| {"id": "01-t2va-dialogue", "prompt": "two kids in a treehouse; the older boy says \"Do you hear that?\" and the girl whispers \"It is coming closer\". 6 seconds", "images": [], "check": ["no alignment line", "single shot", "speaker IDs (S1), (S2)", "dialogue in <d>[English]...</d> verbatim", "age and ethnicity for both children", "no mood words in non_diegetic_music"]} | |
| {"id": "02-t2va-multishot", "prompt": "a chef prepares a dish in a busy kitchen, then serves it to a customer who tastes it. 12 seconds", "images": [], "check": ["3 shots", "[Shot 2] At 00:0x.xxx, the camera cuts to ... in increasing order", "no speaker IDs (nobody speaks)", "no invented signs or brand names"]} | |
| {"id": "03-t2va-dialogue-multishot", "prompt": "a girl and her grandfather fish from a pier; she says \"I got one!\" and he laughs and says \"Careful, hold on tight.\" 12 seconds", "images": [], "check": ["multiple shots", "speaker IDs for both speakers", "exact dialogue", "age and ethnicity for both"]} | |
| {"id": "04-i2va-cats", "prompt": "the cats wake up one by one", "images": ["images/08-counts.png"], "check": ["first line is the exact I2VA alignment line", "style and subjects taken from the image", "exactly three cats, positions match the image", "single shot"]} | |
| {"id": "05-i2va-sign", "prompt": "the camera slowly pushes in as a breeze moves the sign, 5 seconds", "images": ["images/12-visible-text-caption.png"], "check": ["exact I2VA alignment line", "on-screen text \"Mill & Marrow\" quoted verbatim", "camera push-in with small amplitude at slow speed"]} | |
| {"id": "06-l2va-cats", "prompt": "ending frame of the video: the cats are all asleep, the earlier part shows them settling down. 6 seconds", "images": ["images/08-counts.png"], "check": ["last-frame alignment line with 6.00-second mark", "starts in a plausible earlier state", "ends exactly on the reference image"]} | |