# SDXL LoRA MCP and API - Text to image by Stability AI | FlyMy.AI

> SDXL LoRA runs Stable Diffusion XL 1.0 on FlyMy.AI GPUs with LoRA adapters you link, for styles and characters the base model does not know.

Page: https://flymy.ai/mcp/models/sdxl-lora/

MCP / Models / Image generation

# SDXL LoRA MCP: custom-style images with no API key

SDXL LoRA runs Stable Diffusion XL 1.0 on FlyMy.AI GPUs with LoRA adapters you link, for styles and characters the base model does not know. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use SDXL LoRA](https://flymy.ai/mcp/models/sdxl-lora/#start) [Inputs and price](https://flymy.ai/mcp/models/sdxl-lora/#inputs)

No API key, $3.00 / hr, Text to image, Stability AI, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use SDXL LoRA in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

```
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/sdxl-lora.md. Help me connect the FlyMy.AI MCP to this assistant, then run SDXL LoRA (flymyai/sdxl-lora) for this task: Generate an product photo of a glass perfume bottle on black volcanic sand with SDXL LoRA.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/sdxl-lora.md)

## What SDXL LoRA does

Pass loras as a JSON list of adapter links with weights, pick a checkpoint_name and a sampler, and set width and height up to 2048, steps, guidance_scale, a seed and up to four images per prompt. It runs on our own GPUs and is billed by run time.

## SDXL LoRA inputs

Every input of `flymyai/sdxl-lora` as its live schema lists them. Returns `sample` (file).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/sdxl-lora/#input-prompt) `prompt` | string required Default: `a Delorean on synthwave city` |
| [#](https://flymy.ai/mcp/models/sdxl-lora/#input-negative_prompt) `negative_prompt` | string optional Default: `dull colors` |
| [#](https://flymy.ai/mcp/models/sdxl-lora/#input-height) `height` | integer optional Allowed: 256 to 2048 Default: `1024` |
| [#](https://flymy.ai/mcp/models/sdxl-lora/#input-width) `width` | integer optional Allowed: 256 to 2048 Default: `1024` |
| [#](https://flymy.ai/mcp/models/sdxl-lora/#input-num_inference_steps) `num_inference_steps` | integer optional Allowed: 10 to 100 Default: `20` |
| [#](https://flymy.ai/mcp/models/sdxl-lora/#input-guidance_scale) `guidance_scale` | number optional Allowed: 0 to 10 Default: `7.5` |
| [#](https://flymy.ai/mcp/models/sdxl-lora/#input-seed) `seed` | integer optional Allowed: -999999999999999 to 999999999999999 Default: `1645` |
| [#](https://flymy.ai/mcp/models/sdxl-lora/#input-sampler) `sampler` | string optional Default: `Euler` |
| [#](https://flymy.ai/mcp/models/sdxl-lora/#input-loras) `loras` | string optional |
| [#](https://flymy.ai/mcp/models/sdxl-lora/#input-checkpoint_name) `checkpoint_name` | string optional Default: `Original` |
| [#](https://flymy.ai/mcp/models/sdxl-lora/#input-num_images_per_prompt) `num_images_per_prompt` | integer optional Allowed: 1 to 4 Default: `1` |

## Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

**“Generate an product photo of a glass perfume bottle on black volcanic sand with SDXL LoRA.”** runs `flymyai/sdxl-lora`

**“Make three versions of a poster for a summer music festival with SDXL LoRA in one run and send me the links.”** runs `flymyai/sdxl-lora`

**“Create a pencil sketch illustration of a paper airplane flying over a city at dusk with SDXL LoRA.”** runs `flymyai/sdxl-lora`

## SDXL LoRA price

$3.00 per hour of run time, billed per second. Billed per second of run time on L4, $3.00 an hour. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

[See usage pricing →](https://flymy.ai/pricing/)

## Call SDXL LoRA from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

### From an agent, through the MCP

The agent calls `get_model_schema`, then `run_model` with:

```
{
  "endpoint_id": "flymyai/sdxl-lora",
  "input": {
    "prompt": "A ceramic mug on a sunlit kitchen counter, product photo"
  }
}
```

### From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. The answer is a `prediction_id`; read the result at `https://api.flymy.ai/api/v1/flymyai/sdxl-lora/predict/async/result/?request_id=<prediction_id>`.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/sdxl-lora/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=A ceramic mug on a sunlit kitchen counter, product photo'
```

## Questions about SDXL LoRA

**Do I need a Stability AI API key for SDXL LoRA?**

No. SDXL LoRA runs on FlyMy.AI GPUs, so you need no Stability AI key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

**How much does SDXL LoRA cost?**

$3.00 per hour of run time, billed per second. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-09.

**How do I use SDXL LoRA in Claude Code, Codex or Cursor?**

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Generate an product photo of a glass perfume bottle on black volcanic sand with SDXL LoRA." Your agent reads the inputs with get_model_schema and runs flymyai/sdxl-lora with run_model.

**What does SDXL LoRA need as input?**

SDXL LoRA requires prompt; it also takes 10 optional inputs, each listed on this page with its allowed values and default.

**Can I call SDXL LoRA from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/sdxl-lora/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

## More image generation models

Text to image: product shots, ads, posters and illustrations from a prompt, many with reference images.

### GPT Image 2.6

OpenAI's current default image model: faster than 2.5, with text that stays readable.

Text to image / from $0.009 / run

Link: https://flymy.ai/mcp/models/gpt-image-2-6/

### GPT Image 2.6 Sunburst

The precision tier of 2.6 for packaging, campaigns and detailed illustration.

Text to image / from $0.009 / run

Link: https://flymy.ai/mcp/models/gpt-image-2-6-sunburst/

### Nano Banana 2.1

Gemini's newest image model: 14 references, up to 4K, with adjustable thinking.

Text and image to image / from $0.0336 / image

Link: https://flymy.ai/mcp/models/nano-banana-2-1/

### Seedream 5.0 Pro

ByteDance's precise 5.0 tier for product shots and layouts, blending up to 10 reference images.

Text and image to image / from $0.045 / run

Link: https://flymy.ai/mcp/models/bytedance-seedream-5-0-pro/

### GPT Image 2.5

The 2.5 Flare tier: natural light and sharper detail than 2.0 at a short generation time.

Text to image / from $0.009 / run

Link: https://flymy.ai/mcp/models/gpt-image-2-5/

### GPT Image 2.5 Sunburst

The slower, more exact 2.5 tier for campaign and product imagery where detail matters.

Text to image / from $0.009 / run

Link: https://flymy.ai/mcp/models/gpt-image-2-5-sunburst/

## Go to the source

[SDXL LoRA in the playground →](https://app.flymy.ai/models/flymyai/sdxl-lora), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Image generation guide →](https://docs.flymy.ai/guides/generate-images), [Every model on FlyMy.AI →](https://flymy.ai/mcp/models/), [Every MCP in the catalog →](https://flymy.ai/mcp/#catalog), [Usage pricing →](https://flymy.ai/pricing/)

From the FlyMy.AI model catalog of 2026-11-09: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.

---

For agents: the FlyMyAI operating guide (sign up, connect, run models, tools and agents) is https://flymy.ai/skill.md, and https://flymy.ai/llms.txt lists the other pages and the documentation.