video-to-video
Pixverse V6 视频续写
Pixverse V6 视频续写通过分析现有视频的结尾片段，向前生成新帧，延续并增强视频内容，保持自然运动和场景动态效果。
万相 Wan 2.7 视频编辑
万相 Wan 2.7 视频编辑模型，支持多模态输入（文本/图像/视频），可完成指令编辑和视频迁移任务。支持720P和1080P分辨率，时长2~10秒，按秒计费。输出默认包含音频。
万相 Wan 2.7参考生视频
万相 Wan 2.7参考生视频模型，支持多模态输入（文本/图像/视频），可将人或物体作为主角，生成单角色表演或多角色互动视频。支持智能分镜，生成多镜头视频。支持720P和1080P分辨率，时长2~10秒，按秒计费。输出默认包含音频。
Veo 3.1 Lite 视频延展
基于 Google Veo 3.1 Lite 模型的视频延展 API，支持对输入视频进行内容延展生成
Veo 3.1 Fast Video Extension
Extend the input video by 7 seconds using the Google Veo 3.1 Fast model. Supports 720p and 1080p resolutions, as well as 16:9 and 9:16 aspect ratios. Input video requirements: MP4 format, 24 fps, duration 1–30 seconds.
Veo 3.1 Video Extensions
Use the Google Veo 3.1 model to extend the input video by 7 seconds. Supports 720p and 1080p resolutions, as well as 16:9 and 9:16 aspect ratios. Input video requirements: MP4 format, 24 fps, duration 1–30 seconds.
Kling V3.0 Motion Control
The Kling V3.0 motion control tool can extract motion paths from reference videos and apply them to reference images to generate videos while maintaining subject consistency. It supports both Standard and Professional modes and is billed by the second.
Heygen Video-translate
The Heygen series offers reliable generation capabilities, making it ideal for production environments. Designed for production-grade use, this series prioritizes stability and controllable output. Its video translation feature automatically translates voiceovers and synchronizes them with lip movements, making it perfect for multilingual distribution and international localization. The real-time inference API delivers consistent performance with no waiting time and is affordably priced.
Wan 2.6 Video Reference
The Wan2.6 series offers reliable generation capabilities, making it ideal for production environments. Designed for production-grade use, this series prioritizes stability and predictable output. When generating reference videos, it preserves the original video structure while re-rendering the style and texture, making it suitable for fan creations and restoration/upgrades. The real-time inference API delivers stable performance with no waiting time and is affordably priced.