CivArchive
    7th anime XL A - v1.0
    NSFW
    Preview 9318765
    Preview 9321960
    Preview 9321336
    Preview 9322552
    • Conducted highly complex model merging and additional training.

    • Adjusted to recent artistic styles.

    • Reduced anatomical inconsistencies.

    • Enhanced resilience to additional training and LoRA.


    <lyco:Important Notice:1.37>

    default CFG Scale : 7

    default Sampler : DPM++ 2M Karras

    default Steps : 20

    Negative prompt : (worst quality:1.6),(low quality:1.4),(normal quality:1.2),lowres,jpeg artifacts,long neck,long body,bad anatomy,bad hands,text,error,missing fingers,extra digit,fewer digits,cropped,signature,watermark,username,artist name,

    <Marge: The Recipe :0.7>

    1. Merge Animagine 3.0 and 3.1 using a base alpha of 0.49, and merge layers from IN00 to OUT11 at 0.82.

    2. Train a model on sd_xl_base_1.0_0.9vae.safetensors with ~4.6 million images on A100x4, at a learning rate of 1e-5, for ~2 epochs, and then, for compatibility with Animagine models' CLIP modules, further train it with a dataset of 164 AI-generated images to refine CLIP and Unet, using PRODIGY, Initial D at 1e-06, D Coefficient at 0.9, and a batch size of 4 for 1500 steps.

    3. Merge 1. and 2. using two sets of coefficients:

      • Set 1: 0.2, 0.6, 0.8, 0.9, 0.0, 0.8, 0.4, 1.0, 0.7, 0.9, 0.3, 0.1, 0.1, 0.5, 0.6, 0.0, 1.0, 0.6, 0.5, 0.5

      • Set 2: 0.9, 0.8, 0.6, 0.3, 0.9, 0.1, 0.4, 0.7, 0.4, 0.6, 0.2, 0.3, 0.0, 0.8, 0.3, 0.7, 0.7, 0.8, 0.2, 0.3.

    4. Merge Set 1 and Set 2 using a base alpha of 0.79 and merge layers from IN00 to OUT11 at 0.73 to create Set 3.

    5. Train a LoRA based on Set 3 with a curated dataset of 12,018 AI-generated images, Lion optimizer, batch size of 4, gradient accumulation steps of 16, and learning rate 3e-5 for 4 epochs. This model is then blended into Set 3 itself at a strength of 0.2, resulting in the creation of 7th anime B.

    6. Train another LoRA based on 7th anime B with the same dataset as described in step 2. but with Lion optimizer, batch size of 4, lr_scheduler_num_cycles at 5, and learning rate 1e-5 for 80 epochs. This model is then blended into 7th anime B itself at a strength of 0.366, finally resulting in the creation of 7th anime A.

    Description

    FAQ

    Comments (10)

    ZarannaApr 7, 2024· 3 reactions
    CivitAI

    What is the difference between your A and B?

    syaimu
    Author
    Apr 7, 2024· 2 reactions

    B=Diversity

    syaimu
    Author
    Apr 7, 2024· 7 reactions
    einar_rainhartApr 7, 2024
    CivitAI

    Same question as the B model. Does this model have a license, unlike the SD 7th Anime series?

    syaimu
    Author
    Apr 7, 2024

    =animagine

    einar_rainhartApr 7, 2024· 1 reaction

    @syaimu Thanks.

    Disty0Apr 7, 2024

    @syaimu So what was the change from AnimagineXL?

    Fair AI License requires publicizing what you did to the model and how you did it in detail.
    (Like the merge ratios, training parameters, dataset format etc.)

    Currently you didn't share anything that passes this as far as i know.

    More info on this:
    https://huggingface.co/cagliostrolab/animagine-xl-3.1/discussions/1

    syaimu
    Author
    Apr 7, 2024· 1 reaction

    @Disty0 added and amended.ty

    einar_rainhartApr 7, 2024· 2 reactions

    @syaimu Thanks a bunch for doing this.

    itachiiiApr 12, 2024· 2 reactions
    CivitAI

    https://i.imgur.com/4nxtsok.jpeg

    can you please share the prompt & settings i really try to generate more images like this please

    Checkpoint
    SDXL 1.0

    Details

    Downloads
    7,126
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/7/2024
    Updated
    5/26/2026
    Deleted
    -

    Available On (2 platforms)

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