Skip to content

Implement missing features on ModularPipeline #12386

Description

@vladmandic

as i'm looking to take advantage of new ModularPipeline ask is to implement some currently missing features

my use case is to convert existing loaded model using standard pipeline into modular pipeline. that functionality was provided via #11915 and is now working.

first minor obstacle is that modular pipeline does not have defined params for execution
in standard pipeline i can inspect __call__ signature to see which are allowed params
i currently work around this using
possible = [input_param.name for input_param in model.blocks.inputs]
please advise if this is acceptable

second one is that modular pipelines don't seem to implement normal callbacks at all (e.g. callback_on_step_end_tensor_inputs? at the minimum we need some kind of callback functionality to capture interim latents on each step

third is more cosmetic - modular pipeline does implement set_progress_bar_config, but its not doing anything as its not implement on actual block (tested with StableDiffusionXLModularPipeline)

cc @yiyixuxu @DN6 @sayakpaul

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    roadmapAdd to current release roadmapstaleIssues that haven't received updates

    Type

    No type

    Projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions