CivArchive

    For on-site generation, I recommend only using models designed for WAN2.1 or earlier. It does not appear that Civitai can get 2.2 models to work. You can use the Universal model with both high and low noise steps, but if you want the best quality, I included both versions as well.

    This LoRA is trained on conversational language. You can describe your scene in plain English or Chinese, and it should adhere to your prompt well. Below are some inspirations for you if you need it.

    Positions:

    • On her back

    • Kneeling

    Perspectives:

    • POV

    Enhancement phrases:

    • She bounces her body up and down

    • She bounces her breasts up and down with her hands

    All showcase videos have the workflow metadata embedded. You can download the video and drag it into ComfyUI to replicate them with their prompts, seeds, and settings.

    Description

    Includes better nipples, under clothing variation, and better adherence for side-view angles. Additionally, you won't have to be as overly descriptive with your prompts to keep the penis between her breasts. The LoRA now understands that Titfuck means "penis between breasts" usually.

    This version was trained using the following configuration and dataset settings:

    • 26 videos 4-5s long each. 256x256. Downscaled using bicubic to minimize pixelation

    • 200 Epochs, each video is processed once per epoch.

    • Learning rate of 2e-5

    • Captions had reduced redundancy (removal of "penis between breasts" and other overly descriptive elements) to allow the LoRA to increase association with "titfuck" instead of other tokens.

    • Introduced more side-view videos, videos that included better nipple detail, and titfucks with clothing (bikinis, sports bras, etc)

    FAQ

    Comments (37)

    wqn999Feb 18, 2025
    CivitAI

    Awesome Loras, great work

    KinkMasterFeb 18, 2025
    CivitAI

    Stacking loras definitely diminished the movement on it, but still captures it well enough. Great work.

    ComfyTinker
    Author
    Feb 19, 2025

    Some LoRAs that affect body movement are going to be really hard to combine. They both likely affect the same vectors. Other LoRAs (Stylistic, or enhancements) like Move Enhancer or Cyberpunk should work fairly well.

    KinkMasterFeb 20, 2025

    @ComfyTinker The full release version does great at preserving the movement while also not impacting faces too. Great work! Mind sharing your training settings? LR, steps, batch #, frame count and resolution, that sort of thing? Might help me with some complex movement concepts I'm working through with training.

    ComfyTinker
    Author
    Feb 20, 2025· 1 reaction

    @KinkMaster 256x256 videos at 24fps. They were downscaled, but I made sure to use bicubic downscaling to avoid pixelation. They were all manually captioned fairly in detail. I captioned individual facial details when their faces were in frame, and I included a lot of videos that kept the face out of frame, as well.

    Total epochs - 200
    Total input videos - 65
    Total steps - 13000
    Loss rate - 2e-5
    Gradient accumulation steps - 1
    No repeats per epoch

    KinkMasterFeb 20, 2025

    @ComfyTinker Thanks a ton! Very helpful!

    vfx_aiFeb 25, 2025

    lower the guidance for more movement in any scenario

    vfx_aiFeb 26, 2025

    increase the strength to 1.2 to get the motion back when using a character lora

    ImagineBreakerFeb 20, 2025
    CivitAI

    Where is the diffusion model from your workflow from?

    ComfyTinker
    Author
    Feb 20, 2025

    https://comfyanonymous.github.io/ComfyUI_examples/hunyuan_video/

    I use the official comfyorg repackage, but these LoRAs should work with others.

    ImagineBreakerFeb 20, 2025

    @ComfyTinker Do you have a link to the comfyorg repackage? I'm using a 1 click install of comfy called windows portable.

    ComfyTinker
    Author
    Feb 20, 2025

    @crazymanjj I linked to comfy's official example page. you can download it from.

    @crazymanjj do u get the workflow?

    ComfyTinker
    Author
    Mar 3, 2025

    @forbiddenkingmaker1230680 It's in the metadata of the videos.

    @ComfyTinker where to find the metadata

    daldraeicFeb 21, 2025· 1 reaction
    CivitAI

    A noticeable improvement from 0.9 to 1.0. No more movement loras necessary and much less praying to RNGesus for a coherent result.

    ComfyTinker
    Author
    Feb 21, 2025

    I plan to revisit my spanking LoRA with what I've learned.

    KiefstormFeb 22, 2025· 3 reactions
    CivitAI

    It works really well, great work. It doesnt seem to affect char lora too much, which is nice. Did you remove faces from the training data?

    Also, in your Tips you have a typo "She is titfucking his penis between here breasts."

    ComfyTinker
    Author
    Feb 22, 2025· 1 reaction

    Thanks for the correction, I've updated the typo!

    As for faces in the dataset, I used a bunch of videos with the face cropped out, or when the face was included I made sure to describe them with.

    Ex:

    "She is brunette woman with hair is loose waves with thick eyebrows, blue eyes, thick lips, and a seductive expression looking up. Her hair is in a messy bun"

    7213659Feb 23, 2025
    CivitAI

    When I drag the video to ComfyUI online, it says no workflow file is found. I tried 2-3 videos and all say the same. What can I do?

    ComfyTinker
    Author
    Feb 23, 2025

    Not sure how ComfyUI online is set up, but I would just set up a standard HunYuan workflow and copy the prompt I shared in the description, then.

    7213659Feb 23, 2025

    @ComfyTinker Okay thanks, I am new to all this stuff. I shall try your method.

    KinkMasterFeb 26, 2025
    CivitAI

    Where you training WAN loras? Is it really that similar to Hunyuan?

    ComfyTinker
    Author
    Feb 26, 2025· 1 reaction

    I use diffusion-pipe. Yes it is very similar to HunYuan

    OnlyGANsFeb 26, 2025

    @ComfyTinker For the upcoming 14B WAN variant, is that compatible with only the 14B t2v model or it would also work with the 14B i2v model?

    K3NKFeb 26, 2025

    you just drop the wan models into unet and vae folders and youre good to go?

    WhatTheGuyFeb 26, 2025· 1 reaction

    @K3NK use the wrapper https://github.com/kijai/ComfyUI-WanVideoWrapper . From my testing Hunyuan is way better than the 1.3B model. The 14B model doesn't work for me atm

    OnlyGANsFeb 27, 2025

    I haven't seen a unet but I was able to run both the 1.3b and 14b WAN models after updating ComfyUI and using the workflows from this guide https://comfyanonymous.github.io/ComfyUI_examples/wan/

    ComfyTinker
    Author
    Feb 27, 2025· 4 reactions

    @OnlyGANs 14B LoRA models are cross compatible for both I2V and T2V from my testing.

    AivanjoFeb 27, 2025· 1 reaction

    @WhatTheGuy Hunyuan has 13B parameters, so it is expected that the Wan 1.3B model will be worse. But I suppose that Wan 14B should surpass Hunyuan, at least in motion quality. And if there are no problems with censorship, Wan will blow up the community again, as it did with Hunyuan.

    WhatTheGuyFeb 27, 2025

    @Aivanjo yes the 1.3B is the smaller model, but basic concepts like a blowjob work with base hunyuan and isn't possible at all with base WAN. So with hunyuan it's just finetuning what the base model already knows. WAN has never seen it. So it's a entirely new concept for WAN.

    I'm not sure if the bit better model will produces better sex scenes when it entirely depends of the finetuned data. While with Hunyuan the power of the basemodel already knows the concept and you are just perfecting it.

    AivanjoFeb 27, 2025

    @WhatTheGuy Yes, that's what I meant when I talked about censorship. I haven't tested the WAN model myself yet. But if it doesn't allow generating sex and nudity without additional lore, in other words, if the model's dataset didn't contain such videos, then attempts to further train the model won't be very successful.

    WhatTheGuyFeb 27, 2025

    @Aivanjo you can generate naked breasts at least =) But always with underwear. Hm maybe this will become the new Flux of video models ;P

    AivanjoFeb 27, 2025

    @WhatTheGuy Another model to test the community's decensoring skills. Sounds exciting 😁

    firemanbrakeneckFeb 27, 2025· 1 reaction

    Haven't tested myself, but I'm hearing SD2.1 here...

    yuinyan490363Feb 27, 2025
    CivitAI

    Can a video be made by just writing one Titfuck

    ComfyTinker
    Author
    Feb 27, 2025

    You could in theory, but HunYuan typically needs more description than just this. Also you can titfuck a dildo, change clothes, change hair, and a bunch of other variations, so just the word "titfuck" might allow too much creativity and wouldn't get you where you need it.

    "A naked woman titfucking a naked man." would be the bare minimum, and would still require some prompt-fishing.

    "A naked woman titfucking a naked man. She is kneeling between his legs." would be my recommended starting point.

    LORA
    Hunyuan Video

    Details

    Downloads
    10,053
    Platform
    CivitAI
    Platform Status
    Available
    Created
    2/25/2025
    Updated
    7/31/2026
    Deleted
    -
    Trigger Words:
    Titfuck