CivArchive
    FASCIUM KREA2 - 3
    NSFW
    Preview 135611874
    Preview 135610367
    Preview 135612108
    Preview 135610830
    Preview 135611668
    Preview 135611611
    Preview 135610982
    Preview 135611938
    Preview 135611084
    Preview 135612437
    Preview 135611162
    Preview 135612572
    Preview 135611258
    Preview 135612929
    Preview 135611335
    Preview 135613031
    Preview 135611381
    Preview 135613240
    Preview 135611467

    EARLY TEST

    Description

    more trained

    FAQ

    Comments (13)

    JohnLockeJul 3, 2026
    CivitAI

    Any chance to see конврот version?

    FASCIUM
    Author
    Jul 3, 2026

    ?

    JohnLockeJul 3, 2026

    @FASCIUM Имею в виду Новый формат сжатия моделей INT8 ConvRot на примере Krea 2 https://youtu.be/4MMuTYbcE08?si=F5tLij_HeA67vVnF

    FASCIUM
    Author
    Jul 3, 2026· 1 reaction

    Вряд ли, я генерирую только в Forge, там эти фичи пока не сделаны. Опять же конечный мердж делаю через чистый скрипт, аналогичная ситуация.

    JohnLockeJul 3, 2026

    @FASCIUM но тема офигенная, экономит время

    civit77899Jul 3, 2026
    CivitAI

    An interesting merge. Can you possibly do a semi-raw/semi-turbo version? It generally works like this: the base version is RAW, plus Turbo LoRA at 0.6 weight, plus whatever other loras/embeddings you do on top of that.

    Why: because this way it gets MUCH more creative compared to pure Turbo! Like, night and day difference. You still use it at CFG=1, but the number of steps should be 12-14 (up from 8 for pure Turbo). In my opinion, the tradeoff is more than worth it!

    FASCIUM
    Author
    Jul 3, 2026

    I’ve tried RAW, but to be honest, it didn’t really impress me. As I understand it, RAW is good for training but not so much for generation. Then again, working with models is just a hobby for me; once I’m satisfied with the result, I don’t change the models. My business interests lie in a completely different field and take up a lot of time, so I only engage in creative work when I have spare time.

    civit77899Jul 3, 2026

    @FASCIUM I was not meaning the RAW raw; I meant the raw checkpoint with the Turbo lora injected at 0.6 weight (at the time of doing the merge). This is currently the best approach for maximum diversity.

    IggortusJul 3, 2026
    CivitAI

    Стандартная модель все таки не очень выводит длинные тексты на кириллице. Если еще и с разными регистрами. Судя по вашим примерам - вы как то поправили в своем слиянии? ERNIE, на сколько помню лучше всего спрвляется.

    olternautJul 3, 2026
    CivitAI

    I would like to see more ethnic capability trained into Krea 2. It seems to be blank canvas with a lot of capability. But if you wanted to make a Tamil Indian or other complex genotype my go to is still z-image-turbo.

    gadenblw666112Jul 4, 2026
    CivitAI

    В целом неплохо. Лица дествительно как с плакатов эпохи застоя, но уж больно не реалистично. Хотелось бы немного меньше пластика

    FASCIUM
    Author
    Jul 4, 2026

    Для реализма базовая модель вполне достаточна

    q7283wJul 4, 2026
    CivitAI

    Love this checkpoint, but unsure about v3. While it improves in some areas, the facial expressions are often weirdly theatrical and over the top compared to v2. Still best checkpoint for Krea atm. Thanks!

    Checkpoint
    Krea 2

    Details

    Downloads
    278
    Platform
    CivitAI
    Platform Status
    Available
    Created
    7/3/2026
    Updated
    7/6/2026
    Deleted
    -

    Files

    fasciumKREA2_3.safetensors

    Mirrors

    CivitAI (1 mirrors)