CivArchive
    Blowjob WAN2.2 5B - v1.0
    NSFW

    👄 Blowjob Concept LoRA (Video | WAN2.2 5B)

    Hey again!

    This is my second video LoRA, trained for blowjob-style animations using WAN2.2 5B. Like before, I used Ostris’ AI Toolkit and followed the same official tutorial. The process was simple and smooth.

    It is actualy more deepthroat then blowjob I forgot to change the trigger word.


    🔧 Training Details:

    • Model Target: WAN2.2 5B

    • Dataset: AI-generated 3-second clips (72 frames) using WAN2.1, focused on oral scenes

    • Can generate both side view and POV angles

    • Resolution: Trained at 512 this time.

    • Training Steps: 2750 total

    • Training Time: ~4 hours on an RTX 5090

    • VRAM Usage: Peaked at around 14GB

    • Workflow: Default ComfyUI video training workflow, with LoRA loader

    • Trigger Word: bl0wj0b


    💡 Notes:

    • While WAN2.2 5B isn’t as high-quality as 14B, it’s quick, lightweight, and gets the job done.

    • There's still room for better datasets and fine-tuning to enhance facial and mouth motion accuracy.


    Hope this helps others trying to make animation LoRAs!
    Feel free to test it, give feedback, or ask questions 🎬💦

    Description

    FAQ

    Comments (30)

    97BuckeyeAug 7, 2025
    CivitAI

    Does this lora only work with 5B? The details on the right side of the page says 14B.

    iPiKo
    Author
    Aug 7, 2025

    Civitai did not make a wan 5b category.

    settima_aiAug 7, 2025
    CivitAI

    if is 480p, why your videos are 1500x2500 48fps?

    Plus, if I download them (mp4) Windows cant play them. Neither Avidemux can opne them... What coded should be?

    iPiKo
    Author
    Aug 7, 2025

    this is not 480p it is wan2.2 5b the base are 768x1280

    GRIJAYAug 13, 2025

    iPiKo what 5b can do hd?

    iPiKo
    Author
    Aug 13, 2025

    GRIJAY yes wan2.2 can only do 720p it can't do lower.

    GRIJAYAug 19, 2025

    iPiKo can i run it on 12vram?

    brahianvallesAug 7, 2025· 2 reactions
    CivitAI

    Is the workflow attached? my 5b results were never good i wonder how you did it...

    BabaMeAug 7, 2025
    CivitAI

    Can this work with the 14B model?

    iPiKo
    Author
    Aug 8, 2025· 1 reaction

    No

    TurboCoomerAug 8, 2025
    CivitAI

    model is good but tends to create long fake eyelashes :/

    iPiKo
    Author
    Aug 8, 2025

    It was trained on generated wan2.1 videos with cosplay

    TurboCoomerAug 10, 2025

    iPiKo yeah so it kinda needs to blur faces where possible to prevent lora affecting generations this way

    Rapidfire_sukAug 9, 2025
    CivitAI

    So what are the advantages and disadvantages of using the 5B model vs the 14B models?

    iPiKo
    Author
    Aug 9, 2025· 2 reactions

    Easier to train and faster inference speed without any hacks.
    The quality of the video I think it is not bad I still need to try the fp32 version to see.
    It is bad at prompting and doing what you tell him to do, it also do not have a level of understanding of animation like 14B do but with LoRA this is not a problem.

    TheDadNov 25, 2025

    It's "okay". I guess it's useful for people with low (8GB) VRAM; but even then, quantized 14B models would probably be better. If you have the VRAM, use 14B models every time.

    settima_aiAug 10, 2025
    CivitAI

    I'm trying to use your LORA with WAN 2.2 5B 720p on WaveSpeed (a online service) but no movement at all. Is like the LORA did nothing. I tried weight at level 1 and 2, nothing... the strange fact is others LORA works, even LORA for WAN 2.1... I cant understand... are you sure the prompt is simply bl0wj0b, like in your examples, and the LORA will do the job?

    iPiKo
    Author
    Aug 10, 2025

    The prompt is not only bl0wj0b I think you don't even need it, you need to describe the scene download the video and drop it into comfyui to see the prompt.

    settima_aiAug 12, 2025

    iPiKo Hello, meanwhile I noticed there is a (new?) category on Civit AI. Is named WAN 2.2 ti2v 5B. "TI" I presume should include both "t2v" and "i2v." May be is better describing your LORA?

    iPiKo
    Author
    Aug 12, 2025

    settima_ai all my lora are i2v

    settima_aiAug 13, 2025

    iPiKo Perfect now! Thanks! : )

    Amicia420Aug 15, 2025

    iPiKo Dragging mp4 files into comfy doesn't work to show the workflow, never works for me. Only webm files do.

    gonfinal12Aug 11, 2025· 1 reaction
    CivitAI

    epic cool

    dx505050Aug 12, 2025· 1 reaction
    CivitAI

    Using Wangp, but i put the lora in, set it to 1.0 but nothing happens, is there another lora needed nsfw?

    iPiKo
    Author
    Aug 12, 2025· 1 reaction

    Not sure I never used wangp but you need a picture to generate.

    dx505050Aug 12, 2025

    iPiKo OK. Got it, doesnt need the start image to contain everythig to work. it works now.

    serzhyale919Sep 5, 2025

    I need .lset file as well to use this .safetensors in wangp. Any suggestions?

    TheNoobUserOct 5, 2025
    CivitAI

    weird face after gen, the character when wrong but the movement is ok, hope you fix the lora soon

    WhatTheGuyOct 16, 2025
    CivitAI

    hey! which software are you using for finetuning? Somehow I can't find anything about the 5B finetunung ....

    iPiKo
    Author
    Oct 16, 2025

    I did no finetunning I have linked the tool and tutorial for the training.