Fuck Machine Dildo Deepthroat Blowjob LoRa for Hunyuan | Wan Video
Trained on a dataset of 129 clips with 256x256 resolution, 1sec to 3sec, 5e-05 Learning Rate, Num_Repeat = 1
30 different source videos.
The workflow im using is:
FramePack π img2vid / txt2vid with LoRa Workflow from @K3NK
Hunyuan π» AllInOne βAll Versions π.π±π©π§πͺ - Ultra1.5 from @LatentDream
IMG to VIDEO simple workflow WAN2.1 | GGUF | LoRA | UPSCALE | TeaCache @UmeAiRT
TXT to VIDEO simple workflow WAN2.1 | GGUF | LoRA | UPSCALE | TeaCache @UmeAiRT
* you can find a slightly modded wan workflow inside the sample video's metadata
Example i2v prompt:
A woman is seen deep-throating a flesh-colored dildo attached to a fucking machine. She appears to be gagging, with drooling and a huge bulge in her throat. The lighting is soft, highlighting her facial expressions and the movement of the dildo.Example t2v prompt:
A woman with {turquoise|blonde|black|red} hair and {pale|dark} skin is seen deepthroating a {flesh-toned|dark-toned} dildo attached to a fucking machine. She wears a {choker|police hat|helicopter hat}, has {nose|nipple|eyebrow} piercings, and {heavy makeup with dark eyeliner|no makeup}. The dildo is partially inserted, with visible motion suggesting thrusting. She appears to be gagging, with drool and a huge bulge at her throat. The background features a bed with blue sheets and a monochrome leaf-patterned wall art. The lighting is soft, highlighting her facial expressions and the dildo's motion.Have fun! π
***** This LoRA is shared without warranties and with the condition that it is used in a lawful and responsible way. I do not support or take responsibility for illegal, harmful, or harassing uses. By downloading or using it, you accept that you are solely responsible for how it is used. *****
Description
FAQ
Comments (8)
I told you it would look good on t2v! Thank you for doing it man :) much love
Any possibility for a vaginal version?
Either way, good work!
A wan 2.2 version please. Also, really need a version for fucking machine dildo in vagina and ass.
There is a big issue with this lora. When the image start with the dildo inside her mouth, the glans is extremely long when the dildo move back.
Also impossible to replicate, using the recommended prompt, the fast motion of the dildo.
Each time the dildo do 1 or 2 morion only very slowly.
Has someone managed to get good result on wan2.2 with T2v model?
im training this same dataset , i want to improve the face.. so i will retrain again the low at 720 res tonight, removing some of the clips since one of the girls is influecing too much the end result.. didnt happen in 2.1 , maybe is the automagic optimizer.. idk..
Any possibility to recreate this for wan2.2?
Details
Files
wan-fmachine-deepthroat-t2v-36epo-k3nk.safetensors
Mirrors
wan-fmachine-deepthroat-t2v-36epo-k3nk.safetensors
wan-fmachine-deepthroat-36epo-k3nk.safetensors
wan-fmachine-deepthroat-t2v-36epo-k3nk.safetensors
wan-fmachine-deepthroat-36epo-k3nk.safetensors
wan-fmachine-deepthroat-t2v-36epo-k3nk.safetensors
wan-fmachine-deepthroat-t2v-36epo-k3nk.safetensors
wan-fmachine-deepthroat-t2v-36epo-k3nk.safetensors
wan-fmachine-deepthroat-t2v-36epo-k3nk.safetensors
T2V_wan-fmachine-deepthroat-t2v-36epo-k3nk.safetensors
wan-fmachine-deepthroat-36epo-k3nk.safetensors
wan-fmachine-deepthroat-36epo-k3nk.safetensors
wan-fmachine-deepthroat-t2v-36epo-k3nk.safetensors