How to Use HunyuanImage 2.1 in Codex
HunyuanImage 2.1 turns detailed text descriptions into 2K images for illustrations, photographic concepts, and poster drafts. It supports Chinese and English prompts, with an optional refiner to improve clarity and reduce artifacts.
Prompts to try with HunyuanImage 2.1 in Codex
Copy an example into Codex, or ask in your own words.
Read the homepage copy and styles, then use HunyuanImage 2.1 to generate 2560 × 1536 header artwork: a ceramic workshop in morning light, pottery on the right, open wall space on the left.
Use HunyuanImage 2.1 to make a 2048 × 2048 editorial illustration for the budgeting article in this project: three labeled jars on a kitchen table, restrained colors, overhead composition.
Read the game's character brief and use HunyuanImage 2.1 for a 2048 × 2048 concept illustration. Describe the clothing, pose, expression, and setting explicitly, and enable refinement.
Use HunyuanImage 2.1 to create 2048 × 2048 abstract cover artwork for the audio demo: interlocking paper circles, directional shadows, navy and orange. Match the palette values in the project.
Read the Chinese landing-page copy and write a detailed Chinese scene prompt for HunyuanImage 2.1. Generate 2560 × 1536 artwork with the subject on the right and space for the heading on the left.
How to set up HunyuanImage 2.1 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 HunyuanImage 2.1
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/hunyuan-image/v2.1/text-to-image", "input": { "prompt": "A cute, cartoon-style anthropomorphic penguin plush toy, standing in a painting studio, wearing a red knitted scarf and beret." } }'
Then paste one of the prompts above: Codex finds HunyuanImage 2.1 on Spiral, shows the price and runs it.
HunyuanImage 2.1 providers and prices
Spiral runs HunyuanImage 2.1 through fal. Open a card for today's price, with every fee included.
$0.13 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
HunyuanImage 2.1 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 guide the image generation away from certain concepts. | |
| Number of images | 1 to 4 | 1 | The number of images to generate. |
| Number of inference steps | 1 to 50 | 28 | Number of denoising steps. |
| Guidance scale | 1 to 20 | 3.5 | Controls how much the model adheres to the prompt. Higher values mean stricter adherence. |
| Seed | a whole number | Random seed for reproducible results. If None, a random seed is used. | |
| Use reprompt | on or off | on | Enable prompt enhancement for potentially better results. |
| Use refiner | on or off | off | Enable the refiner model for improved image quality. |
| Output format | jpeg or png | png | The format of the generated image. |
Every API field of Hunyuan Image is on its tool page: open its card above.
What can you do with HunyuanImage 2.1 in Codex?
Create website artwork and illustrative assets from the project's written requirements with HunyuanImage 2.1. Have the coding agent turn layout constraints into detailed scene descriptions and prepare the selected artwork for the page.
Article illustrations
Turn an article's central idea into a 2K illustration. Specify a concrete visual metaphor, the main subject, and space for a headline added during layout.
Photographic campaign concepts
Explore a proposed scene before arranging a shoot. Describe the setting, camera viewpoint, materials, and light so a reviewer can judge the direction.
Poster drafts
Develop poster concepts with a short headline integrated into the artwork. Review the generated lettering before using the design.
Website artwork
Create landscape artwork for a page header from a written design brief. Define the focal point and leave a quiet area for interface text.
Character concept illustrations
Explore a character's clothing, expression, pose, and setting through detailed descriptions. Use the results as concepts for an illustrator to assess.
Abstract cover artwork
Develop cover concepts built from geometric shapes, materials, and a specified palette. Generate square artwork at 2048 × 2048.
Chinese-language creative briefs
Write the scene directly in Chinese to develop illustrations or campaign concepts. Specify visual details in the original brief rather than translating it first.
More on HunyuanImage 2.1 and Codex
Overview
HunyuanImage 2.1 in other agents
Questions about HunyuanImage 2.1 in Codex
Can Codex use HunyuanImage 2.1?
Yes. Add Spiral to Codex as an MCP server, and Codex can find and run HunyuanImage 2.1 like any built-in tool.
How much does HunyuanImage 2.1 cost in Codex?
$0.13 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 HunyuanImage 2.1 in Codex?
No. Spiral runs HunyuanImage 2.1 on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up HunyuanImage 2.1 in Codex?
About two minutes: add the hosted server, then sign in.
Does Codex wait while HunyuanImage 2.1 runs?
HunyuanImage 2.1 runs in the background. Codex starts the run, checks on it and gives you the image when it's ready.
What is HunyuanImage 2.1 useful for?
Use it for photographic concepts, digital illustrations, abstract artwork, and poster drafts with text. Tencent demonstrates these styles with prompt enhancement enabled.
What resolution should I generate?
Generate at the documented 2K sizes, such as 2048 × 2048 for square artwork or 2560 × 1536 for landscape compositions. Tencent warns that 1K generation produces artifacts.
Can I write prompts in Chinese?
Yes. HunyuanImage 2.1 natively supports both Chinese and English prompts.
How should I write a useful prompt?
Describe the subject, its appearance, placement, surroundings, lighting, and visual style. Favor a precise scene description over a short string of adjectives.
When should I enable the refiner?
Enable it when clarity and artifact reduction matter, such as when preparing a selected concept for review. Tencent describes it as a second stage that improves image quality and clarity.
Start using HunyuanImage 2.1 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


