💦 Facial Concept LoRA (Video | WAN2.2 5B)

Hey everyone!

This is my fifth video LoRA, trained mostly for facial cumshot animations, but it can also produce full body shots when prompted. This time, I trained on anime-style data, and I was honestly surprised at how well it works on realistic models too.

Huge thanks to FLOW0308 and Bonz_ai for their amazing videos on Civitai — they made this possible.
I didn't want to use realistic cum with realistic dataset because what is the point of it when you can find that on any adult website.
Rvage have released amazing WAN2.2 5B workflow with torch compile, block swap and other goodies, check it out: https://civarchive.com/models/1676197/wan-video-stdgguf?modelVersionId=2095534

🔧 Training Details:

• Model Target: WAN2.2 5B

• Dataset: 3-second clips (72 frames), anime style, focused on facial shots, occasional body framing

• Angles: Front-facing, POV, slight side

• Cross-compatibility: Works well with realistic styles despite anime dataset

• Resolution: 512x512

• Training Steps: 5000 total (concept was harder to learn than usual)

• Training Time: ~7 hours on an RTX 5090

• VRAM Usage: ~14GB peak

• Workflow: Default ComfyUI video training setup with LoRA loader

• Trigger Word: facial

💡 Notes:

• The concept took more steps to learn compared to other positions or actions, but the extra training paid off.

• Works in both anime and realistic models — better than expected.

• Still room for fine-tuning the fluid physics and face-to-camera alignment.

• Dataset was mostly male masturbating so if your picture doesn't contain a male with own penis grab it can do weird stuff.

Hope this helps anyone looking to make specialized erotic video LoRAs!
Feedback is welcome — enjoy 🎬💦