MCP / Models / Image generation
Z-Image Turbo LoRA MCP: fast images with two LoRAs
Z-Image Turbo LoRA adds up to two LoRA adapters to Tongyi-MAI's fast 6B image model, for a trained style or character in seconds. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

$ YOUR NEXT RUN
Use Z-Image Turbo 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/z-image-turbo-lora.md. Help me connect the FlyMy.AI MCP to this assistant, then run Z-Image Turbo LoRA (flymyai/z-image-turbo-lora) for this task: Generate an product photo of a glass perfume bottle on black volcanic sand with Z-Image Turbo LoRA.
What Z-Image Turbo LoRA does
Link adapters in lora_url_1 and lora_url_2, for example ones trained with the Z-Image LoRA Trainer, and weight them with lora_scale_1 and lora_scale_2. Everything else matches Z-Image Turbo: up to 20 steps, width and height up to 4096, a seed and output_format.
Z-Image Turbo LoRA inputs
Every input of flymyai/z-image-turbo-lora as its live schema lists them. Returns image (file).
| Input | Type, values and default |
|---|---|
# prompt | string required |
# num_inference_steps | integer optional Allowed: 1 to 20 Default: 8 |
# seed | integer optional Default: 42 |
# enable_safety_checker | boolean optional Default: true |
# output_format | string optional Default: png |
# width | integer optional Allowed: 256 to 4096 Default: 1024 |
# height | integer optional Allowed: 256 to 4096 Default: 1024 |
# lora_url_1 | string optional Default: None |
# lora_scale_1 | number optional Allowed: 0.0 to 3.0 Default: 1.0 |
# lora_url_2 | string optional Default: None |
# lora_scale_2 | number optional Allowed: 0.0 to 3.0 Default: 1.0 |
Ask your agent
Requests to paste as they are, once the FlyMy.AI MCP is connected.
flymyai/z-image-turbo-loraflymyai/z-image-turbo-loraflymyai/z-image-turbo-loraZ-Image Turbo LoRA price
$0.005 per run. A run at the default settings costs $0.005. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.
Call Z-Image Turbo 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/z-image-turbo-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/z-image-turbo-lora/predict/async/result/?request_id=<prediction_id>.
curl -X POST https://api.flymy.ai/api/v1/flymyai/z-image-turbo-lora/predict/async/ \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-F 'prompt=A ceramic mug on a sunlit kitchen counter, product photo'Questions about Z-Image Turbo LoRA
Do I need a Tongyi-MAI (Alibaba) API key for Z-Image Turbo LoRA?
No. Z-Image Turbo LoRA runs on FlyMy.AI's account, so you need no Tongyi-MAI (Alibaba) key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.
How much does Z-Image Turbo LoRA cost?
$0.005 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 Z-Image Turbo 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 Z-Image Turbo LoRA." Your agent reads the inputs with get_model_schema and runs flymyai/z-image-turbo-lora with run_model.
What does Z-Image Turbo LoRA need as input?
Z-Image Turbo LoRA requires prompt; it also takes 10 optional inputs, each listed on this page with its allowed values and default.
Can I call Z-Image Turbo LoRA from my own code?
Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/z-image-turbo-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.





