Basic Model Information: This is a high-noise LORA model trained based on Wan Video 2.2 I2V-A14B. It can be connected to both high-noise and low-noise pipelines simultaneously, with the model weight set to 1.0.
Core Parameter Settings: The CFG value is 1, the sampler is set to euler, and the scheduler is simple.
Function & Effect: It can realize the cheek-pinching action as shown in the sample video. Through tests, it performs well in scenes of front-facing half-body portraits.
Trigger Word: (HUPONNL，画面里女人的脸颊被双手手指轻柔拉扯，她的面部表情随动作从平静逐步变为嘟嘟嘴，噘嘴或者微笑等不同状态，展现出趣味互动效果。)
Local use of video models has high requirements for computer configuration. If you want to have a try, you can click the link below—I have turned this LORA into an AI application and hosted it there. By registering through my link, you can get 1,000 points, and you will also receive 100 points every day when you log in. With these points, you can generate many pictures and videos for free!
https://www.runninghub.ai/ai-detail/1961299858403561474/?inviteCode=rh-v1158