Ray3.2

Luma video model: generation from text, from start and end keyframes and from multiple keyframe anchors, plus editing and reframing of existing video; up to 1080p with seamless looping.

по странице вендора звук нативно не генерируется — озвучка добавляется отдельным шагом; предел ключевых кадров на разных страницах вендора указан по-разному (16 и 64)

Understands

text, images, video

Produces

video

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.