CivArchive
    Hotaru Blend Anima - v4.0
    NSFW
    Preview 131460489
    Preview 131460485
    Preview 131460473
    Preview 131460482
    Preview 131460484

    Hotaru Blend Anima is a model based on the latest Version base-v1.0 of the new Anima model since V3.0. Previous builds based on Preview 3.

    It offers a clean Anime style and supports prompting in booru tags and natural language.


    You need to download additional text encoder and VAE to use this model:

    Text encoder: https://huggingface.co/circlestone-labs/Anima/blob/main/split_files/text_encoders/qwen_3_06b_base.safetensors

    VAE: https://huggingface.co/circlestone-labs/Anima/blob/main/split_files/vae/qwen_image_vae.safetensors

    Recommended Settings:

    • Sampler / Scheduler: Euler A or ER SDE with Simple or Beta

    • Sampling steps: 20-35

    • CFG Scale: 3-5

    • Shift: 3-4.5

    • Recommended resolution: 1024px based

    • Model tested with Forge Neo

    Please refer to the official model page for detailed instructions: https://civarchive.com/models/2458426/anima-official


    For all samples, the Forge Neo Add-on "Anima Detail Enhancer" was used to improve minor details. Below settings were applied.

    I recommend using a post processing upscale instead of a usual High-res fix.

    The preview images were 4x upscaled with 4x-ClearRealityV1_Soft.

    Quality tags:

    Positive:

    masterpiece, best quality, score_9

    Negative:

    score_1, score_2, score_3, blurry, jpeg artifacts,lowres, worst quality, low quality, bad hands, bad anatomy,signature, text, watermark, censor, bar censor, mosaic censorship, mosaic censor, sound effects, blubble speech, patreon logo, patreon username, twitter username, twitter logo, blur, multiple views or similars.

    Merged models (before V3):

    Anima_chromalinemixNoobaiVPred_v10AnimaPreview3

    Anima_animaika_v30

    animaCatTower_v05

    pornmasterAnima_preview2V1

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

    Description

    Version 4 is another new merge from scratch. The previous version had problems with understanding of natural language and this should now work much better with this release.

    The preview samples were created with an alternative text encoder you can find here:

    https://huggingface.co/DavidAU/Qwen3-0.6B-heretic-abliterated-uncensored

    or here: https://civitai.red/models/2598886/anima-text-encoder-qwen3-06b-heretic-abliterated-uncensored?modelVersionId=2919360

    FAQ

    Comments (4)

    Lizardon1025May 22, 2026· 1 reaction
    CivitAI

    First of all, thank you very much for creating such amazing model merges! Your Hotaru Blend Anima v3.0 is one of my favorite Anima models at the moment :D

    So naturally, I was excited to test out your new v4.0 version. But sadly, it seems to create less detailed images with less color intensity and contrast. Maybe this is intended as v3.0 was sometimes a little bit extreme. But at the moment I think I still prefer v3.0 over v4.0. I hope your model will gain some of its contrast and details back with the next version :)

    Zessica
    Author
    May 25, 2026· 4 reactions

    I will check if I can make the colors with a bit more contrast and details for the next version. V3 was a bit too intense and I wanted it to be a bit less. But maybe a bit too less🤔

    AndyLomJun 1, 2026

    Same here, V3 it's a best model nowadays. I want to see continue for this like v3.1 :D or something like that

    Lizardon1025Jun 11, 2026· 2 reactions

    v5.0 is amazing, thank you for that! It has all the contrast and details back from v3.0 with increased aesthetics and better prompt adherence :)

    Checkpoint
    Anima

    Details

    Downloads
    687
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/22/2026
    Updated
    8/25/2026
    Deleted
    -

    Files

    hotaruBlendAnima_v40.safetensors

    Mirrors