OPENCLAW + 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.

one API key · text to image endpoint · async task polling
Generate a 4K product hero image using Seedream through RunAPI.

Requirements:
- Use the RunAPI text_to_image endpoint.
- Set model to seedream-4.5-text-to-image.
- Read the API key from RUNAPI_API_KEY. Do not hardcode the key.
- Poll the task status endpoint until the task completes.
- Return the generated image URL from the task response.
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"
  }'
{
  "task_id": "tsk_abc123",
  "status": "pending",
  "model": "seedream-4.5-text-to-image"
}
Copy the curl command to test seedream
HOW IT WORKS

Use Seedream in OpenClaw in three steps

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.

export RUNAPI_API_KEY=runapi_xxx
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.

text_to_image
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.

task_id: tsk_abc123
PARAMETERS

Seedream API 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.

What is Seedream on OpenClaw?

Seedream is ByteDance's image model that users describe as offering "unmatched value" with 4K-quality output and 94% text accuracy out of the box. It holds onto structure in complex prompts -- multiple objects, specific spatial relationships, detailed typography -- without losing coherence. OpenClaw agents call it through the RunAPI text_to_image endpoint with the same API key used for chat.

Seedream use cases

E-commerce product catalogs

Generate product lifestyle shots with accurate labels and pricing text baked into the image, ready for catalog pages without post-production text overlays.

Typography-heavy poster and event design

Create event posters, signage, and billboards where the text content is specified in the prompt and rendered at 94% accuracy or better.

Batch generation for brand campaigns

Generate consistent character or product series across dozens of images, maintaining the same brand ambassador appearance and house style throughout.

FAQ

Seedream + OpenClaw questions

OpenClaw general setup

Not configured yet? Start with the RunAPI setup guide for OpenClaw.

OpenClaw setup guide →

Seedream model catalog

See all Seedream variants, pricing, and API docs.

Seedream models →

Try Seedream in OpenClaw today.

Get a free RunAPI key, paste the prompt into OpenClaw, and start generating 4K images with Seedream.