> For the complete documentation index, see [llms.txt](https://docs.avastudio.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.avastudio.com/models-and-credits/model-modes.md).

# Model modes

Modes define the kind of input a model uses and the kind of output it creates.

| Mode               | Input                             | Use when                                                |
| ------------------ | --------------------------------- | ------------------------------------------------------- |
| Text-to-video      | Prompt                            | You want a new scene from written direction.            |
| Image-to-video     | Prompt plus image                 | You need a reference actor, product, or starting frame. |
| First-last-frame   | Prompt plus two images            | You want start and end frame control.                   |
| Reference-to-video | Prompt plus multiple references   | You need stronger consistency.                          |
| Extend-video       | Source clip plus prompt           | You want a clip to continue.                            |
| Motion-control     | Character image plus motion video | You want subject motion to follow a reference.          |
| Text-to-image      | Prompt                            | You want a new still asset.                             |
| Image-to-image     | Prompt plus image references      | You want to transform or adapt references.              |

Not every model supports every mode. If a mode is unavailable, choose a different model or simplify the input.
