How to Use Qwen Image 2512 in Codex
Use Qwen Image 2512 for portraits, detailed nature scenes, and artwork with lettering. Compared with Qwen Image, it improves human realism, natural textures, and text layout.
Prompts to try with Qwen Image 2512 in Codex
Copy an example into Codex, or ask in your own words.
Use Qwen Image 2512 to create a fictional gardener portrait for the demo site. Show a woman in her sixties beside a greenhouse, wearing a canvas apron, with natural skin texture and soft morning light.
Use Qwen Image 2512 to create a bookstore window concept for the localization demo. Put "New stories" on the left sign and "新故事" on the right sign, with dark lettering on pale paper.
Generate a product photo with Qwen Image 2512: a matte black water bottle on wet slate, soft morning light, 1:1. Tell me the price first. Save the result in ./assets.
Make four logo concepts for a coffee brand called "Northline" with Qwen Image 2512.
Create a 16:9 hero image of a quiet mountain cabin at dusk with Qwen Image 2512.
How to set up Qwen Image 2512 in Codex
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
codex mcp add spiral --url https://api.spiral.ai/mcp
- Sign in
Codex opens the browser: sign in to Spiral and click Authorize. No API key. codex mcp list then shows Spiral.
codex mcp login spiral
Use the Spiral skill
- Send Codex 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 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 2512
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-2512", "input": { "prompt": "Single red rose in a clear glass vase on white marble streaked with black and gold veins, harsh directional shadow, high contrast, editorial style, clean…" } }'
Then paste one of the prompts above: Codex finds Qwen Image 2512 on Spiral, shows the price and runs it.
Qwen Image 2512 providers and prices
Spiral runs Qwen Image 2512 through fal. Open a card for today's price, with every fee included.
$0.026 per megapixel. image_size presets count as 1 MP; custom sizes round up to whole megapixels. Billed on num_images, default 1.
Settings you can ask for
Qwen Image 2512 works from your prompt. Ask Codex for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Negative prompt | what to leave out, in words | The negative prompt to generate an image from. | |
| Number of inference steps | 1 to 50 | 28 | The number of inference steps to perform. |
| Guidance scale | 0 to 20 | 4 | The guidance scale to use for the image generation. |
| Seed | a whole number | The same seed and the same prompt given to the same version of the model will output the same image every time. | |
| Number of images | 1 to 4 | 1 | The number of images to generate. |
| Output format | jpeg, png, or webp | png | The format of the generated image. |
| Acceleration | none, regular, or high | regular | The acceleration level to use. |
Every API field of Qwen Image 2512 is on its tool page: open its card above.
What can you do with Qwen Image 2512 in Codex?
Create visual assets that match a project's content and art direction. Turn repository briefs into image prompts with explicit composition, style, and lettering.
Event poster concepts
Develop a poster with an exact headline, a short date line, and a clear visual theme. For Qwen Image Image to Image, supply an existing poster composition to rework.
English and Chinese storefront artwork
Explore shop signs and window displays with specified English or Chinese wording. For Qwen Image Image to Image, start with a storefront picture.
Illustrated cover studies
Explore an illustrated cover with a short title and a defined painting or anime style. For Qwen Image Image to Image, provide a starting cover or illustration.
Campaign art direction
Explore photographic, painted, or minimalist treatments for a campaign concept. For Qwen Image Image to Image, provide an existing campaign image to restyle.
Fictional portrait concepts
Create portraits from a written description of appearance, expression, clothing, and setting. Qwen Image 2512 improves human realism compared with Qwen Image.
Nature illustrations
Create landscape and wildlife scenes from a written brief. Qwen Image 2512 gives natural textures particular attention.
More on Qwen Image 2512 and Codex
Overview
Qwen Image 2512 in other agents
Questions about Qwen Image 2512 in Codex
Can Codex use Qwen Image 2512?
Yes. Add Spiral to Codex as an MCP server, and Codex can find and run Qwen Image 2512 like any built-in tool.
How much does Qwen Image 2512 cost in Codex?
$0.026 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. Billed on `num_images`, default 1. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Codex plan is separate.
Do I need a fal account to use Qwen Image 2512 in Codex?
No. Spiral runs Qwen Image 2512 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 2512 in Codex?
About two minutes: add the hosted server, then sign in.
Does Codex wait while Qwen Image 2512 runs?
Qwen Image 2512 runs in the background. Codex starts the run, checks on it and gives you the image when it's ready.
What is Qwen Image especially useful for?
Artwork that combines a scene with readable lettering, such as event posters, storefront concepts, and illustrated covers. English and Chinese text are documented strengths.
How should I prompt lettering?
Put the exact wording in double quotation marks. Specify where it belongs, its font style and color, and whether it appears on paper, a sign, clothing, or another surface.
Which languages should I start with?
English and Chinese are the best-documented starting points for visible text. Keep names and slogans in their original wording when writing your prompt.
Can Qwen Image make illustrations as well as photographs?
Yes. Qwen documents photographic scenes, impressionist painting, anime, and minimalist design, so name the intended medium explicitly.
What makes a useful visual prompt?
Describe the subject, its position, the artistic style, and the composition. For text-heavy artwork, assign each phrase a clear location instead of asking for a poster with unspecified writing.
Start using Qwen Image 2512 in Codex
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Codex:
set up https://spiral.ai/SKILL.md



