---
title: "Use Seedream in OpenClaw via RunAPI — Image API Guide"
url: "https://runapi.ai/openclaw-seedream.md"
canonical: "https://runapi.ai/openclaw-seedream"
locale: "en"
model: "seedream"
---

# Use Seedream in OpenClaw.

Seedream is Bytedance's image generation model with strong typography rendering and up to 4K output. OpenClaw agents call it through the same RunAPI key and endpoint used for chat — no extra skills or provider accounts.

## API example

```bash
curl -X POST https://runapi.ai/api/v1/task/text_to_image \
  -H "Authorization: Bearer $RUNAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedream-4.5-text-to-image",
    "prompt": "A premium coffee bag on a marble countertop, warm morning light, bold serif text FRESH ROAST, 4K product photography"
  }'

```

### Response

```json
{
  "task_id": "tsk_abc123",
  "status": "pending",
  "model": "seedream-4.5-text-to-image"
}

```

## How it works

1. **Configure RunAPI** — If you already set up RunAPI in OpenClaw for chat, you are done. The same RUNAPI_API_KEY and /v1 endpoint handle image generation. If not, paste the setup prompt from the OpenClaw guide or export the key in your shell.
2. **Call Seedream** — Send a request to the text_to_image endpoint with model set to seedream-4.5-text-to-image. Include a text prompt describing the image. RunAPI returns a task ID immediately.
3. **Get the result** — Poll the task status endpoint with the returned task ID. When the status changes to completed, the response includes the generated image URL. RunAPI SDKs handle polling automatically.

## Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| `model` | `string` | Required. seedream-4.5-text-to-image, seedream-4.5-edit, seedream-5-lite-text-to-image. |
| `prompt` | `string` | Text description of the desired image. |
| `size` | `string` | Optional. Output dimensions. Supports up to 4K. |
| `image_url` | `string` | Source image for editing mode. |

## FAQ

### Can I use Seedream in OpenClaw?

Yes. Configure RunAPI as an OpenAI-compatible provider in OpenClaw, then call the text_to_image endpoint with model set to seedream-4.5-text-to-image. The same API key handles both chat and image generation.

### Do I need a separate API key for Seedream?

No. The same RUNAPI_API_KEY you configured for chat also calls Seedream and every other image model in the RunAPI catalog. One key, one billing account.

### Is Seedream async or sync?

Async. RunAPI returns a task ID on the first call. Poll the task status endpoint until the status is completed, then retrieve the image URL from the response. SDKs and the CLI handle polling automatically.

### What does Seedream cost?

Seedream uses per-generation pricing. Check the RunAPI pricing page for current rates. Failed generations are not charged.

### Can Seedream maintain character consistency across multiple images?

Yes. Seedream handles consistent character generation well when you describe the character in detail across prompts. It maintains facial features, body proportions, and clothing style across a batch of images, making it suitable for creating brand ambassador series or product model sequences.

### Does Seedream work for product photography?

Yes. Seedream produces photorealistic product shots with accurate material textures, lighting, and spatial relationships. It is particularly strong at lifestyle shots where products appear in realistic settings with proper shadows and reflections.

### What is the difference between Seedream 4.5 and Seedream 5 Lite?

Seedream 4.5 is the full model with 4K output and the highest fidelity. Seedream 5 Lite is a faster, cheaper variant optimized for speed at standard resolution. Both share the same text_to_image endpoint -- set the model slug to seedream-5-lite-text-to-image for faster generation or seedream-4.5-text-to-image for maximum quality.


## Links

- [OpenClaw setup guide →](https://runapi.ai/openclaw)
- [Seedream models →](https://runapi.ai/models/seedream)
- [Model catalog](https://runapi.ai/models)
- [API docs](https://runapi.ai/docs)