How to Use FLUX 3 Klein Text to Image in Perplexity
FLUX 3 Klein Text to Image creates images from detailed scene descriptions, with layout boxes to guide composition. It uses the distilled model for generation; FLUX 3 Image Klein Base targets fine-tuning and research.
Prompts to try with FLUX 3 Klein Text to Image in Perplexity
Copy an example into Perplexity, or ask in your own words.
Use FLUX 3 Klein Text to Image to create a 1536 by 1024 editorial image about repairing household objects. Show a wooden workbench, a carefully mended ceramic bowl, and a spool of thread in soft morning window light. Use an overhead view and leave clear space in the upper left.
Use FLUX 3 Klein Text to Image to create a 1024 by 1536 podcast cover concept about urban gardening. Show one tomato plant growing from a weathered rooftop planter, with distant buildings in early evening light. Keep the top quarter simple for a title added later.
Use FLUX 3 Klein Text to Image to create a 1024 by 1024 photograph of an imagined unbranded ceramic coffee cup on a dark wooden table. Show subtle glaze texture, steam rising against the background, and soft light from the left. Frame it close at table height.
Use FLUX 3 Klein Text to Image to create a 1536 by 1024 scene with a red bicycle on the left and a small stone cottage on the right. Use layout boxes to guide those positions, with a broad meadow between them, overcast daylight, and an eye-level camera.
Use FLUX 3 Klein Text to Image to create a 1024 by 1536 poster concept showing a lighthouse in heavy rain. Put the exact words "NIGHT WATCH" near the top in large lettering. Show wet stone, a narrow beam of light, and dark ocean waves, then check the generated title for spelling.
How to set up FLUX 3 Klein Text to Image in Perplexity
Pick the way that suits you. Each takes about two minutes.
Use the Perplexity connector
- Add a remote connector
In Perplexity, open Plugins in the sidebar (or Customize › Connectors if you don't see Plugins yet). Choose Add custom › Add MCP connector, then Remote. Name it Spiral and paste this MCP server URL:
https://api.spiral.ai/mcp
- Sign in to Spiral and approve
Select the Spiral card on the Plugins page to start sign-in. Spiral opens: sign in, pick the organization and click Authorize. No API key.
Use the Spiral skill
- Send Perplexity 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 FLUX 3 Klein 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": "blackforestlabs/flux-3/klein/text-to-image", "input": { "prompt": "A red fox standing in fresh snow at sunrise, its breath visible in the cold air. Soft golden light rakes across the snowfield from the left, pine forest softly…" } }'
Then paste one of the prompts above: Perplexity finds FLUX 3 Klein Text to Image on Spiral, shows the price and runs it.
FLUX 3 Klein Text to Image providers and prices
Spiral runs FLUX 3 Klein Text to Image through fal. Open a card for today's price, with every fee included.
$0.0117 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
FLUX 3 Klein Text to Image works from your prompt. Ask Perplexity for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Enable prompt expansion | on or off | on | If set to true, the prompt is expanded into a detailed caption (grounded in the reference images when editing) before 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. |
Every API field of FLUX 3 Klein Text to Image is on its tool page: open its card above.
What can you do with FLUX 3 Klein Text to Image in Perplexity?
Turn a creative brief into cover artwork, editorial scenes, or campaign concepts. Describe the composition in conversation, including lighting, materials, and where each subject belongs.
Website header artwork
Generate a wide scene from a written brief, placing the subject to one side and requesting clear space for a headline added in the page.
Editorial illustrations
Translate an article's central idea into a visual metaphor. Specify the scene, materials, lighting, and framing so the image supports a particular point.
Campaign concept boards
Explore different scenes for a campaign before choosing a direction. Give each concept a concrete subject, setting, palette, and camera view.
Book and podcast cover concepts
Create cover artwork with deliberate subject placement and room for titles. Treat generated lettering as a draft that needs proofreading.
Product staging concepts
Describe an imagined product scene with specific surfaces, materials, shadows, and camera placement. Use the results to discuss art direction before a photo shoot.
Social post artwork
Create square or portrait artwork for a defined message. Request a clear focal subject and reserve space for copy added after generation.
More on FLUX 3 Klein Text to Image and Perplexity
Overview
FLUX 3 Klein Text to Image in other agents
Questions about FLUX 3 Klein Text to Image in Perplexity
Can Perplexity use FLUX 3 Klein Text to Image?
Yes. Add Spiral to Perplexity as an MCP server, and Perplexity can find and run FLUX 3 Klein Text to Image like any built-in tool.
How much does FLUX 3 Klein Text to Image cost in Perplexity?
$0.0117 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 Perplexity plan is separate.
Do I need a fal account to use FLUX 3 Klein Text to Image in Perplexity?
No. Spiral runs FLUX 3 Klein 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 FLUX 3 Klein Text to Image in Perplexity?
About two minutes: add a remote connector, then sign in to Spiral and approve.
Does Perplexity wait while FLUX 3 Klein Text to Image runs?
FLUX 3 Klein Text to Image runs in the background. Perplexity starts the run, checks on it and gives you the image when it's ready.
What is FLUX 3 Klein useful for?
Use it to turn a written brief into an image and guide where subjects appear. Suggested applications include editorial illustrations, campaign concepts, and website artwork.
How large can FLUX 3 Klein images be?
Each side can be 256 to 4096 pixels, with native 4K generation supported. Choose dimensions that match the intended placement, such as a wide header or a portrait cover.
Why do short prompts sometimes look generic?
FLUX 3 Klein was trained on full scene captions, and the model card warns that short prompts produce generic output. Describe the framing, subject, background, and lighting instead of relying on a few keywords.
Should I keep prompt expansion enabled?
Yes, that is the maker's recommendation for ordinary text-to-image and layout requests. Prompt expansion turns the request into the detailed caption the model expects.
Can FLUX 3 Klein place objects precisely?
Bounding boxes guide an object's position and scale. They are not hard boundaries, so leave room around important subjects and inspect the result before using a tight crop.
Start using FLUX 3 Klein Text to Image in Perplexity
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Perplexity:
set up https://spiral.ai/SKILL.md


