MCP / Models / LoRA training
Qwen-Image LoRA Trainer MCP: train a LoRA on your images
Qwen-Image LoRA Trainer fine-tunes a LoRA adapter on your own images for Alibaba's Qwen-Image, to teach it a style, product or character. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.
$ YOUR NEXT RUN
Any agentUse Qwen-Image LoRA Trainer 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/qwen-image-lora-trainer.md. Help me connect the FlyMy.AI MCP to this assistant, then run Qwen-Image LoRA Trainer (flymyai/qwen-image-lora-trainer) for this task: Train a LoRA with Qwen-Image LoRA Trainer on the product photos in this zip link, with the trigger word mybrand.
What Qwen-Image LoRA Trainer does
Point dataset_url at a public archive of your training images, choose a trigger_word to call the concept in prompts and set training_steps (300 by default). It returns the trained model and its config; load the adapter in Qwen-Image LoRA with lora_url_1.
Qwen-Image LoRA Trainer inputs
Every input of flymyai/qwen-image-lora-trainer as its live schema lists them. Returns config (array).
Ask your agent
Requests to paste as they are, once the FlyMy.AI MCP is connected.
flymyai/qwen-image-lora-trainerflymyai/qwen-image-lora-trainerflymyai/qwen-image-lora-trainerQwen-Image LoRA Trainer price
$2.00 per run. A run at the default settings costs $2.00. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.
Call Qwen-Image LoRA Trainer 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/qwen-image-lora-trainer",
"input": {
"trigger_word": "test-fma",
"dataset_url": "https://example.com/photo.jpg"
}
}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/qwen-image-lora-trainer/predict/async/result/?request_id=<prediction_id>.
curl -X POST https://api.flymy.ai/api/v1/flymyai/qwen-image-lora-trainer/predict/async/ \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-F 'trigger_word=test-fma' \
-F 'dataset_url=https://example.com/photo.jpg'Questions about Qwen-Image LoRA Trainer
Do I need a Alibaba API key for Qwen-Image LoRA Trainer?
No. Qwen-Image LoRA Trainer runs on FlyMy.AI's account, so you need no Alibaba key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.
How much does Qwen-Image LoRA Trainer cost?
$2.00 per run. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-09.
How do I use Qwen-Image LoRA Trainer in Claude Code, Codex or Cursor?
Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Train a LoRA with Qwen-Image LoRA Trainer on the product photos in this zip link, with the trigger word mybrand." Your agent reads the inputs with get_model_schema and runs flymyai/qwen-image-lora-trainer with run_model.
What does Qwen-Image LoRA Trainer need as input?
Qwen-Image LoRA Trainer requires trigger_word and dataset_url; it also takes 2 optional inputs, each listed on this page with its allowed values and default.
Can I call Qwen-Image LoRA Trainer from my own code?
Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/qwen-image-lora-trainer/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.