Spaces:
Sleeping
Sleeping
from typing import List, Optional, Tuple, Union | |
import torch | |
from diffusers.schedulers import DDIMScheduler | |
from diffusers.utils.torch_utils import randn_tensor | |
from diffusers.pipelines.pipeline_utils import DiffusionPipeline, ImagePipelineOutput | |
class DDIMPipelineCustom(DiffusionPipeline): | |
model_cpu_offload_seq = "unet" | |
def __init__(self, unet, scheduler): | |
super().__init__() | |
# make sure scheduler can always be converted to DDIM | |
scheduler = DDIMScheduler.from_config(scheduler.config) | |
self.register_modules(unet=unet, scheduler=scheduler) | |
def __call__( | |
self, | |
condition = None, | |
guidance: float = 1, | |
batch_size: int = 1, | |
generator: Optional[Union[torch.Generator, List[torch.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]: | |
# Sample gaussian noise to begin loop | |
if isinstance(self.unet.config.sample_size, int): | |
image_shape = ( | |
batch_size, | |
self.unet.config.in_channels, | |
self.unet.config.sample_size, | |
self.unet.config.sample_size, | |
) | |
else: | |
image_shape = (batch_size, self.unet.config.in_channels, *self.unet.config.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." | |
) | |
image = randn_tensor(image_shape, generator=generator, device=self._execution_device, 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 | |
uncond = -torch.ones(batch_size, device=self.device) | |
if condition is not None: | |
model_output_uncond = self.unet(image, t, uncond).sample | |
model_output_cond = self.unet(image, t, condition).sample | |
model_output = torch.lerp(model_output_uncond, model_output_cond, guidance) | |
else: | |
model_output = self.unet(image, t, uncond).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).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) |