> For the complete documentation index, see [llms.txt](https://docs.reelhq.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.reelhq.ai/prompting-guide/image-to-video-prompts.md).

# Image-to-Video Prompts

Reel supports image-to-video prompting, allowing you to generate rich video content based on a single image input. This is perfect for evolving artwork, enhancing still frames, or animating stylized visuals into full-motion scenes.

#### ⚙️ How It Works

You can attach an image directly in your prompt (Telegram bot or web app), and Reel will use it as the visual base to generate a motion sequence that stays stylistically consistent.

> 📌 Note: Ensure your image is high quality and well-lit for best results. Complex compositions work better than plain backgrounds.

***

#### 🧠 Best Practices

**✅** 

**Describe the scene, not the image**

Don’t just upload and say “animate this.” Give a clear scene direction.

> Example:

> “A cinematic zoom-out from this image, transitioning into a dreamy sunrise landscape, subtle camera motion.”

**✅** 

**Set motion expectations**

Mention how the camera should move or what should evolve in the scene.

> Example:

> “Slow panning shot revealing a crowd behind the subject, mist rolling in from the mountains.”

**✅** 

**Match your prompt to the image’s aesthetic**

Use the same mood/style keywords (e.g. *vaporwave*, *digital painting*, *anime*, etc.) for consistency.

***

#### 🚫 What to Avoid

* Uploading very low-res or cluttered images
* Using text-heavy images — the model doesn’t preserve written text
* Expecting perfect facial consistency unless specified carefully

***

#### 🧪 Advanced Tip: Use Reels for Evolutions

Want to show time progression or transformation?

Start with an image, and guide the video into a different time of day, expression, or location.

> “Start with this medieval tavern image and slowly transition into a nighttime battle scene in the same location.”


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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.reelhq.ai/prompting-guide/image-to-video-prompts.md?ask=<question>
```

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.