[Integrations](https://spiral.ai/integrations) › [Claude Code](https://spiral.ai/integrations/claude-code) › [Seedream 5.5 Text to Image](https://spiral.ai/integrations/claude-code/seedream-5-5-text-to-image)

# How to Use Seedream 5.5 Text to Image in Claude Code

Seedream 5.5 Text to Image creates photographic scenes, illustrated assets, and lettering from a written brief. Unlike Seedream 5.5 Image Edit, it starts from text rather than reference images.

|  |  |
| --- | --- |
| Model | Seedream 5.5 Text to Image |
| Available through | fal |
| Category | Image |
| Price | $0.05265 per run at the default inputs. $0.05265 per unit of `num_images`. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Seedream 5.5 Text to Image in Claude Code

- Use Seedream 5.5 Text to Image to create a 2048 × 2048 transparent PNG for the project's empty inventory screen: a hand-painted canvas satchel with visible stitching, centered, no lettering. Read the existing design notes for the palette.
- Use Seedream 5.5 Text to Image to create a 2048 × 1152 editorial still life for the article page: a clear glass pitcher beside a folded linen cloth, soft window light from the left, open space on the right, no text.
- Use Seedream 5.5 Text to Image to draft a 1536 × 2048 illustrated poster for the project demo. Show a small neighborhood bakery at dawn, with the exact headline 'Fresh each morning' above the storefront and no other copy.
- Generate a product photo with Seedream 5.5 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 5.5 Text to Image.

## How to set up Seedream 5.5 Text to Image in Claude Code

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

### Use Spiral's MCP server

1. **Add the hosted server**: This adds Spiral to the current project. Add `--scope user` to use it in every project.

```bash
claude mcp add --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `claude`, type `/mcp`, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.

### Use the Spiral skill

1. **Send Claude Code 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 5.5 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": "bytedance/seedream/v5.5/text-to-image",
    "input": {
      "prompt": "Vibrant editorial of a model in contemporary fashion fused with West African textile patterns and beadwork, Campbell Addy bold aesthetic, saturated palette,…"
    }
  }'
```

Then paste one of the prompts above: Claude Code finds Seedream 5.5 Text to Image on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/claude-code

## Seedream 5.5 Text to Image tools and prices

- [Seedream 5.5 Text to Image](https://spiral.ai/tools/fal/bytedance/seedream/v5.5/text-to-image) (fal): $0.05265 per run at the default inputs. $0.05265 per unit of `num_images`.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| image_size |  | auto_2K | The size of the generated image. Total pixels must be between 921600 and 4624220, with aspect ratio between 1/16 and 16. |
| num_images | 1 to 6 | 1 | Number of separate model generations to run with the prompt. |
| output_format | jpeg, png | png | The file format of the generated image. |
| watermark |  | false | Whether to add the provider's visible watermark. |
| background | auto, opaque, transparent | auto | `auto` lets the model choose from the prompt and output format. `transparent` returns an RGBA image and requires `output_format=png`. |

## What can you do with Seedream 5.5 Text to Image in Claude Code?

Create project artwork, character assets, and illustrated content while working on the code that uses them. Give Seedream 5.5 a concrete visual brief and dimensions that match the intended placement.

### Transparent sticker artwork

Create a sticker concept from a written description, or refine supplied sticker artwork. Ask for a transparent PNG so the design can sit over different backgrounds.

### Game character assets

Develop character artwork from a brief or an existing character reference. Request an isolated pose with a transparent background for use in a game layout.

### Editorial photography concepts

Explore a portrait or still-life idea from text, or adjust a supplied image. Specify the light direction, visible materials, camera angle, and intended mood.

### Posters with readable copy

Draft a poster from a written brief or revise existing poster artwork. Supply the exact English or Chinese wording, describe its placement, and check the finished lettering.

### Product scene concepts

Use text to explore a proposed product scene, including glass, fabric, or metal surfaces. Use a product reference when the task starts from an existing product image.

### Interior design studies

Sketch a room concept from a description, or revise furnishings in a supplied room image. Name the materials, lighting, and furniture placement to explore.

### Illustrated information layouts

Draft an illustrated information sheet from text, or refine an existing layout. Provide approved captions and review every label before sharing the result.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Claude Code guides](https://spiral.ai/integrations/claude-code)

## Seedream 5.5 Text to Image in other agents

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

## More Claude Code guides

- [Seedream 5.5 Layerize](https://spiral.ai/integrations/claude-code/seedream-5-5-layerize)
- [Smart Resize](https://spiral.ai/integrations/claude-code/smart-resize)
- [Seedream 5.5 Image Edit](https://spiral.ai/integrations/claude-code/seedream-5-5-image-edit)
- [Solarize](https://spiral.ai/integrations/claude-code/solarize)
- [Seedream 5.0 Pro Text to Image](https://spiral.ai/integrations/claude-code/seedream-5-0-pro-text-to-image)
- [Texture Transform](https://spiral.ai/integrations/claude-code/texture-transform)

## Questions about Seedream 5.5 Text to Image in Claude Code

**Can Claude Code use Seedream 5.5 Text to Image?**

Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Seedream 5.5 Text to Image like any built-in tool.

**How much does Seedream 5.5 Text to Image cost in Claude Code?**

$0.05265 per run at the default inputs. $0.05265 per unit of `num_images`. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.

**Do I need a fal account to use Seedream 5.5 Text to Image in Claude Code?**

No. Spiral runs Seedream 5.5 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 5.5 Text to Image in Claude Code?**

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

**Does Claude Code wait while Seedream 5.5 Text to Image runs?**

Seedream 5.5 Text to Image runs in the background. Claude Code starts the run, checks on it and gives you the image when it's ready.

**What is Seedream 5.5 good at?**

Seedream 5.5 is useful for photographic scenes where lighting, materials, and skin texture matter. Its documented Chinese and English text rendering also makes posters and illustrated information layouts worth trying.

**How large can Seedream 5.5 images be?**

Images must contain 921,600 to 4,624,220 pixels, with a width-to-height ratio between 1:16 and 16:1. A 2048 × 2048 square fits; a 4096 × 4096 square exceeds the limit.

**Can Seedream 5.5 create transparent assets?**

Yes. Seedream 5.5 supports full and partial transparency, which is useful for stickers, character art, and elements placed over other artwork. Request PNG output to retain transparency.

**Can Seedream 5.5 render Chinese and English text?**

ByteDance documents text-rendering evaluations in both languages, including densely arranged small text. For a poster or infographic, provide the exact wording and review the rendered copy before using it.

**Why does Seedream 5.5 sometimes miss details in a brief?**

BytePlus warns that very long prompts can scatter information and cause missing elements. Keep English prompts under its recommended 600 words and put the essential subject, composition, and constraints first.

