KEMBAR78
"joint_attention_kwargs" don't pass the parameters to AttentionProcessor · Issue #8855 · huggingface/diffusers · GitHub
Skip to content

"joint_attention_kwargs" don't pass the parameters to AttentionProcessor #8855

@cyysc1998

Description

@cyysc1998

I want to train my ipadapter in sd3. I noticed that joint_attention_kwargs is used in passing the parameters to AttentionProcessor (https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformers/transformer_sd3.py#L309). But it seems joint_attention_kwargs is not passed to transformer_blocks. Is my usage method wrong or this parameter has not been developed yet? Thank you!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions