I need image-to-video and text-to-video options in one place instead of switching between tools.

Provide a single, unified video generation experience that includes both image-to-video and text-to-video workflows in one place. This reduces context switching, speeds up creation, and makes it easier to compare outputs and iterate quickly.

This feature brings image-to-video and text-to-video generation into one consolidated interface so users don’t need to jump between separate tools. From a single starting point, users can choose whether to begin with a text prompt, an image, or switch modes mid-process without losing their work. The unified workflow keeps settings, styles, and generation controls consistent, helping users learn one system and reuse the same creative preferences across both approaches. Users can iterate faster by generating variations from text, then refining results using an image input (or vice versa) without re-uploading assets or reconfiguring options. Centralizing both capabilities simplifies experimentation, making it easier to evaluate which input method best achieves a desired result. It also streamlines common tasks like drafting concepts from text and then anchoring the final look with a reference image. Teams benefit from a clearer, more standardized process for video creation, reducing confusion about which tool to use for each step. Overall, the feature improves productivity and creative flow by offering a single destination for the two most common video generation starting points.