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 Harley Quinn from Picture 1 — blonde hair with red and blue space buns, freckles, colorful eye makeup, red lipstick, black choker, red-and-blue paint-splattered jacket over a graphic tee. Maintain perfect facial likeness and style throughout. ACTION / TIMING (8 seconds total): [0.0–8.0s] She looks directly at the camera with a wide, playful open-mouthed expression matching the reference. She speaks in a strong New York / Brooklyn accent, teasing and flirty: “Hey Puddin’… welcome to my AI LoRA. The bats won’t get in your way here.” She keeps the teasing energy, slight head movements, and lively facial expression the whole time. ENVIRONMENT / LOOK: Clean light grey studio background matching Picture 1. Soft even lighting, sharp detail on her face and makeup. CAMERA: Starts matching the tight close-up reference framing on her face. Holds steady with only very slight natural movement. AUDIO (native stereo): - Clear female voice with a strong New York / Brooklyn accent, teasing and playful tone: “Hey Puddin’… welcome to my AI LoRA. The bats won’t get in your way here.” - Quiet room tone - No music PRESERVE: Exact face, freckles, space buns, makeup, choker, and jacket from Picture 1. AVOID: Softening her expression or changing the accent.
Parameters used to generate this content
The node graph used to generate this content — pan and zoom to explore, or download it to run in ComfyUI.
AI models used to generate this content