Skip to content

SD3: add T5-XXL text encoder support #104

Description

@stikves

SD3 pipeline currently uses dual CLIP (L+G) only, zero-padding the T5 portion of encoder_hidden_states. Adding T5-XXL (256 token seq len) would significantly improve text comprehension for complex prompts.

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