Spiral gives your agent every tool with one account. Browse the tools →

Factory Droid · Image

How to Use Qwen Image Edit Plus LoRA in Factory Droid

Qwen Image Edit Plus LoRA edits portraits, product shots, and image text using reference images. It adds LoRA customization to Qwen Image Edit Plus, which uses Qwen-Image-Edit-2509.

Prompts to try with Qwen Image Edit Plus LoRA in Factory Droid

Copy an example into Factory Droid, or ask in your own words.

Use Qwen Image Edit Plus LoRA to turn the product photograph in public/images into a 1280 by 720 campaign image. Keep the product shape and printed label unchanged, add a simple studio setting, and save the result separately for review.

Qwen Image Edit Plus LoRAFactory Droid
Try asking
  • Find the promotional poster in this project and use Qwen Image Edit Plus LoRA to replace its headline with "Built for everyday use". Preserve the existing typeface, placement, background, and product image.

  • Use Qwen Image Edit Plus LoRA on the team portrait asset to create a watercolor illustration. Preserve the person's facial features and pose, use the project's supplied illustration LoRA, and save a separate draft.

  • Use Qwen Image Edit Plus LoRA with the project's person, product, and location reference images. Place the person on the left holding the product, use the location as the background, and create a 1280 by 720 draft.

  • Use Qwen Image Edit Plus LoRA to remove the distracting sign from the background of the project's hero photograph. Keep the subject, framing, lighting, and nearby objects unchanged, then show the original and edited images for review.

How to set up Qwen Image Edit Plus LoRA in Factory Droid

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

Use Spiral's MCP server

  1. Add the server

    Droid saves it to your user config, ~/.factory/mcp.json, so it works in every project.

    droid mcp add spiral https://api.spiral.ai/mcp --type http
  2. Sign in

    Start droid, type /mcp, select spiral and authenticate it. Sign in to Spiral in the browser and click Authorize. No API key.

  3. Check it

    Spiral shows as connected. needs authentication means the sign-in did not finish: run /mcp again.

    droid mcp list

Use the Spiral skill

  1. Send Factory Droid 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.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run Qwen Image Edit Plus LoRA

    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": "fal-ai/qwen-image-edit-plus-lora",
        "input": {
          "prompt": "Close shot of a woman standing in next to this car on this highway",
          "image_urls": [
            "<image_urls>"
          ]
        }
      }'

Then paste one of the prompts above: Factory Droid finds Qwen Image Edit Plus LoRA on Spiral, shows the price and runs it.

Qwen Image Edit Plus LoRA providers and prices

Spiral runs Qwen Image Edit Plus LoRA through fal. Open a card for today's price, with every fee included.

falImage
Qwen Image Edit Plus Lora
fal-ai/qwen-image-edit-plus-lora

Settings you can ask for

Qwen Image Edit Plus LoRA works from your prompt and image URLs. Ask Factory Droid for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Number of inference steps2 to 5028

The number of inference steps to perform.

Seeda whole number

The same seed and the same prompt given to the same version of the model

will output the same image every time.

Guidance scale0 to 204

The CFG (Classifier Free Guidance) scale is a measure of how close you want

the model to stick to your prompt when looking for a related image to show you.

Number of images1 to 41

The number of images to generate.

Output formatjpeg or pngpng

The format of the generated image.

Negative promptwhat to leave out, in words

The negative prompt for the generation

Accelerationnone or regularregular

Acceleration level for image generation. Options: 'none', 'regular'. Higher acceleration increases speed. 'regular' balances speed and quality.

Every API field of Qwen Image Edit Plus Lora is on its tool page: open its card above.

What can you do with Qwen Image Edit Plus LoRA in Factory Droid?

Create revised product graphics, portraits, and promotional images from assets already in your project. A coding agent can prepare focused edit instructions for Qwen Image Edit Plus LoRA and place reviewed results into the application.

Product poster drafts

Turn an existing product photograph into a campaign poster. Ask Qwen Image Edit Plus LoRA to preserve the product's shape and label while changing the surrounding composition.

English and Chinese poster edits

Replace a headline in an existing poster with approved English or Chinese copy. Specify the exact text and which parts of the layout should remain unchanged.

Portrait style studies

Explore illustrated treatments of a supplied portrait while asking to retain the person's recognizable facial features. Compare each result against the reference.

Portrait pose concepts

Use a portrait as the starting point for a new pose. Describe the desired body position and ask to preserve the face, clothing, and scene.

Reference-based scene compositions

Combine a person, product, and scene from up to three references into a draft composition. State which image supplies each element and where it belongs.

Targeted photo cleanup

Remove a distracting object from an existing image or replace one visible element. Identify the location and ask to preserve nearby objects, lighting, and framing.

Typography treatments

Explore different typefaces, lettering colors, or material finishes within an existing graphic. Keep the wording fixed so reviewers can compare the visual treatment.

Questions about Qwen Image Edit Plus LoRA in Factory Droid

Can Factory Droid use Qwen Image Edit Plus LoRA?

Yes. Add Spiral to Factory Droid as an MCP server, and Factory Droid can find and run Qwen Image Edit Plus LoRA like any built-in tool.

How much does Qwen Image Edit Plus LoRA cost in Factory Droid?

Up to $0.0455 per run at the default inputs. $0.0455 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 Factory Droid plan is separate.

Do I need a fal account to use Qwen Image Edit Plus LoRA in Factory Droid?

No. Spiral runs Qwen Image Edit Plus LoRA 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 Edit Plus LoRA in Factory Droid?

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

Does Factory Droid wait while Qwen Image Edit Plus LoRA runs?

Qwen Image Edit Plus LoRA runs in the background. Factory Droid starts the run, checks on it and gives you the image when it's ready.

What is Qwen Image Edit Plus LoRA good at?

Use it to turn product photographs into posters or revise lettering inside an existing image. Text edits can change the typeface, color, or material appearance.

How many reference images should I use?

Start with one to three images, the range Qwen recommends for best results. Give each reference a clear role, such as the person, product, or scene.

Can it change a portrait without losing the person's identity?

Preserving facial identity during style and pose changes is a documented strength. Treat that as an editing goal rather than a guarantee, and compare the face with the original before using the result.

Which languages can it edit inside images?

Qwen documents English and Chinese text editing. Put the exact replacement wording in quotation marks and proofread the rendered result.

Can I request a specific output size?

Yes, custom width and height are supported, with 1280 by 720 pixels shown in the documentation. That example is not a stated maximum resolution.

Get started

Start using Qwen Image Edit Plus LoRA in Factory Droid

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into Factory Droid:

Set up Factory Droid

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options