CivArchive
    X3D style (Anima) V2 Update! - Anima prev3 version
    NSFW
    Preview 130210541
    Preview 130210535
    Preview 130210848
    Preview 130210581
    Preview 130210587
    Preview 130210582
    Preview 130210588
    Preview 130210589
    Preview 130210590
    Preview 130210596
    Preview 130210595
    Preview 130210607
    Preview 130210608
    Preview 130210610
    Preview 130210865

    X3D STYLE LORA is on Anima now!

    V2 (LOKR) 19.11.2026 update!

    • +150~ new pics

    • new characters

    • betters style (lokr method)

    Main tags:

    @x3d

    plump, huge breasts, shiny skin, curvy, large breasts,

    optional:

    forehead wrinkles (special concept tag of this lora).

    red lips, thick lips, puckered lips,

    wet, sweat

    stray hair, messy hair

    sidelighting, backlighting

    Known characters:

    Tifa Lockhart, brown eyes, black hair, long hair, low-tied long hair, swept bangs, black thighhighs, skindentation, ankle boots, red footwear, white tank top, crop top, bare shoulders, black shorts, belt, short shorts, fingerless gloves, elbow gloves;

    Honoka \(DOA\), 1girl, brown eyes, pink hair, hair ornament, one side up, side ponytail, thick lips, red lips, freckles, hooters uniform, white tank top, orange shorts, short shorts,

    Black Widow, 1girl, blue eyes, red hair, short hair, hair pulled back, ponytail, (or long hair, straight hair) mole under mouth, thick lips, red lips, freckles, mole on breast, black bodysuit, open bodysuit

    Black cat \(Marvel\), 1girl, blue eyes, white hair, long hair, ponytail, domino mask, black bodysuit, fur trim, fur-trimmed gloves, fur-trimmed boots, black gloves, open bodysuit, unzipped, full-length zipper, center opening

    Samus Aran, 1girl, blue eyes, blonde hair, long hair, ponytail, thick lips, red lips, makeup, hair pulled back, mole under mouth, zero suit, skin tight, bodysuit, blue bodysuit, high heels, two-tone footwear, glowing footwear, blue gloves,

    Chun-li, 1girl, black hair, brown hair, brown eyes, double bun, bun cover, hair pulled back, short hair, hair pulled back, chinese clothes, blue dress, puffy short sleeves, bracelet, white footwear, knee boots,

    Thanos, 1boy, purple skin, muscular male, gauntlet,

    Venom \(Marvel\),1boy, black skin, long tongue, sharp teeth, muscular male

    Ada Wong, mature female, brown eyes, short hair, black hair, thick lips, black choker, red dress, short dress, bare shoulders, wristwatch, thigh holster, pantyhose, brown pantyhose, high belt,

    tyrant \(resident evil\), 1boy, grey skin, muscular male, monster

    rio morales, 1girl, mature female, tan, brown eyes, short hair, black hair, single hair bun, freckles, body freckles, stud earrings, white bikini, side-tie bikini bottom,

    eve \(stellar blade\), 1girl, very long hair, black hair, ponytail, brown eyes, red lips, thick lips, neck tattoo, plump, huge breasts, dark areolae, mole on breast, stomach, thighs, pussy, covered nipples,frontless outfit, purple bodysuit, skin tight, bodysuit, high heels, see-through bodysuit

    My preview can help.

    For extra tags check my preview.

    negative prompt (or not):

    from above (if you don't like from above view on girls which are very usual in x3d images);

    bar \(place\), counter (if you don't like main bar from x3d images. Also negative these tags if they cause "from above" effect);

    SETTINGS FOR ANIMA :

    Check my article about Anima settings.

    Short guide:

    Same aesthetic settings (masterpiece, best quality, good quality, highres, absurdres, worst quality, low quality, bad quality, lowres, extra digits in negative.)

    Don't use "score_". Anima supports these tags but they make you pics AI-slop like Pony because score-based aesthetic tags can cause overcontrast.

    Generations settings:

    Fox txt2img: ER SDE + beta or ER SDE + FlowMatchEulerDiscrete / Simple;

    For highres fix: ER SDE + simple 0.3-0.5 denoising, 15 steps (if you need more changes), ER SDE + KL Optimal 0.5 denoising, 20 steps (if you need enchance small details without changing composition and medium objects) If you don't have option to choose in forge / forge neo go to settings and choose "[Hires. fix]: Show checkpoint, sampler, scheduler, and cfg options"

    CFG 3.5-4.
    Adetailer - use very high pixel padding - about 176-256 pixels instead of 32 pixels because Anima understands context much better. Denoising of adetailer - 0.25-0.3.

    If you have old adetailer - use custom resolution 1024x1024. If you use one of adetailers for forge neo - don't use custom resolution, just high paddig (~256 pixels) because on newest adetailer this option not set resolution of box but minimal resolution. Usually it causes very high res. and you don't need it.

    Description

    Anima preview v3

    FAQ

    Comments (9)

    MikeflowerMay 11, 2026· 4 reactions
    CivitAI

    😍 👍🏻

    FeverEncoreMay 11, 2026· 3 reactions
    CivitAI

    S+++ Tier LoRA as always

    culturedfanMay 14, 2026· 3 reactions
    CivitAI

    even though anima isn't meant for 3d, it works really good!

    Enigmata
    Author
    May 14, 2026· 3 reactions

    thank you :3 I also trained new version for 1.0 base (released today). I think I'll upload in few days. Feels like it is even better than preview 3.

    darkspaceinfinityMay 16, 2026

    @Enigmata Would you say anima 1.0 is better then vpred now?

    Enigmata
    Author
    May 16, 2026· 1 reaction

    @darkspaceinfinity For details and natural language - yes, because better text encoder, vae and prediction noise. For furries and monsters can be worse because as I know it wasn't trained on e621 in comparison with NoobAI.

    waifuliberatorMay 16, 2026· 1 reaction

    @Enigmata Do you think Anima will overtake Illustrious?

    IntosicaJun 20, 2026

    Anima being a DiT model, it's pretty much for anything.
    It's the other models like Pony and Illustrious which are U-Nets that struggle to adapt to anything they're trained outside of.

    GegeNodesJun 20, 2026

    @waifuliberator  It very much "could". There's chaos that follows both as of now.
    Anima has LLM based CLIP, so you can make words with it, and it understands more, but the output lacks quality and general coherence. DiT, so it's hard to intercept the model to ksampler pipeline and make manipulations to the "brain".

    Illustrious has the CLIP G setup, which certainly isn't bad, but isn't the greatest.
    A lot of the methods to make truly great things with this model have been either gatekept, convoluted/broken, hardware intensive, time consuming, or outright useless.
    I finished a node suite for Illustrious to get rid of all that, and shockingly in my usage of Anima I discovered there's some proprietary function similar to what you can already do with Illustrious.
    But the one place it will always fail, is the damn CLIP encoder.

    I find myself wanting to move to Anima totally, but when I did the same going from Pony to Illustrious, over time, I realized I should've never did that, despite it being somewhat beneficial to focus on one thing. I "focused on one (new) thing" for too long.

    LORA
    Anima

    Details

    Downloads
    651
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/9/2026
    Updated
    11/21/2026
    Deleted
    -
    Trigger Words:
    @x3d
    plump, huge breasts, shiny skin, curvy, large breasts,
    forehead wrinkles
    red lips, thick lips
    puckered lips
    wet, sweat, shiny skin
    stray hair, messy hair
    sidelighting, backlighting