Skip to content

Conversation

@yiyixuxu
Copy link
Collaborator

@yiyixuxu yiyixuxu commented Sep 9, 2025

No description provided.

@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

cubiq added a commit to cubiq/Mellon that referenced this pull request Sep 23, 2025


@dataclass(frozen=True)
class MellonParam:
Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

MellonParam: this is to support UI element configuration in Mellon

we will support a direct conversion from InputParam

SUPPORTED_NODE_TYPES = {"controlnet", "vae_encoder", "denoise", "text_encoder", "decoder"}


# Mellon Input Parameters (runtime parameters, not models)
Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

we keep a common configuration for mellon inputs/model_onputs/outputs

]
)

MODULAR_PIPELINE_BLOCKS_MAPPING = OrderedDict(
Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

remove this map, each ModularPipeline should specify a default_blocks_name instead

)


class QwenImageCoreDenoiseStep(SequentialPipelineBlocks):
Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

adding a *CoreDenoiseStep -> corresponding the "Denoise" node in mellon: bascially takes all the encoder inputs and output latents

@yiyixuxu yiyixuxu merged commit 76d4e41 into main Sep 29, 2025
16 of 17 checks passed
@yiyixuxu yiyixuxu deleted the modular-small-fix branch September 29, 2025 21:42
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants