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.

$ YOUR NEXT RUN
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.
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 |
|---|---|
# prompt | string required Default: a Delorean on synthwave city |
# negative_prompt | string optional Default: dull colors |
# height | integer optional Allowed: 256 to 2048 Default: 1024 |
# width | integer optional Allowed: 256 to 2048 Default: 1024 |
# num_inference_steps | integer optional Allowed: 10 to 100 Default: 20 |
# guidance_scale | number optional Allowed: 0 to 10 Default: 7.5 |
# seed | integer optional Allowed: -999999999999999 to 999999999999999 Default: 1645 |
# sampler | string optional Default: Euler |
# loras | string optional |
# checkpoint_name | string optional Default: Original |
# 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.
flymyai/sdxl-loraflymyai/sdxl-loraflymyai/sdxl-loraSDXL 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.
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.
Go to the source
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.





