How to Use FLUX.1 Krea LoRA in VS Code
Use FLUX.1 Krea LoRA for photographic images with a trained style, brand identity, or product appearance. It adds LoRA customization to FLUX.1 Krea Dev's focus on realism and less oversaturated textures.
Prompts to try with FLUX.1 Krea LoRA in VS Code
Copy an example into VS Code, or ask in your own words.
Read the homepage copy and design notes, then use FLUX.1 Krea LoRA to create a photographic hero concept: a ceramic workshop, worn wooden table, soft side light, and open wall space on the left for the heading. Use 1280 × 1024, 28 steps, and guidance 3.5.
Read the recipe page in this project and use FLUX.1 Krea LoRA to create a 1024 × 1024 editorial food image. Describe the finished dish, a linen-covered table, an overhead camera angle, and soft window light; use 28 steps and guidance 3.5.
Use FLUX.1 Krea LoRA to create an interior concept based on the café's written design brief in this project. Show the specified materials, a view from the doorway, and late-afternoon daylight at 1280 × 1024 with 30 steps and guidance 4.
Use FLUX.1 Krea LoRA with the pretrained style LoRA specified in the project's art brief to create a 1024 × 1024 campaign concept: an unbranded canvas backpack on a weathered bench in soft morning light. Use 28 steps and guidance 3.5, then review it against the brief.
Read the portrait brief in this project and use FLUX.1 Krea LoRA to create a 1024 × 1280 editorial portrait concept with a chest-up composition, textured clothing, and side lighting. Use 32 steps and guidance 4.5; check the result against the requested details.
How to set up FLUX.1 Krea LoRA in VS Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
Use Add to VS Code on the console's Agents & MCP page, or run:
code --add-mcp '{"name":"spiral","type":"http","url":"https://api.spiral.ai/mcp"}' - Sign in
VS Code asks you to sign in when it first starts the server: sign in to Spiral and click Authorize. No API key. Run MCP: List Servers from the Command Palette to check that Spiral is running.
Use the Spiral skill
- Send VS 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.1 Krea 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-krea-lora", "input": { "prompt": "Extreme close-up of a single tiger eye, direct frontal view. Detailed iris and pupil. Sharp focus on eye texture and color. Natural lighting to capture…" } }'
Then paste one of the prompts above: VS Code finds FLUX.1 Krea LoRA on Spiral, shows the price and runs it.
FLUX.1 Krea LoRA providers and prices
Spiral runs FLUX.1 Krea LoRA through fal. Open a card for today's price, with every fee included.
$0.0455 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.1 Krea LoRA works from your prompt. Ask VS Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Number of inference steps | 1 to 50 | 28 | The number of inference steps to perform. |
| 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. | |
| Guidance scale (CFG) | 0 to 35 | 3.5 | The CFG (Classifier Free 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. |
| Number of images | 1 to 4 | 1 | The number of images to generate. This is always set to 1 for streaming output. |
| Output format | jpeg or png | jpeg | The format of the generated image. |
| Acceleration | none or regular | none | Acceleration level for image generation. 'regular' balances speed and quality. |
Every API field of FLUX.1 Krea [dev] with LoRAs · Text to Image is on its tool page: open its card above.
What can you do with FLUX.1 Krea LoRA in VS Code?
Create photographic assets from the project's written briefs, page copy, and design notes. Use FLUX.1 Krea LoRA to explore compositions, then inspect the results in the intended layout.
Editorial portrait concepts
Explore a portrait brief through descriptions of pose, clothing, camera distance, and light. Use the results to choose a direction for an article or photo shoot.
Product campaign concepts
Describe a product scene with specific materials, surfaces, and lighting. Test a relevant product LoRA when available, then review the depicted appearance against the brief.
Interior mood studies
Turn a written room concept into photographic studies of furniture, materials, and daylight. Use them to discuss atmosphere and composition.
Food editorial imagery
Develop still-life concepts for recipes or food articles by describing plating, table surfaces, camera angle, and window light.
Article header images
Create photographic illustrations from an article's theme, with deliberate space for a headline. Review the image for visual relevance before placing it.
Brand style exploration
Apply a relevant style LoRA to several written scene briefs. Compare the results for a campaign's desired texture, color treatment, and mood.
Fictional location concepts
Describe an imagined café, shop, or retreat to explore its photographic appearance. Label the result as a concept when sharing it.
More on FLUX.1 Krea LoRA and VS Code
Overview
FLUX.1 Krea LoRA in other agents
Questions about FLUX.1 Krea LoRA in VS Code
Can VS Code use FLUX.1 Krea LoRA?
Yes. Add Spiral to VS Code as an MCP server, and VS Code can find and run FLUX.1 Krea LoRA like any built-in tool.
How much does FLUX.1 Krea LoRA cost in VS Code?
$0.0455 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 VS Code plan is separate.
Do I need a fal account to use FLUX.1 Krea LoRA in VS Code?
No. Spiral runs FLUX.1 Krea 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.1 Krea LoRA in VS Code?
About two minutes: add the hosted server, then sign in.
Does VS Code wait while FLUX.1 Krea LoRA runs?
FLUX.1 Krea LoRA runs in the background. VS Code starts the run, checks on it and gives you the image when it's ready.
What is FLUX.1 Krea LoRA good at?
Its clearest fit is photographic imagery with realistic textures and less oversaturation. Try it for editorial portraits, interior concepts, and product campaign ideas.
When does a LoRA help?
Try a relevant pretrained LoRA when you need a particular style, brand identity, or product appearance. Krea notes that text prompting alone can be insufficient for the level of stylization users want.
What resolution should I start with?
Krea recommends working between 1024 and 1280 pixels. Start with a 1024 × 1024 image; treat the recommendation as a working range, not a documented maximum.
Which generation settings are worth testing first?
Start at 28 steps and guidance 3.5, then compare results within Krea's recommended ranges of 28 to 32 steps and guidance 3.5 to 5.0. Change one setting at a time so you can judge its effect.
What should I include in a prompt?
Describe the subject, framing, visible details, focus, and lighting. The documented example uses a close-up view and concrete surface details, which make a useful checklist for your own scenes.
Start using FLUX.1 Krea LoRA in VS Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into VS Code:
set up https://spiral.ai/SKILL.md


