Skip to content

The model's performance is inconsistent. #62

@yun189

Description

@yun189

I'm not sure how to write text prompts or CoT instructions to generate consistent sound effects.
Has anyone else encountered this? I'm trying to figure out whether my prompts aren't good enough, or if the model's output simply isn't capable of consistently adhering to the text 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