> ## Documentation Index
> Fetch the complete documentation index at: https://docs.videodraft.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# AI Studio

> Generate images, videos, and audio with 50+ AI models

## Overview

Generate images, videos, and audio using 50+ AI models from a single interface.

<Info>
  Available on all plans. Plans differ by credit allocation.
</Info>

## Features

<CardGroup cols={2}>
  <Card title="50+ AI Models" icon="microchip">
    Images, videos, and audio
  </Card>

  <Card title="Multi-Reference" icon="layer-group">
    Up to 16 input images for consistency
  </Card>

  <Card title="Visual Asset Library" icon="images">
    Save and reuse generated assets
  </Card>

  <Card title="Prompt Engineer" icon="robot">
    AI-assisted prompt optimization
  </Card>
</CardGroup>

## Image Models

| Tier     | Models                                   | Credits |
| -------- | ---------------------------------------- | ------- |
| Budget   | Flux Schnell, Imagen 4 Fast, SeedDream 4 | 1-3     |
| Standard | Flux 1.1 Pro, Imagen 4, Flux 2 Pro       | 4-6     |
| Premium  | GPT-Image-1.5, Nano Banana Pro           | 13-24   |

For character consistency, use multi-reference models:

* **SeedDream 4**: 10 refs (3 cr)
* **Flux 2 Pro**: 8 refs (6 cr)
* **GPT-Image-1.5**: 16 refs (13 cr)

<Card title="All Image Models" icon="image" href="/models/image-generation">
  See full model list and pricing
</Card>

## Video Models

| Tier     | Models                   | Cost         |
| -------- | ------------------------ | ------------ |
| Budget   | Kling v2.1, Wan 2.2 Fast | 1-5 cr/sec   |
| Standard | Kling v2.6 Pro, Ray 2    | 7-18 cr/sec  |
| Premium  | Sora 2, Veo 3.1          | 10-60 cr/sec |

<Card title="All Video Models" icon="video" href="/models/video-generation">
  See full model list and pricing
</Card>

## Voice & Audio

60+ voices from Google, OpenAI, and ElevenLabs. Voice cloning available on Pro+.

<Card title="Speech Models" icon="microphone" href="/models/speech-synthesis">
  See all voice options
</Card>

## Prompt Tips

Image prompt structure:

```
[Subject] + [Environment] + [Lighting] + [Style]
```

Video prompt structure:

```
[Camera Movement] + [Subject/Action] + [Environment] + [Mood]
```

## Workflow

1. **Draft**: Flux Schnell (1 cr) or Kling v2.1 (25 cr)
2. **Refine**: Use Prompt Engineer to optimize
3. **Final**: Premium models for deliverables

## Plan Comparison

| Feature          | Starter | Pro | Visionary+ |
| ---------------- | ------- | --- | ---------- |
| All 50+ Models   | Yes     | Yes | Yes        |
| Concurrent Gens  | 1       | 3   | 5-10       |
| Unlimited Images | —       | —   | Yes        |
| Voice Cloning    | —       | Yes | Yes        |

## Next Steps

<CardGroup cols={3}>
  <Card title="Open AI Studio" icon="play" href="https://app.videodraft.ai/ai-studio">
    Start generating
  </Card>

  <Card title="Image Models" icon="image" href="/models/image-generation">
    All image models
  </Card>

  <Card title="Video Models" icon="video" href="/models/video-generation">
    All video models
  </Card>
</CardGroup>