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

# Introduction

Qolaba's Video Generation workspace lets you create short AI-generated videos from text prompts, reference images, or a combination of both — using multiple state-of-the-art generative video models. Whether you are animating a static image, generating a cinematic scene from a prompt, or creating a transition between two frames, the workspace gives you granular control over motion, quality, duration, and style.

***

#### What You Can Do

* **Text-to-video** — Describe a scene and generate a video from a written prompt
* **Image-to-video** — Upload a starting image and animate it with a motion prompt
* **Image transition** — Define a first and last frame and let the model generate the motion between them
* **Reference-guided generation** — Use images, videos, or audio as generation references (model dependent)
* **Cinematic control** — Apply motion, lens, lighting, focus, and enhancement keywords for precise stylistic control
* **Multi-model access** — Choose from multiple video models, each with different strengths for speed, quality, realism, and creative output
* **Multiple variations** — Generate several versions in one run and compare outputs before downloading

***

#### Who It's For

Video Generation in Qolaba is built for:

* **Marketers & advertisers** — Ad creatives, campaign concept videos, product demos
* **Content creators** — Social media clips, short-form video, visual storytelling
* **Designers & creative teams** — Storyboarding, mood reels, concept visualization
* **Businesses** — Product showcases, explainer clips, brand visuals

***

#### How to Access

1. Go to the **left navigation panel**
2. Click **Audio & Video**
3. Select [**Video Generation**](https://www.qolaba.ai/video-generation)

This opens the dedicated Video Generation workspace.

***

#### Interface Overview

The Video Generation workspace is organized into three areas:

1. **Left Panel — Input & Configuration** This is where you set up your generation. It contains:

* Model selector
* Prompt input and Magic Prompt toggle
* Reference media uploads (initial image, last frame, reference files)
* Keywords panel (motion, focus, lens, enhancement, lighting, negative keywords)

2. **Right Panel — Output Controls** This is where you define the parameters of your output:

* Number of generations
* Video duration
* Resolution and quality
* Aspect ratio and dimensions
* Audio generation toggle (model dependent)

3. **Bottom Bar — Credit Display** The live credit counter updates in real time as you adjust settings — showing exactly how many credits will be consumed before you generate. Total credits are calculated as **credits per video × number of generations**.

***

#### Generate Your First Video

* **Step 1 —** Open the workspace via **Audio & Video → Video Generation** in the left navigation panel.
* **Step 2 —** Select a model from the model selector. If you are unsure which to choose, see Model Selection & Configuration → for a full breakdown of model capabilities and recommendations.
* **Step 3 —** Enter a prompt describing your scene. Include the subject, environment, camera movement, and mood for best results. Use **Magic Prompt** to automatically enhance your prompt if needed.
* **Step 4 —** Optionally upload a reference image as the starting frame, last frame, or creative reference depending on your chosen model.
* **Step 5 —** Set your output preferences in the right panel — duration, resolution, aspect ratio, number of generations, and audio if applicable.
* **Step 6 —** Review the **credit cost** in the bottom bar. Adjust settings if needed.
* **Step 7 —** Click **Generate**. Your video will appear in the preview area once processing is complete.

{% hint style="info" %}
Start with a single generation at 720p before committing to a full batch or higher resolution. Refine your prompt based on the first result to avoid using credits on outputs that need significant changes.
{% endhint %}

***

#### What's in This Section

* [Input Controls ](/video-generation/input-controls.md)\
  \- [Prompt & Magic Prompt →](/video-generation/input-controls/prompt-and-magic-prompt.md)\
  \- [Reference Media Uploads →](/video-generation/input-controls/reference-media-uploads.md)\
  \- [Keywords →](/video-generation/input-controls/keywords.md)
* [Output Controls →](/video-generation/output-controls.md)
* [Understanding Credit Usage →](/video-generation/understanding-credit-usage.md)
* [Managing Generated Videos →](/video-generation/managing-generated-videos.md)