CivArchive
    Preview 5784010
    Preview 5785040
    Preview 5923890
    Preview 5923889
    Preview 5923892
    Preview 5923891

    Recommended Usage

    Sampler: Euler a | 50 Steps

    Hires, Fix: 4x Ultrasharp

    30 Steps | 0.4 Denoise | 2x Upscale

    ADetailer (default settings):

    1st Model: face_yolov8.pt (leave prompt empty) - (V2 Inpainting model for V2)

    2nd Model: mediapipe_face_mesh_eyes_only (leave prompt empty) - (V2 Inpainting model for V2)

    FreeU (default settings)

    Also recommend using Regional Prompter with Prompt-Ex for vertical or square images, or Matrix 1,1,1 (columns) for landscape.


    FreeU: https://github.com/ljleb/sd-webui-freeu


    Description

    Partially trained partially merged model. Can do a lot more now and many things are clearer. Style changed a fair bit and is less consistent.

    Recommend using V2 inpainting for ADetailer.

    Can kinda do furry images I think. There were many furry models merged in.

    FAQ

    Comments (17)

    Cass_Jan 23, 2024
    CivitAI

    how do i use this FreeU extension? do i just enable it in the extension list and that's it? (a1111)

    MidFR
    Author
    Jan 23, 2024

    Need to enable it in the generation tab of txt2img/img2img and click the ✅

    Ses_AIJan 24, 2024
    CivitAI

    What's up with this versions history? 2.0 - 2: the electric boogaloo? What version is what now? What's about 2.1?

    MidFR
    Author
    Jan 24, 2024

    Wasn't happy with the Ex versions so I renamed them. Current 2.0 is actually an upgrade on 1.0 I think.

    MalessarJan 24, 2024

    @MidFR 1.3 seems a bit more responsive still... just my initial feedback, limited testing so far, but 1.3 seemed better with faces

    Ses_AIJan 26, 2024· 1 reaction

    @MidFR well, the latest version is pretty bleak. previous 2.0 (curent 1.3???) is beter imo. btw whats up with dpo version?

    MalessarJan 26, 2024

    @Cera_Ralaz concur, previous version is better ...

    MidFR
    Author
    Jan 27, 2024

    @Malessar personal preference I guess but I feel current version is better than 1.3. The faces look good with recommended settings.

    Ses_AIJan 27, 2024

    @MidFR tbh all faces look like a face of a blond lady in armor from preview

    MalessarJan 24, 2024
    CivitAI

    just my feedback, i think 1.3 was better with faces/loras - i posted a comparison, same prompt, same everything, just changed the version.

    MidFR
    Author
    Jan 25, 2024

    Yeah I was using ADetailer with 'V2.0 Inpainting' set as the model for faces and eyes with V2.0.

    MalessarJan 25, 2024

    @MidFR I used adetailer too...

    MidFR
    Author
    Jan 25, 2024

    @Malessar You can choose a different checkpoint for ADetailer to use under the inpainting tab in ADetailer.

    MalessarJan 25, 2024

    @MidFR ill try

    Sixth_DaWnFeb 4, 2024
    CivitAI

    coming back to this style every time :-)

    is there a possibility that you are training an SDXL version ? or could you create a SDXL Lora-Artstyle or Refiner Model ?

    MidFR
    Author
    Feb 6, 2024

    SDXL generally seemed worse when I was trying it. Maybe link some good SDXL models I can have a look.

    CathyPowersOct 6, 2024
    CivitAI

    Can't be used on site, sadly

    Checkpoint
    SD 1.5

    Details

    Downloads
    491
    Platform
    CivitAI
    Platform Status
    Available
    Created
    1/23/2024
    Updated
    4/30/2026
    Deleted
    -

    Files

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.