CivArchive
    tongue out_V2_wan22_5b - v1.0 /natural_soft)
    NSFW

    V2

    This is a complete revision of the original dataset, now composed entirely of custom-made material created specifically for this Lora, using real, live models (with very little synthetic material, less than 10%).

    In this regard, the first thing to do is to give credit to those models who chose to participate, for their time and creativity, which they generously contributed, for a fee, to make this LoRa dataset a reality:

    Alejandra @andromedastrid https://es.fiverr.com/andromedastrid

    Angybel M @angybelmonteneg https://es.fiverr.com/angybelmonteneg

    Geor Hernandez @geor97 https://es.fiverr.com/geor97

    Valeria Perez @valeriap21 https://es.fiverr.com/valeriap21

    Whitney M @fabflop https://es.fiverr.com/fabflop

    And so many other models, without whose participation this wouldn't have been possible. Thank you!

    Beyond this, some technical aspects:

    In short: it produces a more natural, less powerful effect, and groups are a bit more difficult to work with.

    We have extra smiles, better teeth, and maybe even better eyes, like a positive bleed.

    This V2 version also offers more variety in different body types (the 'supermodel' effect is controlled) and generally provides a greater degree of realism. It's also better at working with men, I don't know why, and, yes, let's talk about things that could be improved: 

    There's a certain Caribbean bleed and, above all, an excess of tanning in the skin. Also, there's some awkward hand movements that sometimes occur, which didn't happen before. Beyond that, the drawing and anime capabilities have been reduced.

    But hey, nothing that can't be fixed for a V3!

    Have fun! (And if you want to check out these 21st-century-minded models' Fiverr profiles, even better!)

    ———

    Esta es una revision completa del dataset original, con la novedad de que ahora mismo está íntegramente compuesto con material personalizado creado a medida para este lora trabajando con el arte de modelos reales, de carne y hueso, (con muy poco material sintético, menos del 10%).

    En este sentido lo primero es dar crédito a aquellas modelos, que así lo han decidido, por su tiempo y por la creatividad que han cedido, de manera remunerada, para que el dataset de este LoRa sea realidad:

    Alejandra @andromedastrid https://es.fiverr.com/andromedastrid

    Angybel M @angybelmonteneg https://es.fiverr.com/angybelmonteneg

    Geor Hernandez @geor97 https://es.fiverr.com/geor97

    Valeria Perez @valeriap21 https://es.fiverr.com/valeriap21

    Whitney M @fabflop https://es.fiverr.com/fabflop

    Y otras tantas modelos, que sin su participación esto no podría haber sido posible, ¡Gracias!

    Más allá de esto, cuestiones técnicas:

    En una línea: da un efecto más natural, menos potente y le cuestan un poco más los grupos.

    Tenemos un extra de sonrisas, mejores dientes y quizá mejores ojos como un sangrado positivo.

    Luego también esta versión V2 ofrece más variabilidad de diferentes tipos de cuerpos (se controla el efecto ‘super modelo’) y en general aporta un grado de realismo mayor. También es capaz de trabajar mejor con hombres, no sé por qué, y, eso sí, vamos con las cosas a mejorar:

    Se sangra cierto estilo caribeño y, sobre todo, un exceso de moreno en la piel. Y por otro lado hay cierto juego de manos feas que ocurre a veces y antes no ocurría. Más allá de esto, las capacidades con dibujo y anime han quedado reducidas.

    Pero bueno, ¡nada que no se pueda intentar arreglar para una V3!

    ¡A pasarlo bien! (Y si queréis pasaros por el Fiverr de estas modelos con visión para el siglo XXI, mejor que mejor!)

    V1

    A friend challenged me to make a LoRa of Wan 2.2 5B, without me having ever done one, in less than 24 hours. I raised the bet that I would have it in less than 12. The result?

    I present to you my first LoRa, absolutely experimental xD

    And, as the name suggests, it will get the subject of your image tongue out in a mocking way. Have a good time!


    Un amigo me retó a hacer un LoRa de Wan 2.2 5B, sin yo haber hecho nunca uno en menos de 24h. Yo subí la apuesta a que lo tendría en menos de 12. ¿El resultado?

    Os presento mi primer LoRa, absolutamente experimental xD

    Y, como el nombre indica, conseguirá que el sujeto de vuestra imagen saque la lengua de manera burlona. ¡A pasarlo bien!

    Description

    Original version (The one that gives more natural results at the cost of sometimes failing).

    -

    Versión original (la que da resultados más naturales a costa de a veces fallar).

    FAQ

    Comments (11)

    JoseGomezFreelance
    Author
    Sep 8, 2025· 3 reactions
    CivitAI

    By the way, it almost took me longer to upload it to Civitai than to do it xD

    --

    Por cierto, casi tardo más en subirlo a Civitai que en hacerlo xD

    mcantiSep 8, 2025

    Where did you get the dataset for this? :)

    JoseGomezFreelance
    Author
    Sep 8, 2025

    @mcanti It is totally handmade. I believe it by hand, with my own hands, what I could extrapolate from what I know of generation and... against the clock!

    TempSep 8, 2025· 2 reactions
    CivitAI

    Can we get a 2.1 or 2.2 versions? 5b is fun and all, but not that usable as big variants. Also 5b's vae really hitting that model usability.

    JoseGomezFreelance
    Author
    Sep 8, 2025· 1 reaction

    Now, he has remained like the cub lagging behind... But it's so fast and efficient! Be that as it may, I just started with this training thing, so if you want there to be more and more models, continue support me and I will be one step closer to continuing with this adventure of the LoRas :)

    chicken99erSep 15, 2025· 6 reactions
    CivitAI

    I like it, but please make it for wan 2.2

    JoseGomezFreelance
    Author
    Sep 15, 2025

    If it's already in Wan 2.2 xD

    chicken99erOct 1, 2025

    @JoseGomezFreelance  sorry! I meant the larger I2V or T2V models

    JoseGomezFreelance
    Author
    Oct 1, 2025

    @chicken99er With how small and versatile 5B is!

    JellaiNov 13, 2025· 1 reaction

    @JoseGomezFreelance 5B is small and good, but it's not as versatile or as detailed in both texture and motion as 14B. Still, I get wanting to stick with 5B. It's a bigger pain in the ass to train for 14B, and people who can only run 5B need some attention.

    JoseGomezFreelance
    Author
    Nov 13, 2025· 1 reaction

    @Jellai I won't change a single thing! (And it's great for practicing too. When I've got everything sorted out, I might move on to 14B, but not today or tomorrow xD)

    LORA
    Wan Video 2.2 TI2V-5B

    Details

    Downloads
    327
    Platform
    CivitAI
    Platform Status
    Available
    Created
    9/8/2025
    Updated
    5/13/2026
    Deleted
    -
    Trigger Words:
    tongue out

    Files

    tongue out_V1_wan22_5b_natural_soft.safetensors

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.