[Integrations](https://spiral.ai/integrations) › [Codex](https://spiral.ai/integrations/codex) › [Vidu Q2 Text to Image](https://spiral.ai/integrations/codex/vidu-q2-text-to-image)

# How to Use Vidu Q2 Text to Image in Codex

Vidu Q2 Text to Image turns written scene descriptions into single still images for concept work and marketing drafts. Unlike Vidu Q2 Reference to Image, it starts from text alone.

|  |  |
| --- | --- |
| Model | Vidu Q2 Text to Image |
| Available through | fal |
| Category | Image |
| Price | $0.065 per image. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Vidu Q2 Text to Image in Codex

- Read the homepage copy and use Vidu Q2 Text to Image to create a wide illustration of a neighborhood bicycle repair shop. Put the mechanic and workbench on the right, leave the left third uncluttered for the headline, and use soft morning light.
- Use Vidu Q2 Text to Image to make a square editorial illustration for the gardening article in this project: a balcony with terracotta pots, herbs, a watering can, and late-afternoon light. Keep the generation prompt under 1,500 characters.
- Read the game's setting notes and use Vidu Q2 Text to Image to create one concept image of its abandoned railway station. Show the entrance from street level, with overgrown tracks and rain-darkened brick.
- Use Vidu Q2 Text to Image to create a portrait artwork draft for the reading app's welcome screen: an armchair beside a tall window, books on a low table, and an overcast sky outside. Leave the upper area simple for interface text.
- Use Vidu Q2 Text to Image to create two separate landscape artwork drafts for the travel page. Keep the seed and scene description fixed, change only the requested lighting from morning to evening, and save both prompts with the images.

## How to set up Vidu Q2 Text to Image in Codex

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the hosted server**

```bash
codex mcp add spiral --url https://api.spiral.ai/mcp
```

2. **Sign in**: Codex opens the browser: sign in to Spiral and click Authorize. No API key. `codex mcp list` then shows Spiral.

```bash
codex mcp login spiral
```

### Use the Spiral skill

1. **Send Codex this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Vidu Q2 Text to Image**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/vidu/q2/text-to-image",
    "input": {
      "prompt": "A majestic dragon perches on the mountaintop, its eyes fixed intently on a small baby dragon."
    }
  }'
```

Then paste one of the prompts above: Codex finds Vidu Q2 Text to Image on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/codex

## Vidu Q2 Text to Image tools and prices

- [Vidu](https://spiral.ai/tools/fal/fal-ai/vidu/q2/text-to-image) (fal): $0.065 per image.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| aspect_ratio | 16:9, 9:16, 1:1 | 16:9 | The aspect ratio of the output video |
| seed |  | — | Random seed for generation |

## What can you do with Vidu Q2 Text to Image in Codex?

Create draft artwork for the site or app you are building from a written visual brief. Your coding agent can use the project's copy to describe a scene and place the resulting still image in the layout.

### Article illustrations

Use Vidu Q2 Text to Image to turn an article's central idea into a scene, such as a crowded repair bench for a story about fixing electronics.

### Campaign concept reviews

Use Vidu Q2 Text to Image to sketch a campaign setting before commissioning final artwork. Describe the subject, props, lighting, and space reserved for copy.

### Website artwork drafts

Use Vidu Q2 Text to Image to explore artwork for a landing page. Describe the intended composition and leave clear space where the page's headline will sit.

### Social post artwork

Use Vidu Q2 Text to Image to create a still scene for a social post, with the subject and background described in the brief.

### Fictional scene development

Use Vidu Q2 Text to Image to explore a location from a written story, such as a mountain observatory or a market built inside an abandoned station.

### Newsletter artwork

Use Vidu Q2 Text to Image to illustrate an issue's theme with a new still image. Keep the visual brief separate from headlines and other publication text.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Codex guides](https://spiral.ai/integrations/codex)

## Vidu Q2 Text to Image in other agents

- [Amp](https://spiral.ai/integrations/amp/vidu-q2-text-to-image)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/vidu-q2-text-to-image)
- [Claude](https://spiral.ai/integrations/claude-desktop/vidu-q2-text-to-image)
- [Claude Code](https://spiral.ai/integrations/claude-code/vidu-q2-text-to-image)
- [Cline](https://spiral.ai/integrations/cline/vidu-q2-text-to-image)
- [Cursor](https://spiral.ai/integrations/cursor/vidu-q2-text-to-image)
- [Devin](https://spiral.ai/integrations/devin/vidu-q2-text-to-image)
- [dots](https://spiral.ai/integrations/dots/vidu-q2-text-to-image)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/vidu-q2-text-to-image)
- [Gemini](https://spiral.ai/integrations/gemini/vidu-q2-text-to-image)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/vidu-q2-text-to-image)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/vidu-q2-text-to-image)
- [goose](https://spiral.ai/integrations/goose/vidu-q2-text-to-image)
- [Grok](https://spiral.ai/integrations/grok/vidu-q2-text-to-image)
- [Grok Build](https://spiral.ai/integrations/grok-build/vidu-q2-text-to-image)
- [Hermes](https://spiral.ai/integrations/hermes/vidu-q2-text-to-image)
- [Instinct](https://spiral.ai/integrations/instinct/vidu-q2-text-to-image)
- [Manus](https://spiral.ai/integrations/manus/vidu-q2-text-to-image)
- [Muse](https://spiral.ai/integrations/muse/vidu-q2-text-to-image)
- [Muse Code](https://spiral.ai/integrations/muse-code/vidu-q2-text-to-image)
- [n8n](https://spiral.ai/integrations/n8n/vidu-q2-text-to-image)
- [Notion](https://spiral.ai/integrations/notion/vidu-q2-text-to-image)
- [OpenClaw](https://spiral.ai/integrations/openclaw/vidu-q2-text-to-image)
- [opencode](https://spiral.ai/integrations/opencode/vidu-q2-text-to-image)
- [Perplexity](https://spiral.ai/integrations/perplexity/vidu-q2-text-to-image)
- [Raycast](https://spiral.ai/integrations/raycast/vidu-q2-text-to-image)
- [VS Code](https://spiral.ai/integrations/vscode/vidu-q2-text-to-image)
- [Windsurf](https://spiral.ai/integrations/windsurf/vidu-q2-text-to-image)
- [Zapier](https://spiral.ai/integrations/zapier/vidu-q2-text-to-image)

## More Codex guides

- [Vidu Q2 Reference to Image](https://spiral.ai/integrations/codex/vidu-q2-reference-to-image)
- [Vidu Reference to Image](https://spiral.ai/integrations/codex/vidu-reference-to-image)
- [Topaz Upscale Precision](https://spiral.ai/integrations/codex/topaz-upscale-precision)
- [Wan 2.2 5B Text to Image](https://spiral.ai/integrations/codex/wan-2-2-5b-text-to-image)
- [Topaz Transparent Image Upscale](https://spiral.ai/integrations/codex/topaz-transparent-image-upscale)
- [Wan 2.2 A14B Image to Image](https://spiral.ai/integrations/codex/wan-2-2-a14b-image-to-image)

## Questions about Vidu Q2 Text to Image in Codex

**Can Codex use Vidu Q2 Text to Image?**

Yes. Add Spiral to Codex as an MCP server, and Codex can find and run Vidu Q2 Text to Image like any built-in tool.

**How much does Vidu Q2 Text to Image cost in Codex?**

$0.065 per image. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Codex plan is separate.

**Do I need a fal account to use Vidu Q2 Text to Image in Codex?**

No. Spiral runs Vidu Q2 Text to Image on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Vidu Q2 Text to Image in Codex?**

About two minutes: add the hosted server, then sign in.

**Does Codex wait while Vidu Q2 Text to Image runs?**

Vidu Q2 Text to Image runs in the background. Codex starts the run, checks on it and gives you the image when it's ready.

**What is Vidu Q2 Text to Image useful for?**

Use it for still-image concepts, marketing drafts, and illustrations for static content. Suggested starting points include an article illustration, a campaign scene, or a visual direction to discuss with a designer.

**Does Vidu Q2 Text to Image create video?**

It produces a single still image. Use it to develop the appearance of a scene before planning animation.

**How long can a Vidu Q2 Text to Image prompt be?**

Keep the generation prompt within 1,500 characters. Put the subject, setting, composition, and lighting first, then remove repeated descriptions.

**What does Vidu Q2 Text to Image return?**

Each generation returns one PNG image. Request separate generations when you want several concepts to compare.

**How should I refine a Vidu Q2 image concept?**

Try keeping the seed and most of the description fixed while changing one detail, such as the lighting or viewpoint. Treat this as a comparison method rather than a promise that every other detail will stay identical.

