Beijing Aishi Technology Co., Ltd. recently announced that its PixVerse platform has officially launched video generation and image generation technology services to the public.
Prior to this, Aishi Technology's PixVerse V3 was globally launched, showcasing significant improvements in its underlying model capabilities. It offers multimodal generation abilities and a variety of AI features, including creative templates, lip-syncing, story continuation, and style transfer.
PixVerse V3 demonstrates a more precise and stunning understanding of prompts and video generation effects, capable of conveying details such as emotions, textures, and cinematography, effortlessly blending reality and the virtual world. The model showcases its video generation capabilities through a series of vivid examples, such as a samurai running in the snow, a cat wearing a wizard hat, and a panda resting on a swing, all of which highlight the advanced capabilities of PixVerse V3 in video generation.
In addition to basic video generation functions, PixVerse V3 has introduced multiple creative templates, including Alive Art, Monster Invasion, Wizard Hat, and Leggy Run, allowing users to easily use AI magic to add fun to their lives. The V3 version also supports multimodal video generation, including multilingual character voice synchronization and story extension, broadening the boundaries of AI video creation. Users can utilize the lip-syncing feature to make characters in the video speak and support various languages. The story continuation feature allows users to add prompts based on already generated videos, advancing the plot while maintaining high coherence of characters and actions.
Application link: https://wiuswkbgux0.feishu.cn/share/base/form/shrcnp3FuYHCpkqTzJbQzoUu5F5
