Genur.art

I2VA: For the target video, at 0.00 seconds into the target video, <Picture 1> is fully referenced as the exact starting frame and character identity. SUBJECT: Exact same freckled Asian woman from Picture 1 — short dark hair with bangs, freckles, topless. Maintain perfect facial and body likeness. ACTION / TIMING (9–10 seconds total): [0.0–2.5s] She holds the tongue-out, eyes-up funny face from the reference image. [2.5–5.0s] She switches to a new funny face — big exaggerated smile with eyes squinted shut. [5.0–7.5s] She switches to a third funny face — wide-eyed shocked expression with mouth open and tongue slightly out. [7.5–10.0s] She looks at the camera and says clearly: “Welcome to my funny face LoRA, noob.” End on this. ENVIRONMENT / LOOK: Exact soft indoor lighting and background from Picture 1. CAMERA: Tight close-up matching the reference framing. Holds steady on her face the entire time. AUDIO (native stereo): - Soft natural mouth and facial movement sounds - Clear female voice: “Welcome to my funny face LoRA, noob.” - Quiet room ambience - No music PRESERVE: Exact face, hair, freckles, and likeness from Picture 1. Keep the clear sequence of three different funny faces followed by the spoken line. AVOID: Repeating the same face or making the expressions too subtle.