Wan doesn't seem to understand the concept of licking or sucking fingers, so I decided to remedy that!
Wan 2.2 version: trained locally on my RTX5090 with Musubi Tuner on 20 videos of various porn stars. 384x384x60 frames. Different training set to Wan 2.1 that has less exaggerated mouth movements which are more natural. Hi: 40 epochs 800 steps (2h45m), Lo: 65 epochs 1300 steps (5h30m)
Wan 2.1 versions (T2V/I2V): trained locally on my RTX5090 with Musubi Tuner on 34 videos of various porn stars. 256x256 resolution, 3400 steps, 100 epochs. 5 hours total training time.
My Wan motion LoRA full training process is covered here in my new tutorial.
I have also written a series of articles here on Civitai on the subject of Video Motion Training.
Please consider supporting me on RiotModels to help me in continuing to make new LoRAs. Your reward is exclusive content of the Seven Sisters in the most naughty of animations.
Keyword shouldn't be necessary but it's "fingers_in_mouth" for Wan 2.2
Prompt is simple. Use any combination of
licking fingers
fingers in mouth
sucking fingers
she licks her fingers
For one person licking the other person's fingers, the starting image really needs the other's fingers close to the mouth otherwise the person tends to suck their own fingers.
See sample videos for full prompts.
Versions:
Wan 2.2 i2v v1.0 - good natural motion with guaranteed prompt adherence
Wan 2.1 480 i2v v1.0 - very nice, detailed licking and sucking action with lips, fingers and tongue
Wan 2.1 14B t2v v1.0 - good motion but IMO not as good as i2v. May require more training.
Description
FAQ
Comments (9)
Nice LORA. Finger sucking/Licking definitely needed some help with a LORA.
Looks great! You got it working in combo with liquids.
I COULD WATCH THIS ALL DAY
Is this wan2.2?
No, sir, it's 2.1. I'll update the description to clarify this.
It works in 2.2 though, just fine. An update with hi/low would be welcome though
@null it's on the list!
For some reason this model won't run on tensor art, tried to reprint it privately and it says wrong base model, I have tried all labeling with all their wan model options but it always has the same problem. I don't know much about this but is there some kind of metadata missing or mislabeled in the model? Not sure what is wrong.
"Base model type of the file is , which does not match the selected type. Please check and re-upload."
Having had no experience of running remote models, or tensor art, I'm afraid I don't know. The training command definitely invoked the Wan14B480p i2v model. It's possible that there might be an additional flag to add metadata. If I find out anything new, I'll let you know.
Details
Files
wan_finger_licking_i2v-480_v10.safetensors
Mirrors
wan_finger_licking_i2v-480_v10.safetensors
wan_finger_licking_i2v-480_v10.safetensors
wan_finger_licking_i2v-480_v10.safetensors
wan_finger_licking_i2v-480_v10.safetensors
wan_finger_licking_i2v-480_v10.safetensors
wan_finger_licking_i2v-480_v10.safetensors
wan_finger_licking_i2v-480_v10.safetensors
wan_finger_licking_i2v-480_v10.safetensors
wan_finger_licking_i2v-480_v10.safetensors
wan_finger_licking_i2v-480_v10.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.