CivArchive
    LTX 2.3. Frieren Anime - v1.0
    NSFW

    I ENCOURAGE YOU TO MAKE AND POST SOME VIDEOS, TRAINING THIS WAS FAR FROM FREE!

    AB TESTS 4 and 8 steps:

    Short model description

    frieren_000003000.safetensors is a rank-32 motion and native-audio LoRA for

    the LTX 2 family, tested with the LTX 2.3 22B distilled image-to-video workflow.

    It is intended to animate an already-correct first frame into restrained anime

    character performance: breathing, blinking, gaze changes, conversational

    reactions, walking, sequential dialogue, and quiet environmental movement.

    It works best when the prompt explicitly identifies every visible character, assigns every

    character a speech state, and uses Then, responds, and replies to express

    speaker order.

    This is i2v LoRA. It does not create the initial

    Frieren/Fern/Stark image and cannot repair a wrong first-frame identity. Generate

    or supply the correct guide image first, then use this LoRA for LTX motion and

    native audio.

    Ltx 2.3 dev distilled

    8 steps

    i2v

    1080p (1920*1080)

    What it is good at

    - Calm anime I2V performance from a strong first-frame guide.

    - Frieren, Fern, and Stark reacting naturally in the same shot.

    - One visible speaker while the other characters listen silently.

    - One, two or three speakers talking in an explicitly ordered sequence. Also by prompting "Fern is speaking off-screen..." you can often make it happen.

    - Native LTX ambience and speech generated with the video.

    - Subtle breathing, blinking, gaze changes, hair/cloth movement, and wind.

    Description

    initial commit

    FAQ

    Comments (8)

    TheArgonautJul 30, 2026· 2 reactions
    CivitAI

    cool! how many clips did you train and for how long the quality is crisp

    HSDHC
    Author
    Jul 30, 2026· 1 reaction

    I wouldn't say the quality is crisp haha, except the 6 talking sequences the clips are somewhat cherry-picked. This was trained with batch size 2 for 3000 steps, 5 temporal buckets, 8 resolution buckets, total 300+ clips.

    TheArgonautJul 30, 2026

    @HSDHC nice that's a lot of clips! must gave taken some time. many thanks!

    TagrimAug 4, 2026
    CivitAI

    For some reason, I can't reproduce the anime style. Instead, it generates a generic anime style with characters that only vaguely resemble the description. The strength is set to 1.0 and prompt is copied.

    HSDHC
    Author
    Aug 5, 2026

    do you use i2v (image to video)? this is an i2v model.

    TagrimAug 5, 2026

    @HSDHC got it, my fault.

    HSDHC
    Author
    Aug 5, 2026· 1 reaction

    @Tagrim you can use this model to make frames https://civitai.red/models/2835233/frieren-anime-screencap

    TagrimAug 5, 2026

    @HSDHC thanks

    LORA
    LTXV 2.3

    Details

    Downloads
    188
    Platform
    CivitAI
    Platform Status
    Available
    Created
    7/29/2026
    Updated
    8/13/2026
    Deleted
    -