class ImageEncodeStep(ModularPipelineBlocks):
    ...

    @property
    def inputs(self):
        return [
            InputParam(name="image", type_hint="PIL.Image", required=True, description="raw input image to process"),
        ]
    ...

class ImageEncodeStep(ModularPipelineBlocks):
    ...

    @property
    def intermediate_outputs(self):
        return [
            OutputParam(name="image_latents", description="latents representing the image"),
        ]

    ...

class ImageEncodeStep(ModularPipelineBlocks):
    ...

    @property
    def expected_components(self):
        return [
            ComponentSpec(name="vae", type_hint=AutoencoderKL),
        ]

    @property
    def expected_configs(self):
        return [
            ConfigSpec("force_zeros_for_empty_prompt", True),
        ]

    ...

class ImageEncodeStep(ModularPipelineBlocks):

    def __call__(self, components, state):
        # Get a local view of the state variables this block needs
        block_state = self.get_block_state(state)

        # Your computation logic here
        # block_state contains all your inputs
        # Access them like: block_state.image, block_state.processed_image

        # Update the pipeline state with your updated block_states
        self.set_block_state(state, block_state)
        return components, state

from diffusers import ComponentSpec, AutoencoderKL
from diffusers.modular_pipelines import InputParam, ModularPipelineBlocks, OutputParam


class ImageEncodeStep(ModularPipelineBlocks):

    @property
    def description(self):
        return "Encode an image into latent space."

    @property
    def expected_components(self):
        return [
            ComponentSpec(name="vae", type_hint=AutoencoderKL),
        ]

    @property
    def inputs(self):
        return [
            InputParam(name="image", type_hint="PIL.Image", required=True, description="raw input image to process"),
        ]

    @property
    def intermediate_outputs(self):
        return [
            OutputParam(name="image_latents", type_hint="torch.Tensor", description="latents representing the image"),
        ]

    def __call__(self, components, state):
        block_state = self.get_block_state(state)
        block_state.image_latents = components.vae.encode(block_state.image)
        self.set_block_state(state, block_state)
        return components, state

block = ImageEncoderStep()
print(block.doc)
class ImageEncodeStep

  Encode an image into latent space.

  Components:
      vae (`AutoencoderKL`)

  Inputs:
      image (`PIL.Image`):
          raw input image to process

  Outputs:
      image_latents (`torch.Tensor`):
          latents representing the image