[Integrations](https://spiral.ai/integrations) › [Cursor](https://spiral.ai/integrations/cursor) › [FLUX.2 Realism LoRA](https://spiral.ai/integrations/cursor/flux-2-realism-lora)

# How to Use FLUX.2 Realism LoRA in Cursor

FLUX.2 Realism LoRA creates photographic portraits, product concepts, and believable scenes from text. Its realism tuning emphasizes natural lighting and skin texture over stylized imagery.

|  |  |
| --- | --- |
| Model | FLUX.2 Realism LoRA |
| Available through | fal |
| Category | Image |
| Price | $0.0273 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. Billed on `num_images`, default 1. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with FLUX.2 Realism LoRA in Cursor

- Read the homepage brief and use FLUX.2 Realism LoRA to create a landscape photograph of a ceramic mug on a walnut desk. Put the mug on the right, with soft window light and open wall space on the left for the headline.
- Use FLUX.2 Realism LoRA to create a square product concept for the store described in this project: an amber glass soap bottle on pale stone, soft studio lighting, visible glass texture, and a plain label. Add the selected image to the product card.
- Read the article draft and use FLUX.2 Realism LoRA to make a landscape editorial concept of a bicycle mechanic at a workbench. Specify natural side light and a 35mm lens, then add it to the article preview.
- Use FLUX.2 Realism LoRA to create a portrait photograph for this project's restaurant page: a chef in a linen apron beside a kitchen window, soft daylight, visible fabric texture, and an 85mm lens. Fit it into the existing image area.
- Use FLUX.2 Realism LoRA to explore the café interior described in the design brief. Create a landscape composition with oak tables, worn leather seating, morning window light, and a 35mm camera view, then show it in the page preview.

## How to set up FLUX.2 Realism LoRA in Cursor

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the hosted server**: Use Add to Cursor on the console's Agents & MCP page, or add this to `.cursor/mcp.json` (one project) or `~/.cursor/mcp.json` (every project):

```json
{
  "mcpServers": {
    "spiral": { "url": "https://api.spiral.ai/mcp" }
  }
}
```

2. **Sign in**: Open Cursor Settings › MCP, click Connect next to spiral, sign in to Spiral and click Authorize. No API key. Spiral then shows as connected, with its tools listed.

### Use the Spiral skill

1. **Send Cursor this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run FLUX.2 Realism LoRA**: One request; the result comes back by polling or a webhook.

```bash
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-gallery/realism",
    "input": {
      "prompt": "A portrait of a woman with natural lighting"
    }
  }'
```

Then paste one of the prompts above: Cursor finds FLUX.2 Realism LoRA on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/cursor

## FLUX.2 Realism LoRA tools and prices

- [FLUX 2 Lora Gallery Realism](https://spiral.ai/tools/fal/fal-ai/flux-2-lora-gallery/realism) (fal): $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

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| image_size |  | landscape_4_3 | The size of the generated image. |
| guidance_scale | 0 to 20 | 2.5 | The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt. |
| num_inference_steps | 4 to 50 | 40 | The number of inference steps to perform. |
| acceleration | none, regular | regular | Acceleration level for image generation. 'regular' balances speed and quality. |
| seed |  | — | Random seed for reproducibility. Same seed with same prompt will produce same result. |
| output_format | png, jpeg, webp | png | The format of the output image |

## What can you do with FLUX.2 Realism LoRA in Cursor?

Turn a project's written requirements into photographic assets for websites and apps. A coding agent can read the design brief, draft images, and place selected results in the interface.

### Product photo concepts

Explore a written product idea on a tabletop, with specific materials, shadow direction, and studio lighting.

### Portrait lighting studies

Draft portraits with window light, studio light, or late-afternoon sun to compare a shoot's visual direction.

### Editorial scene concepts

Create staged photographic scenes for article illustrations, such as a quiet workshop or a neighborhood café.

### Website photography concepts

Draft photographic assets with deliberate space for headlines and subjects positioned around the planned layout.

### Food photography briefs

Explore plated-food compositions, ceramic textures, and side lighting before planning a restaurant shoot.

### Interior photography concepts

Describe a room from scratch to explore furniture materials, camera position, and daylight direction.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Cursor guides](https://spiral.ai/integrations/cursor)

## FLUX.2 Realism LoRA in other agents

- [Amp](https://spiral.ai/integrations/amp/flux-2-realism-lora)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/flux-2-realism-lora)
- [Claude](https://spiral.ai/integrations/claude-desktop/flux-2-realism-lora)
- [Claude Code](https://spiral.ai/integrations/claude-code/flux-2-realism-lora)
- [Cline](https://spiral.ai/integrations/cline/flux-2-realism-lora)
- [Codex](https://spiral.ai/integrations/codex/flux-2-realism-lora)
- [Devin](https://spiral.ai/integrations/devin/flux-2-realism-lora)
- [dots](https://spiral.ai/integrations/dots/flux-2-realism-lora)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/flux-2-realism-lora)
- [Gemini](https://spiral.ai/integrations/gemini/flux-2-realism-lora)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/flux-2-realism-lora)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/flux-2-realism-lora)
- [goose](https://spiral.ai/integrations/goose/flux-2-realism-lora)
- [Grok](https://spiral.ai/integrations/grok/flux-2-realism-lora)
- [Grok Build](https://spiral.ai/integrations/grok-build/flux-2-realism-lora)
- [Hermes](https://spiral.ai/integrations/hermes/flux-2-realism-lora)
- [Instinct](https://spiral.ai/integrations/instinct/flux-2-realism-lora)
- [Manus](https://spiral.ai/integrations/manus/flux-2-realism-lora)
- [Muse](https://spiral.ai/integrations/muse/flux-2-realism-lora)
- [Muse Code](https://spiral.ai/integrations/muse-code/flux-2-realism-lora)
- [n8n](https://spiral.ai/integrations/n8n/flux-2-realism-lora)
- [Notion](https://spiral.ai/integrations/notion/flux-2-realism-lora)
- [OpenClaw](https://spiral.ai/integrations/openclaw/flux-2-realism-lora)
- [opencode](https://spiral.ai/integrations/opencode/flux-2-realism-lora)
- [Perplexity](https://spiral.ai/integrations/perplexity/flux-2-realism-lora)
- [Raycast](https://spiral.ai/integrations/raycast/flux-2-realism-lora)
- [VS Code](https://spiral.ai/integrations/vscode/flux-2-realism-lora)
- [Windsurf](https://spiral.ai/integrations/windsurf/flux-2-realism-lora)
- [Zapier](https://spiral.ai/integrations/zapier/flux-2-realism-lora)

## More Cursor guides

- [FLUX.2 Max Edit](https://spiral.ai/integrations/cursor/flux-2-max-edit)
- [FLUX.2 Satellite View Style](https://spiral.ai/integrations/cursor/flux-2-satellite-view-style)
- [FLUX.2 Max](https://spiral.ai/integrations/cursor/flux-2-max)
- [FLUX.2 Sepia Vintage](https://spiral.ai/integrations/cursor/flux-2-sepia-vintage)
- [FLUX.2 LoRA Edit](https://spiral.ai/integrations/cursor/flux-2-lora-edit)
- [FLUX.2 Turbo](https://spiral.ai/integrations/cursor/flux-2-turbo)

## Questions about FLUX.2 Realism LoRA in Cursor

**Can Cursor use FLUX.2 Realism LoRA?**

Yes. Add Spiral to Cursor as an MCP server, and Cursor can find and run FLUX.2 Realism LoRA like any built-in tool.

**How much does FLUX.2 Realism LoRA cost in Cursor?**

$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 Cursor plan is separate.

**Do I need a fal account to use FLUX.2 Realism LoRA in Cursor?**

No. Spiral runs FLUX.2 Realism 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 Realism LoRA in Cursor?**

About two minutes: add the hosted server, then sign in.

**Does Cursor wait while FLUX.2 Realism LoRA runs?**

FLUX.2 Realism LoRA runs in the background. Cursor starts the run, checks on it and gives you the image when it's ready.

**What is FLUX.2 Realism LoRA best used for?**

Use it for photographic portraits, product concepts, and scenes where natural light and believable texture matter. Give it a concrete photographic brief with a subject, setting, and light source.

**How should I write a photographic prompt?**

Put the main subject first, followed by its action, surroundings, and lighting. Add a lens or film stock when you want a particular photographic look, such as an 85mm portrait or Kodak Portra 400 colors.

**How large can the images be?**

The published limit is 4 megapixels, with landscape, portrait, and square compositions supported. Describe the framing alongside the subject so the composition suits the intended shape.

**Which setting changes the realism treatment?**

Realism strength controls the effect, with 1 as the documented starting value. Compare different strengths while keeping the written brief unchanged to judge the treatment.

**Is it a good choice for illustration or abstract art?**

Its stated emphasis is natural lighting and skin texture over stylized imagery. That makes it a less direct fit for an illustration or abstract-art brief.

