Can I use Qwen 2 Image in OpenClaw?

Yes. OpenClaw supports custom OpenAI-compatible providers. Add RunAPI with baseUrl https://runapi.ai/v1 and your RUNAPI_API_KEY, then call the text_to_image endpoint with model set to qwen-2-text-to-image. The same provider handles chat and image generation.

How does Qwen 2 compare to other image models for Chinese-language prompts?

Qwen 2 Image has native multilingual support from Alibaba's Qwen architecture, so it understands Chinese prompts without translation. Other models often require English prompts for best results. If your workflow involves Chinese text or bilingual content, Qwen 2 is a strong choice.

Is Qwen 2 Image async or sync?

Async. The endpoint returns a task ID immediately. Poll the task status endpoint or use a webhook callback to know when the image is ready. RunAPI SDKs and the CLI handle polling automatically.

What does Qwen 2 Image cost on RunAPI?

Qwen 2 Image uses per-task billing. Check the RunAPI pricing page for current rates. There is no monthly subscription or minimum spend -- you pay only for completed generations.

OPENCLAW + QWEN 2 IMAGE

Use Qwen 2 Image in OpenClaw.

Qwen 2 Image is Alibaba's image generation and editing model. OpenClaw agents call it through the same RunAPI endpoint used for chat — send a prompt, get an image URL. Supports text-to-image, image editing, and image remixing through three model variants.

Get API Key Read the docs

one API key · text to image endpoint · async task polling

Use RunAPI to generate an image with Qwen 2 Image.

Requirements:
- Call the RunAPI text_to_image endpoint at https://runapi.ai/api/v1/task/text_to_image.
- Set the model to "qwen-2-text-to-image".
- Read the API key from the RUNAPI_API_KEY environment variable.
- The response returns a task_id. Poll the task status endpoint until the task completes, then retrieve the image URL from the output.
- For image editing, use model "qwen-2-edit-image" and include an image_url field.
- For remixing, use model "qwen-2-remix-image" and include an image_url field.

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": "qwen-2-text-to-image",
    "prompt": "A traditional Chinese ink painting of misty mountains at dawn, elegant brushwork"
  }'

{
  "task_id": "tsk_abc123",
  "status": "pending",
  "model": "qwen-2-text-to-image"
}

Copy the curl command to test qwen-2

HOW IT WORKS

Use Qwen 2 Image in OpenClaw in three steps

Configure RunAPI

Set your RunAPI API key as an environment variable. If you have not added RunAPI as an OpenClaw provider yet, follow the OpenClaw setup guide first.

export RUNAPI_API_KEY=runapi_xxx

Call Qwen 2 Image

Paste the prompt into OpenClaw or call the text_to_image endpoint directly. Set the model field to qwen-2-text-to-image for generation, qwen-2-edit-image for editing, or qwen-2-remix-image for remixing.

text_to_image

Get the result

The endpoint returns a task ID. Poll the task status endpoint until the status changes to completed, then read the image URL from the output. RunAPI SDKs handle polling automatically.

task_id: tsk_abc123

PARAMETERS

Qwen 2 Image API parameters

Parameter	Type	Description
`model`	`string`	Required. qwen-2-text-to-image, qwen-2-edit-image, or qwen-2-remix-image.
`prompt`	`string`	Text description or editing instruction.
`image_url`	`string`	Source image for edit or remix mode.
`size`	`string`	Optional. Output dimensions.

What is Qwen 2 Image on OpenClaw?

Qwen 2 Image is Alibaba's image model that covers generation, editing, and remixing through one API. It is strong at multilingual prompt understanding (especially Chinese and English), handles complex multi-object scenes well, and supports instruction-based editing where you describe what to change in natural language. OpenClaw agents call all three modes through the same RunAPI endpoint.

Qwen 2 Image use cases

Multilingual marketing campaigns

Generate images from prompts written in Chinese, English, or mixed-language text for bilingual marketing materials without translating prompts first.

Instruction-based image editing

Modify existing images by describing the change in plain language -- swap backgrounds, add objects, adjust lighting, or remove elements without opening an editor.

Fine-tuning open-weight models for specific domains

Use Qwen 2 Image outputs as training data or baselines when fine-tuning open-weight Qwen models for domain-specific image tasks like product catalogs or branded content.

FAQ

Qwen 2 Image + OpenClaw questions

OpenClaw general setup

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

OpenClaw setup guide →

Qwen 2 Image model catalog

See all Qwen 2 Image variants, pricing, and API docs.

Qwen 2 Image models →

Try Qwen 2 Image in OpenClaw today.

Get a free RunAPI key, paste the prompt into OpenClaw, and start generating.

Browse models →