> For the complete documentation index, see [llms.txt](https://sogni.gitbook.io/sogni-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://sogni.gitbook.io/sogni-docs/sogni-studio/creating-videos/convert-image-to-video.md).

# Convert Image to Video

**Convert to Video** is the fastest way to bring a single image to life. It turns an existing image into a short video clip by adding motion, pacing, and cinematic direction—without requiring a full video setup.

This workflow is ideal for quick animations, testing ideas, or creating clips that you can later extend or combine.

<figure><img src="/files/ORCygsPLfn7dVQ9ZqCdz" alt="" width="375"><figcaption><p>Access the Convert to Video feature from the top toolbar.</p></figcaption></figure>

***

#### <mark style="color:blue;">Settings:</mark>

#### Cinematic Direction Prompt

The **Cinematic Direction Prompt** describes *how* the image should move and feel over time.

Instead of redefining the image itself, this prompt focuses on:

* camera behavior (push-in, pull-back, handheld, orbit)
* pacing (slow, fast, rhythmic, drifting)
* cinematic style (music video, film shot, documentary, abstract motion)

**Example**

> Rock music video, fast paced, slow shutter speed

Think of this as directing a shot, not rewriting the scene.

***

#### Presets and Custom Direction

You can choose a preset for common cinematic styles or write your own custom direction.

Presets are a great starting point if you want predictable results.\
Custom prompts give you full control when you already know the motion you want.

***

#### Include Image Prompt and Style

When enabled, Sogni automatically carries over:

* the original image prompt
* the image’s visual style

This helps maintain consistency between the still image and the generated video.

**Recommended:** Leave this enabled unless you intentionally want the motion to reinterpret the image.

***

#### FPS and Duration

* **FPS (Frames Per Second)**\
  Controls how smooth motion appears.
  * 16 FPS: cinematic, slightly stylized motion
  * 32 FPS: smoother, more fluid motion
* **Duration**\
  Sets the total length of the clip.

Longer clips take more time and cost more to render, so starting short is usually best.

***

#### Loop

When enabled, the clip is generated with looping in mind, making it suitable for seamless repeats or background motion.

Best used for:

* ambient scenes
* subtle camera motion
* abstract or rhythmic visuals

***

#### Create Video

Once you’re ready, click **Create Video** to start rendering.

* Video rendering runs on **Fast Supernet**
* Currently supports **Wan 2.2**
* Progress appears in the **Activity Window**
* You can continue working while the job runs

<figure><img src="/files/UGj4BrFWZGA9SvllTt79" alt="" width="375"><figcaption><p>Progress appears in the <strong>Activity Window.</strong><br>Use shortcut Command-1 or open it from the Windo menu<strong>.</strong></p></figcaption></figure>

When finished, the clip can be previewed, saved to the gallery, extended using frame references, or combined with other clips.

***

#### Tips for Better Results

* Images with clear depth (foreground / background separation) animate best.
* If motion feels too static, add directional cues like *slow push forward* or *camera drift*.
* If motion feels chaotic, simplify the prompt and reduce stylistic adjectives.
* Short clips are easier to refine—extend them later using first/last frame continuity.


---

# 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://sogni.gitbook.io/sogni-docs/sogni-studio/creating-videos/convert-image-to-video.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.