CivArchive
    Magick XL - v1.0
    Preview 43545667Preview 43545713Preview 43545721Preview 43545988Preview 43546025Preview 43546049Preview 43546091Preview 43546123Preview 43546133

    This is the model I intended to create when I made Elsewhere XL. Although Magick XL can also be used as a general purpose model, a medieval castle may randomly popup in the background - as it did in one of the sample images. 🏰🙂

    Magick XL is merged from SDXL FaeTastic 2.4 (80%) and animaPencilXL 5.0 (20%) together with the SDXL Offset Example (0.5) and Better Blur Control (1.0) LoRAs.

    Each of these source models and LoRAs represent an enormous amount of dedicated hours and inspired problem solving, shared freely here at CivitAI. Please respect the licenses of each of these creators. For example, do not use Magick XL on any service that monetizes image creation, such as for online image generation. Also, do not sell or license this model for a fee or something else of value.

    Usage:

    My preferences for Magick XL are a CFG of 6, but going down to 4.5 for soft focus and up to 12 for special effects. I set sampling steps to 30 and use the default Fooocus sampler, dpmpp_2m_sde_gpu karras.

    Put "sharp background" in the positive prompt and "blurry background" in the negative prompt to increase the depth of field. "Bokeh" or "blurry background" in the positive prompt creates a shallow depth of field.

    If this model creates NSFW images it is not intentional.

    Credits:

    SDXL FaeTastic 2.4: https://civarchive.com/models/129681

    animaPencilXL 5.0: https://civarchive.com/models/261336/animapencil-xl

    Better Blur Control LoRA: https://civarchive.com/models/324815/better-blur-control-less-depth-of-field-xl-lora

    SDXL Offset Example LoRA: https://civarchive.com/models/137511/sdxl-offset-example-lora

    The merges involved in this project were all created with the RuinedFooocus MergeMaker, a simple but effective tool:
    https://github.com/runew0lf/RuinedFooocus/wiki/Checkpoint-merges

    The featured images are samples from the ten standard tests applied to this particular model at the Pure Fooocus Base Model Reviews Guide:
    https://www.facebook.com/groups/fooocus/learning_content/?filter=519238867322550&post=753347100153801
    (Facebook links are notoriously unreliable, you may need to scroll up or down to access this particular guide)

    Description

    Checkpoint
    SDXL 1.0

    Details

    Downloads
    208
    Platform
    CivitAI
    Platform Status
    Available
    Created
    12/3/2024
    Updated
    9/27/2025
    Deleted
    -

    Files

    magickXL_v10.safetensors

    Mirrors

    Huggingface (1 mirrors)
    CivitAI (1 mirrors)