How to Use Kling Image 3.0 Text to Image in Codex
Kling Image 3.0 Text to Image creates portraits, product scenes, and illustrations from written descriptions. Unlike Kling Image 3.0 Edit, it can start without a source picture.
Prompts to try with Kling Image 3.0 Text to Image in Codex
Copy an example into Codex, or ask in your own words.
Read the homepage copy and use Kling Image 3.0 Text to Image to create a 2K landscape illustration of a ceramic workshop, with afternoon window light and open space on the left.
Read the game's character brief and use Kling Image 3.0 Text to Image to create a watercolor portrait of its lighthouse keeper, wearing a weathered yellow coat.
Use Kling Image 3.0 Text to Image to create a 2K cinematic concept for the game's harbor scene: eye-level framing, fishing boats, dawn fog, and muted green water.
Generate a product photo with Kling Image 3.0 Text to Image: 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 Kling Image 3.0 Text to Image.
How to set up Kling Image 3.0 Text to Image 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 Kling Image 3.0 Text to Image
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/kling-image/v3/text-to-image", "input": { "prompt": "Extremely realistic image of a scholar'\''s study filled with maps and curiosities, roaring fireplace, rain against round windows, stacks of handwritten journals,…" } }'
Then paste one of the prompts above: Codex finds Kling Image 3.0 Text to Image on Spiral, shows the price and runs it.
Kling Image 3.0 Text to Image providers and prices
Spiral runs Kling Image 3.0 Text to Image through fal. Open a card for today's price, with every fee included.
resolution: 1K (default) $0.0364, 2K $0.0364 per image. Billed on num_images, default 1.
Settings you can ask for
Kling Image 3.0 Text to Image 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 | Negative text prompt. It is recommended to supplement negative prompt information through negative sentences directly within positive prompts. | |
| Resolution | 1K or 2K | 1K | Image generation resolution. 1K: standard, 2K: high-res. |
| Number of images | 1 to 9 | 1 | Number of images to generate (1-9). |
| Aspect ratio | 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, or 21:9 | 16:9 | Aspect ratio of generated images. |
| Output format | jpeg, png, or webp | png | The format of the generated image. |
Every API field of Kling Image · Text to Image is on its tool page: open its card above.
What can you do with Kling Image 3.0 Text to Image in Codex?
Create artwork for a project's pages or revise existing visual assets with Kling Image 3.0. Use the project's content and design direction to write specific image briefs.
Product scene concepts
Explore a product's setting, lighting, and composition before planning a shoot.
Character concept art
Develop a character's clothing, appearance, and surroundings for an illustrated story.
Campaign art direction
Compare visual approaches by changing the palette, materials, framing, or lighting.
Film scene concepts
Explore a scene's camera angle, atmosphere, and composition before production.
Editorial artwork from a brief
Create an illustration from a written article concept, with a defined subject, mood, and composition.
Portrait concepts from text
Describe a fictional subject, wardrobe, setting, and lighting to explore a portrait without a source photo.
More on Kling Image 3.0 Text to Image and Codex
Overview
Kling Image 3.0 Text to Image in other agents
Questions about Kling Image 3.0 Text to Image in Codex
Can Codex use Kling Image 3.0 Text to Image?
Yes. Add Spiral to Codex as an MCP server, and Codex can find and run Kling Image 3.0 Text to Image like any built-in tool.
How much does Kling Image 3.0 Text to Image cost in Codex?
`resolution`: 1K (default) $0.0364, 2K $0.0364 per image. 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 Kling Image 3.0 Text to Image in Codex?
No. Spiral runs Kling Image 3.0 Text to Image on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Kling Image 3.0 Text to Image in Codex?
About two minutes: add the hosted server, then sign in.
Does Codex wait while Kling Image 3.0 Text to Image runs?
Kling Image 3.0 Text to Image runs in the background. Codex starts the run, checks on it and gives you the image when it's ready.
What is Kling Image 3.0 good for?
Use it for portraits, product scenes, cinematic concepts, and illustrations. Give each image a clear subject and visual direction.
How should I write a Kling Image 3.0 prompt?
Describe the subject, setting, composition, lighting, and style. Prioritize the details that matter most and remove conflicting instructions.
What is the maximum output resolution?
Kling Image 3.0 Text to Image and Kling Image 3.0 Edit support output up to 2K.
How long can a prompt be?
Both Kling Image 3.0 Text to Image and Kling Image 3.0 Edit accept up to 2,500 characters. Use that space for concrete visual details.
Where does Kling Image 3.0 need extra review?
Busy scenes can lose important objects or actions. Check their positions and relationships, then simplify the request around the most important subject.
Start using Kling Image 3.0 Text to Image 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


