How to Use FLUX.2 LoRA in Claude Code
Use FLUX.2 LoRA to generate images with a trained style, subject, or brand treatment. Unlike FLUX.2, it applies custom adapters to the underlying image model.
Prompts to try with FLUX.2 LoRA in Claude Code
Copy an example into Claude Code, or ask in your own words.
Generate a product photo with FLUX.2 LoRA: 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 FLUX.2 LoRA.
Create a 16:9 hero image of a quiet mountain cabin at dusk with FLUX.2 LoRA.
Generate a 9:16 poster with FLUX.2 LoRA for a jazz night called "Blue Hour", deep navy and brass tones.
Generate a flat illustration of a team planning session with FLUX.2 LoRA for our blog header, 16:9.
How to set up FLUX.2 LoRA in Claude Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
This adds Spiral to the current project. Add --scope user to use it in every project.
claude mcp add --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start claude, type /mcp, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.
Use the Spiral skill
- Send Claude Code 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 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/lora", "input": { "prompt": "Close shot a pianist plays in a luxurious room with tall windows overlooking a rainy metropolis. Shot with a 50mm lens at a side profile angle, soft tungsten…" } }'
Then paste one of the prompts above: Claude Code finds FLUX.2 LoRA on Spiral, shows the price and runs it.
FLUX.2 LoRA providers and prices
Spiral runs FLUX.2 LoRA through fal. Open a card for today's price, with every fee included.
$0.0273 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 LoRA works from your prompt. Ask Claude Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Guidance scale | 0 to 20 | 2.5 | Guidance Scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. |
| 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 50 | 28 | The number of inference steps to perform. |
| Number of images | 1 to 4 | 1 | The number of images to generate. |
| Acceleration | none, regular, or high | regular | The acceleration level to use for the image generation. |
| Enable prompt expansion | on or off | off | If set to true, the prompt will be expanded for better results. |
| Output format | jpeg, png, or webp | png | The format of the generated image. |
Every API field of FLUX 2 Lora · Text to Image is on its tool page: open its card above.
What can you do with FLUX.2 LoRA in Claude Code?
Create product imagery and visual design concepts alongside the project you are building. Have the agent turn project requirements into concrete image briefs with explicit composition, colors, and text.
Product concept photography
Create product concepts from a written brief, with specific materials, camera angles, and lighting. Explore packaging or industrial design before arranging a shoot.
Editorial cover concepts
Develop cover images with a clear focal subject and a short, explicitly quoted headline. Specify where the headline sits relative to the subject.
Interface design concepts
Create visual concepts for app screens with named sections, clear placement instructions, and exact button text. Use the image to discuss layout and art direction.
Explanatory posters
Turn a short explanation into a poster with a title, a few labeled sections, and a specified illustration style. Supply every label you want rendered.
More on FLUX.2 LoRA and Claude Code
Overview
FLUX.2 LoRA in other agents
Questions about FLUX.2 LoRA in Claude Code
Can Claude Code use FLUX.2 LoRA?
Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run FLUX.2 LoRA like any built-in tool.
How much does FLUX.2 LoRA cost in Claude Code?
$0.0273 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 Claude Code plan is separate.
Do I need a fal account to use FLUX.2 LoRA in Claude Code?
No. Spiral runs FLUX.2 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 LoRA in Claude Code?
About two minutes: add the hosted server, then sign in.
Does Claude Code wait while FLUX.2 LoRA runs?
FLUX.2 LoRA runs in the background. Claude Code starts the run, checks on it and gives you the image when it's ready.
What is FLUX.2 good at?
FLUX.2 is useful for realistic product imagery, editorial scenes, and designs that include text. Specify the materials, lighting, composition, and exact wording you want.
How large can FLUX.2 images be?
These FLUX.2 tools support dimensions from 512 to 2048 pixels per side. A square image can reach 2048 × 2048 pixels, roughly four megapixels.
How should I write a FLUX.2 prompt?
Describe the subject, action, visual style, and setting. Use concrete details such as brushed steel, side lighting, or an overhead view.
Does FLUX.2 support negative prompts?
No. Describe the desired result positively: ask for an empty street or sharp focus instead of listing things to exclude.
How do I get readable text in FLUX.2 images?
Put the exact wording in quotation marks and describe its position and appearance. Black Forest Labs warns that text-bearing objects can produce gibberish when you leave their wording unspecified.
Start using FLUX.2 LoRA in Claude Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Claude Code:
set up https://spiral.ai/SKILL.md


