Video
Pixverse 5
Use it ↗A high-resolution model with Text-to-Video (T2V) support and First/Last Frame workflows for precise cinematic control and multi-subject handling.
Pixverse 5 (August 2025) is a versatile AI video generator that creates clips from text or image inputs. It supports output durations of 5 and 8 seconds and resolutions of 360p, 540p, 720p, and 1080p. This model introduced Text-to-Video (T2V) and First/Last Frame workflow capabilities to the Pixverse family, offering users precise creative control over cinematic outputs. It is engineered for high-resolution results and strong multi-subject handling, making it suitable for detailed commercial and narrative work.