File size: 3,735 Bytes
bd81ad3 |
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 |
from typing import Optional, Union, List, Tuple
import torch
from diffusers.utils.torch_utils import randn_tensor
from diffusers.pipelines.pipeline_utils import DiffusionPipeline, ImagePipelineOutput
class ScoreSdeVePipelineConditioned(DiffusionPipeline):
r"""
Pipeline for unconditional image generation.
This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods
implemented for all pipelines (downloading, saving, running on a particular device, etc.).
Parameters:
unet ([`UNet2DModel`]):
A `UNet2DModel` to denoise the encoded image.
scheduler ([`ScoreSdeVeScheduler`]):
A `ScoreSdeVeScheduler` to be used in combination with `unet` to denoise the encoded image.
"""
def __init__(self, unet, scheduler):
super().__init__()
self.register_modules(unet=unet, scheduler=scheduler)
@torch.no_grad()
def __call__(
self,
batch_size: int = 1,
num_inference_steps: int = 2000,
class_labels: Optional[torch.Tensor] = None,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
**kwargs,
) -> Union[ImagePipelineOutput, Tuple]:
r"""
The call function to the pipeline for generation.
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.
output_type (`str`, `optional`, defaults to `"pil"`):
The output format of the generated image. Choose between `PIL.Image` or `np.array`.
return_dict (`bool`, *optional*, defaults to `True`):
Whether or not to return a [`ImagePipelineOutput`] instead of a plain tuple.
Returns:
[`~pipelines.ImagePipelineOutput`] or `tuple`:
If `return_dict` is `True`, [`~pipelines.ImagePipelineOutput`] is returned, otherwise a `tuple` is
returned where 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 = randn_tensor(shape, generator=generator, device=self.device) * self.scheduler.init_noise_sigma
sample = sample.to(self.device)
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] * torch.ones(shape[0], device=self.device)
# correction step
for _ in range(self.scheduler.config.correct_steps):
model_output = self.unet(sample, sigma_t, class_labels).sample
sample = self.scheduler.step_correct(model_output, sample, generator=generator).prev_sample
# prediction step
model_output = model(sample, sigma_t, class_labels).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.clamp(0, 1)
sample = sample.cpu().permute(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) |