Step-Video-TI2V is an advanced image-to-video model developed by Shanghai Jieyue Xingchen Intelligent Technology Co., Ltd. It is trained based on the 30B parameter Step-Video-T2V and can generate videos up to 102 frames long based on text and image input. The core advantages of this model lie in its controllable motion amplitude and controllable camera movement, balancing the dynamism and stability of the generated video. In addition, it performs exceptionally well in generating anime-style videos, making it ideal for animation creation, short video production, and other applications. The open-sourcing of this model provides strong technical support for the video generation field and promotes the development of multimodal generation technology.