How to Use Qwen Image 3 Edit in OpenClaw
Qwen Image 3 Edit changes existing images while preserving details such as faces and identity. Unlike Qwen Image 3 Text to Image, it works from one to three reference images, making it useful for portrait changes, annotations, and artwork repairs.
Prompts to try with Qwen Image 3 Edit in OpenClaw
Copy an example into OpenClaw, or ask in your own words.
For each approved product image supplied with a campaign, use Qwen Image 3 Edit to change the setting to match the campaign's season. Preserve the product's shape, color, and visible label.
When an approved lesson photograph arrives, use Qwen Image 3 Edit to add the supplied labels and arrows. Preserve the photographed subject and flag labels that overlap important details.
Every Monday at 9am: remove the background from the photo I attach with Qwen Image 3 Edit and give me a transparent PNG.
Use Qwen Image 3 Edit to clean up these product shots so they sit on pure white.
Edit this image with Qwen Image 3 Edit: keep the subject, swap the background for a sunlit studio.
How to set up Qwen Image 3 Edit in OpenClaw
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send OpenClaw this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use Spiral's MCP server
- Add the server
On the machine that runs OpenClaw's Gateway:
openclaw mcp add spiral \ --url https://api.spiral.ai/mcp \ --transport streamable-http \ --auth oauth
- Sign in
In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.
openclaw mcp login spiral
- Reload and check
A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.
openclaw mcp reload openclaw mcp doctor spiral --probe
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Qwen Image 3 Edit
One request; the result comes back by polling or a webhook.
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": "alibaba/qwen-image-3/edit", "input": { "prompt": "Change the wolves into extremely realistic small puppies of different colors.", "image_urls": [ "<image_urls>" ] } }'
Then paste one of the prompts above: OpenClaw finds Qwen Image 3 Edit on Spiral, shows the price and runs it.
Qwen Image 3 Edit providers and prices
Spiral runs Qwen Image 3 Edit through fal. Open a card for today's price, with every fee included.
Up to $0.0975 per run at the default inputs. $0.0975 per unit of num_images.
Settings you can ask for
Qwen Image 3 Edit works from your prompt and image URLs. Ask OpenClaw for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Negative prompt | what to leave out, in words | Content to avoid in the generated image. Max 500 characters. | |
| Enable prompt expansion | on or off | on | Enable automatic LLM prompt rewriting for better results. |
| Seed | a whole number | Random seed for reproducibility (0-2147483647). | |
| Number of images | 1 to 6 | 1 | The number of images to generate. |
| Output format | jpeg, png, or webp | png | The format of the generated image. |
Every API field of Qwen Image 3 Image Editing is on its tool page: open its card above.
What can you do with Qwen Image 3 Edit in OpenClaw?
Prepare recurring visual drafts such as weekly announcements, educational graphics, and updated promotional images with Qwen Image 3. Have the scheduled agent use approved content and flag text or visual details that need review.
Portrait setting changes
Change the setting of a supplied portrait while asking to preserve the person's facial features and identity.
Product image revisions
Revise a supplied product image with a different setting or composition, explicitly identifying the product details that must stay unchanged.
Annotated learning materials
Add handwritten comments, underlines, circles, or explanatory labels to a supplied page or photograph.
Damaged artwork repair drafts
Propose repairs for missing or damaged areas in a supplied painting while following the surrounding brushwork and composition.
More on Qwen Image 3 Edit and OpenClaw
Overview
Qwen Image 3 Edit in other agents
Questions about Qwen Image 3 Edit in OpenClaw
Can OpenClaw use Qwen Image 3 Edit?
Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Qwen Image 3 Edit like any built-in tool.
How much does Qwen Image 3 Edit cost in OpenClaw?
Up to $0.0975 per run at the default inputs. $0.0975 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 OpenClaw plan is separate.
Do I need a fal account to use Qwen Image 3 Edit in OpenClaw?
No. Spiral runs Qwen Image 3 Edit on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Qwen Image 3 Edit in OpenClaw?
About two minutes: add the server, then sign in, then reload and check.
Does OpenClaw wait while Qwen Image 3 Edit runs?
Qwen Image 3 Edit runs in the background. OpenClaw starts the run, checks on it and gives you the image when it's ready.
What is Qwen Image 3 especially useful for?
Text-heavy visuals such as posters, menus, infographics, storyboards, and interface mockups. Its typography and layout capabilities make it a useful choice when words and illustrations need to share the same image.
Can Qwen Image 3 put readable text inside an image?
Yes. Qwen reports rendering text as small as 10 pixels across 12 languages and multiple fonts; check the actual wording and legibility at the intended display size before publishing.
Should I write prompts in English or Chinese?
Both English and Chinese are explicitly supported by the served endpoints. State the desired language for text inside the image and supply the exact wording you want.
Can Qwen Image 3 produce a 4K image?
The documented maximum is 2048×2048. Plan the composition for that output size, especially when it contains small labels or several panels.
How long can a Qwen Image 3 prompt be?
The served endpoints limit prompts to 5,000 characters. Keep the required text, layout, and visual instructions within that limit.
Start using Qwen Image 3 Edit in OpenClaw
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into OpenClaw:
set up https://spiral.ai/SKILL.md



