[Integrations](https://spiral.ai/integrations) › [Codex](https://spiral.ai/integrations/codex) › [Seedream 4.5 Text to Image](https://spiral.ai/integrations/codex/seedream-4-5-text-to-image)

# How to Use Seedream 4.5 Text to Image in Codex

Seedream 4.5 Text to Image creates posters, packaging concepts, and campaign artwork from a written brief. Unlike Seedream 4.5 Edit, it starts without reference images, making it useful when you need an initial visual direction.

|  |  |
| --- | --- |
| Model | Seedream 4.5 Text to Image |
| Available through | fal |
| Category | Image |
| Price | $0.052 per image. Billed on `num_images`, default 1. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Seedream 4.5 Text to Image in Codex

- Read the project's brand guide and use Seedream 4.5 Text to Image to create one 2K square campaign image for a reusable bottle. Place the bottle on the right, reserve the left third for copy, and use directional studio lighting.
- Read the event brief and use Seedream 4.5 Text to Image to create one 4K square poster. Use the exact title "Night garden", place the approved event details below it, and make the title the strongest element.
- Use Seedream 4.5 Text to Image to create one 2K square environment concept for the game described in the design document. Show the station entrance at dusk, with readable spatial depth and warm light from the doorway.
- Generate a product photo with Seedream 4.5 Text to Image: a matte black water bottle on wet slate, soft morning light, 1:1. Tell me the price first. Save the result in ./assets.
- Make four logo concepts for a coffee brand called "Northline" with Seedream 4.5 Text to Image.

## How to set up Seedream 4.5 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 Seedream 4.5 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/bytedance/seedream/v4.5/text-to-image",
    "input": {
      "prompt": "A selfie of a cat, with the cat as the protagonist. The setting is twilight at the Eiffel Tower. The cat is happy, holding a piece of baklava in its paw. The…"
    }
  }'
```

Then paste one of the prompts above: Codex finds Seedream 4.5 Text to Image on Spiral, shows the price and runs it.

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

## Seedream 4.5 Text to Image tools and prices

- [Bytedance Seedream V4.5 · Text to Image](https://spiral.ai/tools/fal/fal-ai/bytedance/seedream/v4.5/text-to-image) (fal): $0.052 per image. Billed on `num_images`, default 1.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| image_size |  | {"width":2048,"height":2048} | The size of the generated image. Width and height must be between 1920 and 4096, or total number of pixels must be between 2560*1440 and 4096*4096. |
| num_images | 1 to 6 | 1 | Number of separate model generations to be run with the prompt. |
| max_images | 1 to 6 | 1 | If set to a number greater than one, enables multi-image generation. The model will potentially return up to `max_images` images every generation, and in total, `num_images` generations will be carried out. In total, the number of images generated will be between `num_images` and `max_images*num_images`. |
| seed |  | — | Random seed to control the stochasticity of image generation. |

## What can you do with Seedream 4.5 Text to Image in Codex?

Create visual assets from the project's design brief, including posters, product concepts, and promotional artwork. Your coding agent can turn layout requirements into focused Seedream 4.5 prompts and review the results against the brief.

### Event poster concepts

Develop a poster with a clear title, supporting details, and a specified visual hierarchy. Use a written brief for new artwork or reference artwork for an edit.

### Packaging design studies

Explore package imagery, material appearance, and label placement before choosing a design direction. Check every word in the result.

### Campaign artwork

Develop promotional images around a specific subject, palette, lighting treatment, and headline. Describe each composition separately so its priorities stay clear.

### Product presentation concepts

Explore how a product could appear in a studio or lifestyle scene. Start from a description for concept work, or use Seedream 4.5 Edit with the actual product image.

### Film and game concept art

Develop characters, environments, and scene compositions for pre-production. Specify materials, lighting, and the relationship between objects.

## Overview

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

## Seedream 4.5 Text to Image in other agents

- [Amp](https://spiral.ai/integrations/amp/seedream-4-5-text-to-image)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/seedream-4-5-text-to-image)
- [Claude](https://spiral.ai/integrations/claude-desktop/seedream-4-5-text-to-image)
- [Claude Code](https://spiral.ai/integrations/claude-code/seedream-4-5-text-to-image)
- [Cline](https://spiral.ai/integrations/cline/seedream-4-5-text-to-image)
- [Cursor](https://spiral.ai/integrations/cursor/seedream-4-5-text-to-image)
- [Devin](https://spiral.ai/integrations/devin/seedream-4-5-text-to-image)
- [dots](https://spiral.ai/integrations/dots/seedream-4-5-text-to-image)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/seedream-4-5-text-to-image)
- [Gemini](https://spiral.ai/integrations/gemini/seedream-4-5-text-to-image)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/seedream-4-5-text-to-image)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/seedream-4-5-text-to-image)
- [goose](https://spiral.ai/integrations/goose/seedream-4-5-text-to-image)
- [Grok](https://spiral.ai/integrations/grok/seedream-4-5-text-to-image)
- [Grok Build](https://spiral.ai/integrations/grok-build/seedream-4-5-text-to-image)
- [Hermes](https://spiral.ai/integrations/hermes/seedream-4-5-text-to-image)
- [Instinct](https://spiral.ai/integrations/instinct/seedream-4-5-text-to-image)
- [Manus](https://spiral.ai/integrations/manus/seedream-4-5-text-to-image)
- [Muse](https://spiral.ai/integrations/muse/seedream-4-5-text-to-image)
- [Muse Code](https://spiral.ai/integrations/muse-code/seedream-4-5-text-to-image)
- [n8n](https://spiral.ai/integrations/n8n/seedream-4-5-text-to-image)
- [Notion](https://spiral.ai/integrations/notion/seedream-4-5-text-to-image)
- [OpenClaw](https://spiral.ai/integrations/openclaw/seedream-4-5-text-to-image)
- [opencode](https://spiral.ai/integrations/opencode/seedream-4-5-text-to-image)
- [Perplexity](https://spiral.ai/integrations/perplexity/seedream-4-5-text-to-image)
- [Raycast](https://spiral.ai/integrations/raycast/seedream-4-5-text-to-image)
- [VS Code](https://spiral.ai/integrations/vscode/seedream-4-5-text-to-image)
- [Windsurf](https://spiral.ai/integrations/windsurf/seedream-4-5-text-to-image)
- [Zapier](https://spiral.ai/integrations/zapier/seedream-4-5-text-to-image)

## More Codex guides

- [Seedream 4.5 Edit](https://spiral.ai/integrations/codex/seedream-4-5-edit)
- [Seedream 5.0 Flash Image Editing](https://spiral.ai/integrations/codex/seedream-5-0-flash-image-editing)
- [Seedream 4.0 Text to Image](https://spiral.ai/integrations/codex/seedream-4-0-text-to-image)
- [Seedream 5.0 Flash Layerize](https://spiral.ai/integrations/codex/seedream-5-0-flash-layerize)
- [Seedream 4.0 Edit](https://spiral.ai/integrations/codex/seedream-4-0-edit)
- [Seedream 5.0 Flash Text to Image](https://spiral.ai/integrations/codex/seedream-5-0-flash-text-to-image)

## Questions about Seedream 4.5 Text to Image in Codex

**Can Codex use Seedream 4.5 Text to Image?**

Yes. Add Spiral to Codex as an MCP server, and Codex can find and run Seedream 4.5 Text to Image like any built-in tool.

**How much does Seedream 4.5 Text to Image cost in Codex?**

$0.052 per image. Billed on `num_images`, default 1. 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 Seedream 4.5 Text to Image in Codex?**

No. Spiral runs Seedream 4.5 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 Seedream 4.5 Text to Image in Codex?**

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

**Does Codex wait while Seedream 4.5 Text to Image runs?**

Seedream 4.5 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 Seedream 4.5 useful for?**

Seedream 4.5 suits visual work that combines an image with deliberate layout and lettering, such as posters, packaging concepts, and campaign artwork. Its documented strengths include composition, typography, and readable small text.

**What resolution can Seedream 4.5 produce?**

Seedream 4.5 supports 2K and 4K output. Choose the image shape to match its intended use, then describe where the subject and lettering should sit.

**Can Seedream 4.5 put words inside an image?**

Yes. Typography and readable small text are documented strengths, and the maker recommends enclosing the exact wording in double quotation marks. Check the finished lettering before using the image.

**Which prompt languages does Seedream 4.5 support?**

The maker documents Chinese and English prompt support. That does not establish equal accuracy for lettering in every language.

**How should I structure a Seedream 4.5 prompt?**

Write a clear description of the subject, action, and environment. Add the intended image type, composition, lighting, and exact lettering where they matter.

