
img_size = self.unet.config.sample_size | |
shape = (batch_size, 3, img_size, img_size) | |
model = self.unet | |
sample = paddle.randn(shape, generator=generator) * self.scheduler.init_noise_sigma | |
self.scheduler.set_timesteps(num_inference_steps) | |
self.scheduler.set_sigmas(num_inference_steps) | |
for i, t in enumerate(self.progress_bar(self.scheduler.timesteps)): | |
sigma_t = self.scheduler.sigmas[i] * paddle.ones((shape[0],)) | |
# correction step | |
for _ in range(self.scheduler.config.correct_steps): | |
model_output = self.unet(sample, sigma_t).sample | |
sample = self.scheduler.step_correct(model_output, sample, generator=generator).prev_sample | |
# prediction step | |
model_output = model(sample, sigma_t).sample | |
output = self.scheduler.step_pred(model_output, t, sample, generator=generator) | |
sample, sample_mean = output.prev_sample, output.prev_sample_mean | |
sample = sample_mean.clip(0, 1) | |
sample = sample.transpose([0, 2, 3, 1]).numpy() | |
if output_type == "pil": | |
sample = self.numpy_to_pil(sample) | |
if not return_dict: | |
return (sample,) | |
return ImagePipelineOutput(images=sample) | |