CivArchive
    DaSiWa - Anima - Luminous Labyrinth v1
    NSFW
    Preview 130878521
    Preview 130881964
    Preview 130881992
    Preview 130882777
    Preview 130882785
    Preview 130884931
    Preview 130923232

    DaSiWa - Anima

    Refer to the official Anima page for recommended parameters and documentation.

    🖤 Why I Made This

    Anima was hard to tame for me, so I wanted as always have a starting point for:

    • 🔥 Easy usage

    • ☄️ Less prompting hassle

    • 🌟 Enhanced Quality

    • 👘 Better understanding style composition

    🍒Workflow

    My optimized workflow.

    🍄LoRA's

    But: This checkpoint is not meant to replace all LoRAs, it is meant to:

    • Perform better overall at his own

    • As easy as possible to use

    • With LoRAs to be more awesome

    ⚠️ Read the corresponding announcements.

    📢 Make sure to check it out for in-depth information and a complex comparison!

    • CFG 4-6

    • Euler/linear_quadratic | er_sde/simple

    • 40-50 Steps

    Dependencies

    VAE and Text Encoder (CLIP) as separate files.

    Closing words

    🤩 I want to thank all the fantastic other creators who made super nice LoRAs and concepts to play with! Support that awesome creators by using their LoRAs and post to their gallery and share the meta-data!
    ⚠️ I made all this with permissions or open-source resources (the time it is incorporated).

    I share as much insights as I can without compromising my work. I'm doing this for fun as my hobby and just do not want my hobby to be destroyed.

    More details can be obtained in the corresponding announcements!

    If you are into SLIME GIRLS check out SLIMA from @DustyDrab !💙

    If you would like to contribute in my awesome (😉) checkpoint or willing to share resources I'll gladly give credit! Just contact me!

    ✅ All credits / resources are mentioned inside the announcements! - Since different versions may have different resources.

    YOU are responsible for outputs as always! If you make ToS violating content and I get aware I WILL report this.

    Disclaimer

    This models are shared without warranties and with the condition that it is used in a lawful and responsible way. I do not support or take responsibility for illegal, harmful, or harassing uses. By downloading or using it, you accept that you are solely responsible for how it is used.

    FAQ

    Comments (24)

    PopcornMavenMay 16, 2026· 4 reactions
    CivitAI

    I haven’t tried Anima yet. Gonna have to give it a go.

    darksidewalkerMay 16, 2026

    I wish you a lot of fun! I'm still testing things myself :)

    LolTurdFergusonMay 16, 2026· 2 reactions
    CivitAI

    Perfect timing! Can't wait to try it out. <3

    darksidewalkerMay 16, 2026· 2 reactions

    Have a try and have fun!

    MikeflowerMay 16, 2026· 1 reaction
    CivitAI

    Great work as always👍🏻

    darksidewalkerMay 16, 2026· 2 reactions

    Thank you!

    LunaUmbraMay 16, 2026· 2 reactions
    CivitAI

    It's really good! I've only tried it a little so far, but the quality consistency and prompt accuracy already look really solid.

    DaisukethestarMay 16, 2026
    CivitAI

    1.0 is out. Will you make a new version soon?

    Darksidewalker
    Author
    May 16, 2026· 9 reactions

    This is 1.0 based

    DaisukethestarMay 16, 2026

    @darksidewalker you are goated. Comparisson between the original BF16 vs your quants soon? what about your own flavor of the turbo lora?

    Darksidewalker
    Author
    May 23, 2026

    This is BF16, just a type from me, because I released so much XD
    As for turbo, why not just add the normal turbo lora, I do not quite get the sense behind a styled turbo lora when the checkpoint is already styled.
    A turbo checkpoint would make sense, since faster/less vram compared to adding the lora.

    is there any reason for a styled turbo lora?

    captainugm244May 17, 2026· 2 reactions
    CivitAI

    That's excellent work.

    It's great to have more options.

    ElGordoAIMay 17, 2026· 2 reactions
    CivitAI

    yooooooo

    KeMiliUsMay 17, 2026
    CivitAI

    Get next error when tried starting lora training: File "/content/Anima-Standalone-Trainer/library/anima_models.py", line 1721, in get_dit_config dit_config["in_channels"] = (state_dict['{}x_embedder.proj.1.weight'.format(key_prefix)].shape[1] // 4) - int(concat_padding_mask) ~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ KeyError: 'x_embedder.proj.1.weight'

    KeMiliUsMay 17, 2026

    Anima Base checkpoint loading for training without any problems, it a mix checkpoint?

    darksidewalkerMay 17, 2026· 1 reaction

    @KeMiliUs it is a merge from anima base 1.0 and some loras plus extractions. I did not normalize the Loras, maybe that's why. But I don't know for sure

    23423daMay 17, 2026· 1 reaction
    CivitAI

    This is far superior to Nova Anima and even better than Anima 1.0.

    darksidewalkerMay 17, 2026

    Thank you! Glad to hear that!

    _Kapot_May 17, 2026· 1 reaction
    CivitAI

    Nice to see you making Anima stuff too!
    Thanks for sharing!

    darksidewalkerMay 17, 2026· 1 reaction

    Will possibly not be the last :)

    FirstPrinciplesMay 25, 2026· 1 reaction
    CivitAI

    Pretty good for no loras whatsoever, a little action/clothing drift but that can probably be cleaned up in prompting. really good for a 3 character scene without any regional prompting!

    jianshanssdMay 27, 2026
    CivitAI

    Common Anima models are usually placed in the diffusion_models path. Why is yours in the checkpoints path? This conflicts with many workflow model loaders.

    Darksidewalker
    Author
    May 27, 2026

    No special reason

    phatestronaughtMay 28, 2026· 3 reactions
    CivitAI

    A great resource. I am obsessed with it.

    Highly recommend!

    Checkpoint
    Anima
    by Darksidewalker
    Download (Beta) View on CivitAI
    anima
    base model
    dasiwa

    Details

    Downloads
    1,730
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/16/2026
    Updated
    7/2/2026
    Deleted
    -

    Files

    qwen_image_vae.safetensors

    Size:
    242.05 MB
    SHA256:
    a70580f0213e67967ee9c95f05bb400e8fb08307e017a924bf3441223e023d1f

    Mirrors

    HuggingFace (157 mirrors)
    CivitAI (78 mirrors)
    TensorFiles (1 mirrors)
    ModelScope (1 mirrors)
    ModelScope CN (5 mirrors)

    dasiwaAnima_luminousLabyrinthV1.safetensors

    Size:
    3.90 GB
    SHA256:
    5b950cdc835869c5adb4b701a5f438e9ed4fe7225a8bd4f720b0cbb9ea75d24f

    Mirrors

    HuggingFace (2 mirrors)
    CivitAI (1 mirrors)

    dasiwaAnima_luminousLabyrinthV1_txt.safetensors

    Size:
    1.11 GB
    SHA256:
    cd2a512003e2f9f3cd3c32a9c3573f820bb28c940f73c57b1ddaa983d9223eba

    Mirrors

    HuggingFace (72 mirrors)
    CivitAI (73 mirrors)
    ModelScope CN (2 mirrors)