# Reference images and videos
| Mode | Use when | Input |
| -------------------- | ---------------------------------------------------------------- | ------------------------------------------------ |
| Text-to-video | You want a new scene from prompt only. | No reference required. |
| Image-to-video | You need one actor, product, or starting image reference. | One image. |
| First-last-frame | You need control over the beginning and ending frame. | Start image and end image. |
| Reference-to-video | You need stronger consistency across people, products, or style. | Multiple references, depending on model support. |
| Motion-control | You want an actor or subject to follow reference movement. | Character image and motion video. |
| Video edit/reference | You are using an existing video as the base or motion reference. | Video plus optional images. |
Use clean references. For actors, use a clear face, stable lighting, and minimal occlusion. For products, use sharp images on simple backgrounds. For app demos, use screen recordings as b-roll instead of asking the model to recreate exact UI from memory.
---
# Agent Instructions: Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://docs.avastudio.com/studio-mode/reference-images-and-videos.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.