How to Use FLUX.2 Klein 4B LoRA in Gemini
FLUX.2 Klein 4B LoRA generates images from text with custom LoRA support for a learned visual style. It keeps the four-step approach of FLUX.2 Klein 4B while adding adaptation for recurring illustration work.
Prompts to try with FLUX.2 Klein 4B LoRA in Gemini
Copy an example into Gemini, or ask in your own words.
Use FLUX.2 Klein 4B LoRA with my selected style adapter to create a square newsletter cover, 1024 pixels on each side. Show a gardener planting a seed in an oversized teacup, with the subject centered and a simple background.
Generate a product photo with FLUX.2 Klein 4B LoRA: a matte black water bottle on wet slate, soft morning light, 1:1. Tell me the price first.
Make four logo concepts for a coffee brand called "Northline" with FLUX.2 Klein 4B LoRA.
Create a 16:9 hero image of a quiet mountain cabin at dusk with FLUX.2 Klein 4B LoRA.
Generate a 9:16 poster with FLUX.2 Klein 4B LoRA for a jazz night called "Blue Hour", deep navy and brass tones.
How to set up FLUX.2 Klein 4B LoRA in Gemini
Pick the way that suits you. Each takes about two minutes.
Use the Gemini connector
- Open Connected Apps
On your computer, go to gemini.google.com. At the bottom, click Settings › Connected Apps. If you don't see Connected Apps, click Personal Intelligence first, then Connected Apps.
- Add Spiral as a custom app
Under Custom apps, click Add a custom app and paste this MCP server URL:
https://api.spiral.ai/mcp
- Sign in to Spiral and approve
Follow the on-screen instructions. Spiral opens: sign in, pick the organization and click Authorize. No API key.
Use the Spiral skill
- Send Gemini 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.2 Klein 4B 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/flux-2/klein/4b/lora", "input": { "prompt": "Cheetah in pre-sprint crouch, muscles tensed, gazelle visible in distance, African savanna golden grass, dust particles in air, National Geographic wildlife…" } }'
Then paste one of the prompts above: Gemini finds FLUX.2 Klein 4B LoRA on Spiral, shows the price and runs it.
FLUX.2 Klein 4B LoRA providers and prices
Spiral runs FLUX.2 Klein 4B LoRA through fal. Open a card for today's price, with every fee included.
$0.013 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.2 Klein 4B LoRA works from your prompt. Ask Gemini for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | The seed to use for the generation. If not provided, a random seed will be used. | |
| Number of inference steps | 4 to 8 | 4 | The number of inference steps to perform. |
| 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.2 [klein] 4B LoRA · Text to Image is on its tool page: open its card above.
What can you do with FLUX.2 Klein 4B LoRA in Gemini?
Turn an idea described in conversation into an image draft for a post, presentation, or creative brief. Describe the scene, lighting, and framing in everyday language, then review the image against what you asked for.
Website artwork drafts
Generate a scene from a written website brief, leaving deliberate empty space for headings. Add the final typography in the page layout.
Editorial illustrations
Turn an article's central idea into a visual metaphor, such as an overflowing inbox for a story about distraction.
Product concept scenes
Explore an imagined product's materials, setting, and lighting from text before commissioning photography or building a physical prototype.
Social post artwork
Draft square scenes for social posts using a clear focal subject. Keep required wording outside the generated image.
Storyboard planning
Generate separate scene concepts from written shot descriptions to discuss framing and mood before a shoot.
Game item concepts
Describe individual objects such as potions, treasure chests, or tools to explore their appearance. Use a suitable style LoRA when a learned art treatment is required.
Illustration series with a learned style
Use a selected style LoRA to carry one learned appearance across different subjects, such as a series of illustrated newsletter covers.
More on FLUX.2 Klein 4B LoRA and Gemini
Overview
FLUX.2 Klein 4B LoRA in other agents
Questions about FLUX.2 Klein 4B LoRA in Gemini
Can Gemini use FLUX.2 Klein 4B LoRA?
Yes. Add Spiral to Gemini as an MCP server, and Gemini can find and run FLUX.2 Klein 4B LoRA like any built-in tool.
How much does FLUX.2 Klein 4B LoRA cost in Gemini?
$0.013 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 Gemini plan is separate.
Do I need a fal account to use FLUX.2 Klein 4B LoRA in Gemini?
No. Spiral runs FLUX.2 Klein 4B 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 FLUX.2 Klein 4B LoRA in Gemini?
About two minutes: open Connected Apps, then add Spiral as a custom app, then sign in to Spiral and approve.
Does Gemini wait while FLUX.2 Klein 4B LoRA runs?
FLUX.2 Klein 4B LoRA runs in the background. Gemini starts the run, checks on it and gives you the image when it's ready.
What is FLUX.2 Klein 4B useful for?
Use it to explore image ideas from written briefs, such as editorial illustrations, product concepts, and website artwork. Its distilled four-step design makes iterative visual work a sensible starting point.
How should I write a FLUX.2 Klein prompt?
Describe a complete scene in connected sentences: the subject, its surroundings, composition, and lighting. Klein does not automatically expand your prompt, so write the details you want to see.
How large can FLUX.2 Klein images be?
Black Forest Labs documents output from 64 by 64 pixels to 4 megapixels, with each dimension divisible by 16. A 1024 by 1024 image is a practical starting point for reviewing composition.
Should I use FLUX.2 Klein for factual diagrams?
Treat the result as an illustration draft. The model is not a source of factual information, so check structures, labels, and relationships against a reliable reference before publishing.
How many generation steps should I start with?
Start with four steps, the distilled model's intended generation approach. Compare the resulting composition with your brief before experimenting further.
Start using FLUX.2 Klein 4B LoRA in Gemini
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Gemini:
set up https://spiral.ai/SKILL.md


