diffusers/pr_13171/en/api/modular_diffusers/pipeline_blocks.md

Pipeline blocks

ModularPipelineBlocks[[diffusers.ModularPipelineBlocks]]

diffusers.ModularPipelineBlocks[[diffusers.ModularPipelineBlocks]]

Source

Base class for all Pipeline Blocks: ConditionalPipelineBlocks, AutoPipelineBlocks, SequentialPipelineBlocks, LoopSequentialPipelineBlocks

ModularPipelineBlocks provides method to load and save the definition of pipeline blocks.

> This is an experimental feature and is likely to change in the future.

get_block_statediffusers.ModularPipelineBlocks.get_block_statehttps://github.com/huggingface/diffusers/blob/vr_13171/src/diffusers/modular_pipelines/modular_pipeline.py#L459[{"name": "state", "val": ": PipelineState"}] Get all inputs and intermediates in one dictionary

get_execution_blocks[[diffusers.ModularPipelineBlocks.get_execution_blocks]]

Source

Get the block(s) that would execute given the inputs. Must be implemented by subclasses that support conditional block selection.

Parameters:

• **kwargs : Input names and values. Only trigger inputs affect block selection.

get_workflow[[diffusers.ModularPipelineBlocks.get_workflow]]

Source

Get the execution blocks for a specific workflow. Must be implemented by subclasses that define _workflow_map.

Parameters:

workflow_name : Name of the workflow to retrieve.

init_pipeline[[diffusers.ModularPipelineBlocks.init_pipeline]]

Source

create a ModularPipeline, optionally accept pretrained_model_name_or_path to load from hub.

SequentialPipelineBlocks[[diffusers.SequentialPipelineBlocks]]

diffusers.SequentialPipelineBlocks[[diffusers.SequentialPipelineBlocks]]

Source

A Pipeline Blocks that combines multiple pipeline block classes into one. When called, it will call each block in sequence.

This class inherits from ModularPipelineBlocks. Check the superclass documentation for the generic methods the library implements for all the pipeline blocks (such as loading or saving etc.)

> This is an experimental feature and is likely to change in the future.

from_blocks_dictdiffusers.SequentialPipelineBlocks.from_blocks_dicthttps://github.com/huggingface/diffusers/blob/vr_13171/src/diffusers/modular_pipelines/modular_pipeline.py#L964[{"name": "blocks_dict", "val": ": dict"}, {"name": "description", "val": ": str | None = None"}]- blocks_dict -- Dictionary mapping block names to block classes or instances0A new SequentialPipelineBlocks instance Creates a SequentialPipelineBlocks instance from a dictionary of blocks.

Parameters:

block_classes : list of block classes to be used

block_names : list of prefixes for each block

Returns:

A new SequentialPipelineBlocks instance

get_execution_blocks[[diffusers.SequentialPipelineBlocks.get_execution_blocks]]

Source

Get the blocks that would execute given the specified inputs.

As the traversal walks through sequential blocks, intermediate outputs from resolved blocks are added to the active inputs. This means conditional blocks that depend on intermediates (e.g., "run img2img if image_latents is present") will resolve correctly, as long as the condition is based on presence/absence (None or not None), not on the actual value.

Parameters:

• **kwargs : Input names and values. Only trigger inputs affect block selection.

Returns:

SequentialPipelineBlocks containing only the blocks that would execute

LoopSequentialPipelineBlocks[[diffusers.LoopSequentialPipelineBlocks]]

diffusers.LoopSequentialPipelineBlocks[[diffusers.LoopSequentialPipelineBlocks]]

Source

A Pipeline blocks that combines multiple pipeline block classes into a For Loop. When called, it will call each block in sequence.

This class inherits from ModularPipelineBlocks. Check the superclass documentation for the generic methods the library implements for all the pipeline blocks (such as loading or saving etc.)

> This is an experimental feature and is likely to change in the future.

from_blocks_dictdiffusers.LoopSequentialPipelineBlocks.from_blocks_dicthttps://github.com/huggingface/diffusers/blob/vr_13171/src/diffusers/modular_pipelines/modular_pipeline.py#L1398[{"name": "blocks_dict", "val": ": dict"}]- blocks_dict -- Dictionary mapping block names to block instances0A new LoopSequentialPipelineBlocks instance

Creates a LoopSequentialPipelineBlocks instance from a dictionary of blocks.

Parameters:

block_classes : list of block classes to be used

block_names : list of prefixes for each block

Returns:

A new LoopSequentialPipelineBlocks instance

AutoPipelineBlocks[[diffusers.AutoPipelineBlocks]]

diffusers.AutoPipelineBlocks[[diffusers.AutoPipelineBlocks]]

Source

A Pipeline Blocks that automatically selects a block to run based on the presence of trigger inputs.

This is a specialized version of ConditionalPipelineBlocks where:

• Each block has one corresponding trigger input (1:1 mapping)
• Block selection is automatic: the first block whose trigger input is present gets selected
• block_trigger_inputs must have the same length as block_names and block_classes
• Use None in block_trigger_inputs to specify the default block, i.e the block that will run if no trigger inputs are present

Example:

    class MyAutoBlock(AutoPipelineBlocks):
        block_classes = [InpaintEncoderBlock, ImageEncoderBlock, TextEncoderBlock]
        block_names = ["inpaint", "img2img", "text2img"]
        block_trigger_inputs = ["mask_image", "image", None]  # text2img is the default

With this definition:

• As long as mask_image is provided, "inpaint" block runs (regardless of image being provided or not)
• If mask_image is not provided but image is provided, "img2img" block runs
• Otherwise, "text2img" block runs (default, trigger is None)

select_blockdiffusers.AutoPipelineBlocks.select_blockhttps://github.com/huggingface/diffusers/blob/vr_13171/src/diffusers/modular_pipelines/modular_pipeline.py#L889[{"name": "**kwargs", "val": ""}] Select block based on which trigger input is present (not None).

Parameters:

block_classes : List of block classes to be used. Must have the same length as block_names and block_trigger_inputs.

block_names : List of names for each block. Must have the same length as block_classes and block_trigger_inputs.

block_trigger_inputs : List of input names where each element specifies the trigger input for the corresponding block. Use None to mark the default block.