Skip to content

Does LoRa affect memory usage and run-time during inference? #2247

@FBehrad

Description

@FBehrad

Hello,
I fine-tuned the Stable Diffusion using LoRa. Although the fine-tuning became much faster and required less memory, the inference was heavily affected. Now, inference has become very slow and needs more memory.
Is this normal?

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