CivArchive
    r1zen Style T-LoRA for Anima - v2.0
    Preview 1

    The art style of r1zen is a highly polished, modern anime illustration style that blends cinematic lighting with sharp, intricate character designs.

    Trained on Anima Base v1 using a carefully pruned dataset of 71 images with a combination of tags and natural-language captions. Trigger word: @r1zen.

    Recommended settings:

    • 30-40 steps

    • 4-5 cfg

    • euler + beta57 or er_sde + simple . The beta57 scheduler is better at bringing out the style's soft, painterly texture, but can cause melted hands and other anatomical issues.

    • āŒ euler_ancestral + beta57 will fry your gens. In fact, I ran into all kinds of artifacts with Euler A and other schedulers as well.

    Recommended resources:

    • RES4LYF for the beta57 scheduler. Or just search "RES4LYF" in ComfyUI Manager.

    • ComfyUI-Spectrum-KSampler: training-free Anima acceleration. Shaves a solid 10 seconds off my inference time.

    • The 01.09.2025 version of Danbooru/e621 autocomplete tag lists. Anima's knowledge cut-off date is September 2025, so this is the best version for Anima even though it's labeled as "ChenkinNoob 01".

    Known issues:

    • Has a tendency to generate torn paper-like edges (see Showcase 2). I haven't found a reliable negative prompt to counter that. Try inset border, torn paper effect, etc.

    Description

    Initial release

    LORA
    Anima

    Details

    Downloads
    0
    Platform
    SeaArt
    Platform Status
    Available
    Created
    7/3/2026
    Updated
    7/3/2026
    Deleted
    -
    Trigger Words:
    @r1zen

    Files

    Available On (1 platform)

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