CivArchive
    Sakuramochi Blend - Anima v1.0
    NSFW
    Preview 147214419
    Preview 147214426
    Preview 147214438
    Preview 147214450

    This checkpoint is primarly made for testing anime themed loras of all kinds. It has a clean default art stlye, but is still very flexibel and has a good compatibility with all kinds of 2D styles.

    Recommended Settings for Anima:

    Sampler / Scheduler: Euler A or ER SDE with Normal scheduler

    Sampling steps: 20-35

    CFG Scale: 3.5 - 5.0 (higher CFG can produce better results with some styling loras)

    Shift: 3-4.5

    Recommended resolution: 1024px based or higher

    Model tested with Forge Neo

    Recommended settings for illustrious:
    Sampler/Scheduler: Euler A + SGM Uniform
    CFG: 4-6
    Steps: 25-35
    Optional: Highres Fix and Adetailer

    Quality tags for Anima:

    Positive

    masterpiece, best quality, highres

    Negative

    score_1, score_2, score_3, blurry, jpeg artifacts,lowres, worst quality, low quality, bad hands, bad anatomy,signature, text, watermark, (censor, censored, bar censor, mosaic censorship, mosaic censor:2.0), sound effects, blubble speech, patreon logo, patreon username, twitter username, twitter logo, blur


    Quality tags for illustrious:
    You can use my Quality Embeddings for Anime models.

    or folliowing tags:

    Positive

     masterpiece, best quality, newest, absurdres, highres, very aesthetic

    Negative

    worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands, mammal, anthro, furry, ambiguous form, feral, semi-anthro, censored, bar censor, mosaic censoring, watermark

    Merged models:

    https://civarchive.com/models/2904237/wai-simple-illustrious

    https://civarchive.com/models/2167995/chenkin-noob-xl-ckxl?modelVersionId=2841101

    https://civarchive.com/models/827184/wai-illustrious-sdxl?modelVersionId=2883731

    Permission: no commercial use, no selling, use only on Civitai (please also check the sources for their respective permissions)

    Description

    Anima version of this model.

    It follows the same goal as the IL Version, beeing primarly made for lora testing. But it also works very well without loras.

    Recommended Settings:

    Sampler / Scheduler: Euler A or ER SDE with Normal scheduler

    Sampling steps: 20-35

    CFG Scale: 3.5 - 5.0 (higher CFG can produce better results with some styling loras)

    Shift: 3-4.5

    Recommended resolution: 1024px based or higher

    Model tested with Forge Neo

    FAQ

    Checkpoint
    Anima

    Details

    Downloads
    174
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/29/2026
    Updated
    11/1/2026
    Deleted
    -

    Files

    sakuramochiBlend_animaV10.safetensors

    Mirrors