Skip to content

The Klein LoRA training results lack fine details and are blurry, with performance inferior to both Kontext and Qwen-Image-Edit-2511. #1268

@zzzgit256

Description

@zzzgit256

4b、base-4b、9b、base-9b both blurry, use comfyui
workflow from : https://blog.comfy.org/p/flux2-klein-4b-fast-local-image-editing

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