{ "reference_lock": "first frame = uploaded image 1; use image 2 to keep her face consistent; keep her hair, outfit, the armchair, the sunset and the ocean exactly as in image 1; no sand on her; do not change identity", "action": "0-1.5s: she nods slightly to the table and says the short line; 1.5-2.5s: pause; 2.5-5s: she says the second line with a light ironic smile, glancing at the sand ...
Free to start · Generate videos and images with AI in seconds
