CivArchive
    Preview 11883782
    Preview 11364166
    Preview 11364221

    This model is focused on improving the details in faces, skin, clothing, fur, and materials. It performs well in both txt2img and img2img/upscaling workflows.

    Flux Model v2 - Weak vs. Strong:

    The weak version is more flexible, allowing for a wide range of outputs.

    The strong version enhances details more dramatically but has a higher risk of inconsistencies.

    Both versions have their pros and cons. The strong model can really make details stand out, while the weak version offers more control and stability across different styles.

    Recommended Settings:

    CFG: 2.0 - 2.5

    Steps: 20 - 30

    SDXL/Pony:

    Upscaling (1.5x - 2x) really brings out the fine details. I’ve personally had great results with full strength, but anything from 0.3 to 1 with 30 to 60 steps can make a noticeable difference.

    Recommended Settings:

    CFG: 2.0 - 7.0

    Steps: 30 - 60

    As a heads-up, most of the provided images (except for upscaled ones) were generated through txt2img without any editing, so there may be a few minor issues visible here and there.

    Description

    FAQ

    Comments (6)

    OzzyOsmanMay 2, 2024· 7 reactions
    CivitAI

    Looks good. Can you share any info on this LORA? Which Checkpoint do you recommend? EverClearPNY? What weight works best?

    zwaetschge
    Author
    May 2, 2024· 4 reactions

    tested with everclear too and works better than on original pony imo. overall its pretty flexible with different pony checkpoints. i tested between 0,6 and 1 with 30-60 steps, while for t2i id go with 1 and 30 steps, its a bit more try and error with i2i

    nikolaibloom805May 26, 2024

    @zwaetschge are your prompts or workflow in the images you attached would love a good starting point to get faces like that

    zwaetschge
    Author
    May 27, 2024

    @nikolaibloom805 easiest is to just use my fooocus styles: https://civitai.com/articles/5367/fooocus-detail-styles

    I didn't notice, I had to turn it on manually. so only newer will have prompts with it sorry. but really my main prompt is rather small and I let my fooocus styles do the work

    Bango_BangholoJun 9, 2024

    @zwaetschge 
    How to use the workflow with fooocus?

    zwaetschge
    Author
    Jun 10, 2024· 1 reaction

    @Bango_Bangholo download the txt file and drop it in the folder "sdxl styles" in your fooocus rootfolder. Restart fooocus and then search for "plum" and you should see my styles

    LORA
    Pony

    Details

    Downloads
    428
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/2/2024
    Updated
    5/13/2026
    Deleted
    -

    Files

    detailedfacesconcept_PONY_v2.safetensors