Upload pipeline.py

pipeline.py

@@ -0,0 +1,66 @@
+from typing import List, Optional, Tuple, Union
+from diffusers import DiffusionPipeline, ImagePipelineOutput, randn_tensor
+
+import torch
+
+
+class DDPMConditionalPipeline(DiffusionPipeline):
+    model_cpu_offload_seq = "unet"
+
+    def __init__(self, unet, scheduler):
+        super().__init__()
+        self.register_modules(unet=unet, scheduler=scheduler)
+
+    @torch.no_grad()
+    def __call__(
+        self,
+        label,
+        batch_size: int = 1,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        num_inference_steps: int = 1000,
+        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 self.device.type == "mps":
+            # randn does not work reproducibly on mps
+            image = randn_tensor(image_shape, generator=generator)
+            image = image.to(self.device)
+        else:
+            image = randn_tensor(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, label).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)