States¶
Blocks rely on the PipelineState
and BlockState
data structures for communicating and sharing data.
State | Description |
---|---|
PipelineState |
Maintains the overall data required for a pipeline's execution and allows blocks to read and update its data. |
BlockState |
Allows each block to perform its computation with the necessary data from inputs |
This guide explains how states work and how they connect blocks.
PipelineState¶
The PipelineState
is a global state container for all blocks. It maintains the complete runtime state of the pipeline and provides a structured way for blocks to read from and write to shared data.
There are two dict's in PipelineState
for structuring data.
- The
values
dict is a mutable state containing a copy of user provided input values and intermediate output values generated by blocks. If a block modifies aninput
, it will be reflected in thevalues
dict after callingset_block_state
.
PipelineState(
values={
'prompt': 'a cat'
'guidance_scale': 7.0
'num_inference_steps': 25
'prompt_embeds': tensor(dtype=ms.float32, shape=[1, 1, 1, 1])
'negative_prompt_embeds': None
},
)
BlockState¶
The BlockState
is a local view of the relevant variables an individual block needs from PipelineState
for performing it's computations.
Access these variables directly as attributes like block_state.image
.
BlockState(
image: <PIL.Image.Image image mode=RGB size=512x512 at 0x7F3ECC494640>
)
When a block's __call__
method is executed, it retrieves the BlockState
with self.get_block_state(state)
, performs it's operations, and updates PipelineState
with self.set_block_state(state, block_state)
.
def __call__(self, components, state):
# retrieve BlockState
block_state = self.get_block_state(state)
# computation logic on inputs
# update PipelineState
self.set_block_state(state, block_state)
return components, state
State interaction¶
PipelineState
and BlockState
interaction is defined by a block's inputs
, and intermediate_outputs
.
inputs
, a block can modify an input - likeblock_state.image
- and this change can be propagated globally toPipelineState
by callingset_block_state
.intermediate_outputs
, is a new variable that a block creates. It is added to thePipelineState
'svalues
dict and is available as for subsequent blocks or accessed by users as a final output from the pipeline.